All blog post summaries for Zilliz

Date published
Nov. 19, 2024

Author(s)
Steffi Li

Language
English

Word count
556

Hacker News points
None found.

Zilliz Cloud has released a new version with enhanced features and performance improvements. The key highlights include Cardinal, a vector search engine that delivers a 10X performance boost in production environments, and various enterprise-ready features such as multi-replica support for high-traffic applications, increased capacity of compute units by 50%, enhanced observability with Prometheus integration, simplified data migration from Qdrant and Pinecone Serverless, Auth0-based authentication system, global expansion to AWS Tokyo region, and developer experience improvements. These features are available now across all Zilliz Cloud deployments, with a free tier and 30-day enterprise trial offered.

Date published
Nov. 15, 2024

Author(s)
Benito Martin

Language
English

Word count
2764

Hacker News points
None found.

Meta has released a series of powerful open-source models called Llama, including Llama 3, Llama 3.1, and Llama 3.2 in just six months. These models are designed to narrow the gap between proprietary and open-source tools, offering developers valuable resources to push the boundaries of their projects. The recent Unstructured Data Meetup hosted by Zilliz discussed the rapid evolution of the Llama models since 2023, advancements in open-source AI, and the architecture of these models. The talk covered up to Llama 3.1, with some notes on Llama 3.2 focusing mainly on size and version differences. The Llama series is based on a decoder-only transformer architecture and can be divided into two main categories: core models and safeguards. The core models are further categorized by size and purpose, while the safeguard tools include LlamaGuard 3, Prompt Guard, CyberSecEval 3, and Code Shield. These models have been trained and fine-tuned on representative datasets and evaluated rigorously for harmful content to ensure safe and reliable use in AI applications. In addition to the core models, Meta has released specialized models like LlamaGuard to promote responsible and safe AI development. The Llama System (Llama Stack API) is a set of standard interfaces that can be used to build adapters for different applications. By providing high-performance models to the public, Meta is fostering innovation in AI and encouraging collaboration within the open-source community.

Date published
Nov. 13, 2024

Author(s)
Stephen Batifol

Language
English

Word count
1636

Hacker News points
None found.

This blog post guides users through creating a Multimodal Retrieval Augmented Generation (RAG) system using open-source solutions Milvus and vLLM. The tutorial demonstrates how to self-host an AI application, providing full control over the technology while enhancing its capabilities. By leveraging the power of an open-source vector database combined with open-source LLM inference, users can design a system capable of processing and understanding multiple types of data - text, images, audio, and even videos. The resulting multimodal RAG system is flexible, scalable, and under complete user control, mitigating risks associated with relying solely on cloud API providers.

Date published
Nov. 12, 2024

Author(s)
ShriVarsheni R

Language
English

Word count
1660

Hacker News points
None found.

Transformers4Rec is a powerful library designed for creating sequential and session-based recommendation systems with PyTorch, integrating with transformer models from natural language processing (NLP). It includes four main components—Feature Aggregation, Sequence Masking, Sequence Processing, and Prediction Head—that work together to make predictions. Transformers4Rec supports various architectures for sequence processing, including XLNet, GPT-2, and LSTM, allowing users to choose the most suitable model for their recommendation system. Evaluation metrics like precision, recall, MAP, and NDCG help evaluate system effectiveness, ensuring recommendations meet user needs. Challenges of scaling Transformers4Rec include infrastructure costs, storage needs, and handling new or frequently changing product catalogs.

Date published
Nov. 8, 2024

Author(s)
Ruben Winastwan

Language
English

Word count
2334

Hacker News points
None found.

Inkeep and Milvus have developed an AI-powered assistant to enhance interaction with technical documentation, aiming to save time for developers searching through platforms or services. The AI assistant is built using Retrieval Augmented Generation (RAG), a method that combines advanced NLP techniques such as vector search and LLMs to generate accurate answers to users' queries. Inkeep handles the ingestion and generation parts, while Zilliz provides support in the indexing and retrieval steps. The AI assistant is currently available on both the Zilliz and Milvus documentation sites.

Date published
Nov. 7, 2024

Author(s)
Jiang Chen and Victor Bian

Language
English

Word count
837

Hacker News points
None found.

Zilliz and HydroX AI have partnered to introduce PII Masker, an advanced tool designed to enhance data privacy in AI applications. The collaboration aims to protect Personally Identifiable Information (PII) during model training and inference for Generative AI (GenAI) models like Retrieval Augmented Generation (RAG). With the increasing use of unstructured data in AI, ensuring PII safety is crucial for responsible GenAI usage. PII Masker automatically detects and masks sensitive information with high precision using DeBERTa-v3 NLP model. The tool has seamlessly integrated with both Milvus and Zilliz Cloud vector databases, allowing users to build compliant GenAI applications while protecting user data. Future iterations of PII Masker will expand language support and improve the detection of contextually implied PII.

Date published
Nov. 3, 2024

Author(s)
Chloe Williams

Language
English

Word count
2321

Hacker News points
None found.

Couchbase and Chroma are both vector databases designed to store and query high-dimensional vectors, which are numerical representations of unstructured data. They play a crucial role in AI applications by enabling efficient similarity searches for tasks such as e-commerce product recommendations, content discovery platforms, anomaly detection in cybersecurity, medical image analysis, and natural language processing (NLP). Couchbase is a distributed multi-model NoSQL document-oriented database with vector search capabilities. It combines the strengths of relational databases with the versatility of JSON and provides flexibility to implement vector search despite not having native support for vector indexes. Developers can store vector embeddings within Couchbase documents as part of their JSON structure, allowing for similarity search use cases like recommendation systems or retrieval-augmented generation based on semantic search. Chroma is an open-source, AI-native vector database that simplifies the process of building AI applications by making knowledge, facts, and skills easily accessible to large language models (LLMs). It provides tools for managing vector data, allowing developers to store embeddings along with their associated metadata, which enables efficient similarity searches and data retrieval based on vector relationships. When choosing between Couchbase and Chroma, consider factors such as search methodology, data storage requirements, scalability and performance, flexibility and customization, integration and ecosystem, cost and security, and the specific needs of your application. Couchbase is a full-featured database that can include vector search capabilities with enterprise features, strong security, and proven scalability, while Chroma is simple and vector-focused, perfect for AI-first applications where vector search is the top priority.

Date published
Nov. 3, 2024

Author(s)
Chloe Williams

Language
English

Word count
2113

Hacker News points
None found.

Couchbase and Elasticsearch are both distributed databases with vector search capabilities as an add-on. Couchbase is a NoSQL document-oriented database, while Elasticsearch is a search engine based on Apache Lucene. Both can be adapted to handle vector search functionality for various AI tasks that rely on similarity searches. Elasticsearch has native vector search through Apache Lucene and uses the HNSW algorithm for efficient similarity search. It manages vector search performance through its segment-based architecture, which allows concurrent search without locks. Elasticsearch treats vector data as a native data type and automatically maintains vector indexes. Couchbase stores vectors as part of JSON documents, giving developers full control over the structure and organization of their vectors. It requires more setup for vector search integration but offers flexibility in implementation methods. Couchbase's performance for vector search varies depending on the chosen implementation method, with its core strength being efficient document storage and retrieval. The choice between Elasticsearch and Couchbase depends on technical requirements and development resources. Elasticsearch is a ready-to-use vector search solution with performance optimizations and text search integration, while Couchbase offers more flexibility and control over vector search implementation with strong distributed computing and edge capabilities.

Date published
Oct. 31, 2024

Author(s)
Tim Spann

Language
English

Word count
1420

Hacker News points
None found.

This article discusses practical applications of Multimodal Retrieval Augmented Generation (RAG) using Milvus, a vector database. It covers two Halloween-themed use cases: identifying if something is a ghost and finding the cutest cat ghost. The first application involves image search with filters and uses Ollama, LLava 7B, and LLM reranking to determine if an object is a ghost by comparing it to a database of ghost images. The second application focuses on finding the cutest cat ghost using a visualized BGE model. Both applications demonstrate how multimodal RAG can be used for various tasks beyond text-based search. Additionally, the article highlights running advanced RAG techniques locally with Milvus Lite, Ollama, and LLava 7B.

Date published
Oct. 31, 2024

Author(s)
Chloe Williams

Language
English

Word count
2084

Hacker News points
None found.

Chroma and Aerospike are two options in the vector database space. Vector databases store and query high-dimensional vectors, which represent unstructured data such as text semantics, image features, or product attributes. They enable efficient similarity searches for applications like e-commerce recommendations, content discovery platforms, cybersecurity anomaly detection, medical image analysis, and natural language processing (NLP). Chroma is an open-source, AI-native vector database that simplifies the process of building AI applications by providing tools for managing vector data. It supports various types of data and can work with different embedding models. Chroma integrates seamlessly with other AI tools and frameworks and has a commitment to ongoing development and support. Aerospike is a distributed, scalable NoSQL database that added support for vector indexing and searching. Its vector search capability uses the Hierarchical Navigable Small World (HNSW) index exclusively. Aerospike shines in scalability with its concurrent distributed indexing system and smart caching through "pre-hydration" of the index cache. When choosing between Chroma and Aerospike, consider factors such as search methodology, data handling, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, and cost considerations. For newer AI projects prioritizing development speed, Chroma is often the better choice. For enterprise applications requiring scalability and precise control, especially those already using Aerospike, AVS is likely the better fit.

Date published
Oct. 31, 2024

Author(s)
Chloe Williams

Language
English

Word count
2223

Hacker News points
None found.

Chroma and Vearch are two popular vector databases that enable efficient similarity searches in AI applications. Chroma is an open-source, AI-native vector database designed to simplify the process of building AI applications by providing tools for managing vector data and enabling efficient similarity searches. It supports various types of data and can work with different embedding models. Vearch is a tool for developers building AI applications that need fast and efficient similarity searches. It uses a hybrid search system, allowing users to combine vector similarity search with traditional database filtering. Both Chroma and Vearch have their strengths and are suitable for different use cases. When choosing between the two, consider factors such as search methodology and performance, data and storage, scalability, integrations, usability, and cost and deployment.

Date published
Oct. 31, 2024

Author(s)
Chloe Williams

Language
English

Word count
1953

Hacker News points
None found.

Chroma and Vald are two popular vector databases that offer efficient similarity searches, making them suitable for AI applications such as e-commerce product recommendations, content discovery platforms, and natural language processing tasks. Chroma is an open-source, AI-native vector database designed to simplify the process of building AI applications by providing tools for managing vector data and enabling efficient similarity searches. It supports various types of data and can work with different embedding models, allowing users to choose the best approach for their specific use case. Vald is a powerful tool for searching through massive amounts of vector data quickly and reliably. It uses the NGT algorithm for similarity searches and has features like index replication and distributed computing that make it suitable for large-scale deployments. The choice between Chroma and Vald depends on factors such as scale requirements, technical expertise, and whether simplicity or maximum performance is more important.

Date published
Oct. 25, 2024

Author(s)
Fendy Feng and Yesha Shastri

Language
English

Word count
1451

Hacker News points
None found.

Large Language Models (LLMs) are revolutionizing various industries, including tourism. GetYourGuide (GYC), an online marketplace for travel experiences, is leveraging LLMs to enhance customer experiences and streamline operations. One of the primary applications of LLMs at GYC is content translation and localization, enabling real-time translation of travel information in users' native languages. Additionally, LLMs are used for content generation and customer support through automated FAQs and multi-turn conversations. However, challenges such as hallucinations, prompt leakage, and role consistency arise when using LLMs like ChatGPT. To address these issues, Retrieval-Augmented Generation (RAG) is proposed as a solution. RAG combines an LLM, a vector database, and an embedding model to mitigate hallucinations by retrieving relevant context and feeding it to the LLM for more accurate responses. While fine-tuning a model can improve its understanding of domain-specific language, RAG offers flexibility and cost efficiency in handling diverse or dynamic queries without extensive re-training. Combining fine-tuning with RAG can result in a more robust and effective solution that meets both general and specialized requirements.

Date published
Oct. 23, 2024

Author(s)
Trevor Trinh

Language
English

Word count
1807

Hacker News points
None found.

The article discusses self-hosting large language models (LLMs) and provides actionable advice for those who prefer control and customization while trying to achieve the performance of just calling a managed API. It highlights BentoML's research insights in AI orchestration, demonstrating solutions it developed for optimizing common performance issues when self-hosting models. The article also explores how to integrate BentoML and Milvus to build more powerful GenAI applications. The LLM Doom Stack is introduced as a framework that includes data, operations, orchestration, and AI models. It explains the benefits of using vector databases like Zilliz/Milvus in various LLM-powered systems, particularly retrieval augmented generation (RAG). The article also discusses the challenges and considerations for self-hosting LLMs, such as control, customization, and long-term cost benefits. The article presents key approaches to address these challenges, including inference optimization techniques like batching requests, token streaming, quantization, kernel optimizations, and model parallelism. It also discusses scaling LLM inference with concurrency-based autoscaling, prefix caching for cost savings, and solutions to the cold start problem. Finally, the article explores integrating BentoML and Milvus for more powerful LLM applications, particularly Retrieval Augmented Generation (RAG). It provides resources for building RAG or other types of GenAI APPs using these tools.

Date published
Oct. 22, 2024

Author(s)
David Wang

Language
English

Word count
3733

Hacker News points
None found.

The rise of multimodal models has led to a shift in search methods, with multimodal retrieval gaining popularity due to its ability to combine inputs from multiple modalities such as text and images. This approach allows for more nuanced and precise ways to capture users' search intents by leveraging the strengths of both modalities. One common task within multimodal retrieval is Composed Image Retrieval (CIR), where users provide a query that includes a reference image along with a descriptive caption. This dual-input approach enables the retrieval of specific images by combining visual content with textual instructions, creating a more detailed and accurate query. Various techniques have been developed for CIR, including Pic2Word, CompoDiff, CIReVL, and MagicLens. Each of these builds on the foundational capabilities of CLIP while adopting different approaches to improve retrieval. For example, Pic2Word transforms images into text tokens embedded in a text-based search, leveraging CLIP text embeddings for highly versatile, text-driven image retrieval. CompoDiff employs text-guided denoising, refining noisy visual embeddings with text input to conditionally reconstruct image embeddings, improving search precision. MagicLens uses Transformer models to process text and images in parallel, generating a unified embedding that captures both modalities and enhances retrieval performance. Explore Our Multimodal Search Demo! We’ve developed an online demo for multimodal search powered by the Milvus vector database. In this demo, you can upload an image and input text instructions, which are processed by a composed image retrieval model to find matching images based on both visual and textual input.

Date published
Oct. 21, 2024

Author(s)
Chloe Williams

Language
English

Word count
2098

Hacker News points
None found.

MongoDB Atlas Vector Search and Vearch are two prominent databases with vector search capabilities, essential for AI applications such as recommendation engines, image retrieval, and semantic search. Both offer robust vector search features but have different strengths. MongoDB integrates well with document-based data and is a managed service within the MongoDB ecosystem, making it suitable for projects that need to combine vector similarity searches with document filtering. Vearch offers flexibility in indexing methods, hardware optimization, and scalable architecture, making it ideal for projects that need real-time indexing, can handle multiple vector fields in a single document, or require scaling out to handle massive amounts of vector data. The choice between these two should be based on the specific use case, existing infrastructure, performance requirements, and team expertise.

Date published
Oct. 21, 2024

Author(s)
Chloe Williams

Language
English

Word count
2037

Hacker News points
None found.

MongoDB and Vald are two prominent databases with vector search capabilities, essential for applications such as recommendation engines, image retrieval, and semantic search. While both offer powerful vector data handling, they have different approaches and strengths. MongoDB integrates vector search with its flexible document model, making it great for applications that require contextual searches where you need to consider both vector similarity and other document attributes. Vald is high-performance vector search for massive scale and continuous indexing, ideal for applications that have billions of vectors and need fast, efficient similarity searches. The choice between these should be based on the use case, type of data, and performance requirements.

Date published
Oct. 21, 2024

Author(s)
Chloe Williams

Language
English

Word count
1950

Hacker News points
None found.

MongoDB Atlas Vector Search and Rockset are two prominent databases with vector search capabilities, essential for applications such as recommendation engines, image retrieval, and semantic search. Both offer robust support for handling vector search but have different strengths that align with specific use cases and data handling needs. MongoDB Atlas Vector Search integrates with the existing MongoDB ecosystem and is great for applications that need vector search to be seamlessly integrated with document querying. Rockset, on the other hand, is perfect for real-time analytics and high dimensional vector search with its unique indexing approach to query fast on fast changing data. The choice between these two ultimately depends on factors such as existing infrastructure, nature of data, dimensionality of vector embeddings, and the importance of real-time analytics in an application.

Date published
Oct. 21, 2024

Author(s)
Ruben Winastwan

Language
English

Word count
3361

Hacker News points
None found.

Retrieval-Augmented Generation (RAG) is a method that improves Language Model's responses and addresses hallucinations by providing context to the LLMs. RAG consists of several components, including query processing, context chunking, context retrieval, context reranking, and response generation. The best approach for each component leads to optimal RAG performance. Query classification helps determine whether a query requires context retrieval or can be processed directly by the LLM. Chunking techniques split long input documents into smaller segments, improving the LLM's granular context understanding. Vector databases store and retrieve relevant contexts efficiently. Retrieval techniques improve the quality of fetched contexts, while reranking and repacking techniques reorder and present the most relevant contexts to the LLM. Summarization techniques condense long contexts while preserving key information. Fine-tuning an LLM is not always necessary but can be done for smaller models to improve their robustness when generating responses related to specific use cases.

Date published
Oct. 20, 2024

Author(s)
Chloe Williams

Language
English

Word count
2166

Hacker News points
None found.

MongoDB Atlas Vector Search and ClickHouse are two prominent databases with vector search capabilities, essential for applications such as recommendation engines, image retrieval, and semantic search. Both provide robust capabilities for handling vector search but have different approaches to it. MongoDB is great for handling flexible, document-based data structures and integrates well with AI services and tools. ClickHouse is best when you have massive datasets that require complex queries combining vector search with SQL filtering and aggregation. The choice between these should be driven by your use case, data types, and performance requirements.

Date published
Oct. 20, 2024

Author(s)
Chloe Williams

Language
English

Word count
2094

Hacker News points
None found.

MongoDB Atlas Vector Search and Deep Lake are two prominent databases with vector search capabilities, essential for recommendation engines, image retrieval, and semantic search. MongoDB is a NoSQL database that stores data in JSON-like documents while Deep Lake is a data lake optimized for vector embeddings. Both use the Hierarchical Navigable Small World (HNSW) algorithm for indexing and searching vector data. MongoDB Atlas Vector Search supports both Approximate Nearest Neighbor (ANN) and Exact Nearest Neighbors (ENN) search, integrates with popular AI services and tools, and allows combining vector similarity searches with traditional document filtering. It also supports hybrid search, combining vector search with full text search for more granular results. Deep Lake is designed for storing and searching vector embeddings and related metadata, including text, JSON, images, audio, and video files. It integrates seamlessly with tools like LangChain and LlamaIndex, allowing developers to easily build Retrieval Augmented Generation (RAG) applications. When choosing between MongoDB and Deep Lake as a vector search tool, consider the differences in search methodology, data types supported, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost, and security features. The choice should be guided by your specific needs and requirements.

Date published
Oct. 20, 2024

Author(s)
Chloe Williams

Language
English

Word count
2175

Hacker News points
None found.

MongoDB Atlas Vector Search and MyScale are two prominent databases with vector search capabilities, essential for applications such as recommendation engines, image retrieval, and semantic search. Both provide robust capabilities for handling vector search, but their strengths fit different scenarios and dev environments. MongoDB integrates seamlessly with your existing MongoDB deployment, has powerful vector search, and can combine vector search with document filtering. MyScale is a single platform for SQL, vector, and full-text search with flexible indexing and native SQL support for vector queries. Users should consider factors like integration with document data, SQL-based querying, types of data they're working with, and scalability needs when choosing between these two powerful but different approaches to vector search in distributed database systems.

Date published
Oct. 20, 2024

Author(s)
Chloe Williams

Language
English

Word count
2236

Hacker News points
None found.

MongoDB Atlas Vector Search and Aerospike Vector Search (AVS) are two prominent databases with vector search capabilities, essential features for AI applications such as recommendation engines, image retrieval, and semantic search. Both use the Hierarchical Navigable Small World (HNSW) algorithm for indexing and searching vector data. MongoDB Atlas Vector Search is great for applications that need a flexible data model and integration with regular queries, hybrid searches, and AI tools ecosystems. Aerospike Vector Search excels in high-performance, real-time scenarios where low latency and high throughput are key. The choice between MongoDB and Aerospike should be driven by application requirements, data complexity, performance needs, and scalability demands.

Date published
Oct. 18, 2024

Author(s)
Chloe Williams

Language
English

Word count
1954

Hacker News points
None found.

Pinecone and Aerospike are two prominent databases with vector search capabilities that play a crucial role in AI applications, such as recommendation engines, image retrieval, and semantic search. While both support vector search, they differ in their approach and features. Pinecone is a purpose-built vector database designed for machine learning applications, offering real-time updates, compatibility with ML models, and proprietary indexing techniques for fast searches. Aerospike, on the other hand, is a distributed NoSQL database that has added support for vector search as an add-on feature called Aerospike Vector Search (AVS). Pinecone's key features include real-time updates, machine learning model compatibility, metadata filtering, and serverless offering. It supports hybrid search, which combines dense and sparse vector embeddings to balance semantic understanding with keyword matching. Pinecone integrates with popular ML frameworks and cloud services, making it a complete solution for vector search in AI applications. Aerospike's AVS uses HNSW indexes for approximate nearest neighbor search and supports multiple vectors and indexes per record. It is designed for high-performance real-time applications and can handle large scale, high throughput workloads. Aerospike has flexibility in data modeling and indexing, as well as a wide range of connectors and integrations. When choosing between Pinecone and Aerospike, consider factors such as search methodology, data types, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost, and security features. Ultimately, the decision should be based on your specific use case, data types, performance requirements, and team expertise.

Date published
Oct. 18, 2024

Author(s)
Chloe Williams

Language
English

Word count
1588

Hacker News points
None found.

Pinecone and Myscale are two prominent databases with vector search capabilities that play a crucial role in AI applications such as recommendation engines, image retrieval, and semantic search. Pinecone is a purpose-built vector database while MyScale is built on ClickHouse and combines vector search and SQL analytics. Both offer robust vector search capabilities but differ in their features, performance, and ecosystems. Developers and engineers should consider factors such as search methodology, data handling, scalability, flexibility, integration, ease of use, and cost when choosing between these two powerful tools for their specific requirements.

Date published
Oct. 18, 2024

Author(s)
Chloe Williams

Language
English

Word count
1837

Hacker News points
None found.

Pinecone and Deep Lake are two prominent databases with vector search capabilities that play a crucial role in AI applications such as recommendation engines, image retrieval, and semantic search. While both offer robust vector search capabilities, they have some key differences. Pinecone is a purpose-built vector database designed for machine learning applications requiring fast vector search even with billions of vectors. It supports real-time updates, machine learning model compatibility, metadata filtering, and hybrid search. Deep Lake, on the other hand, is a specialized data lake optimized for vector embeddings that can handle multiple data types, including multimedia and has versioning for datasets. The choice between these two should be based on specific use cases, data requirements, performance needs, and preference for managed or self-hosted solutions.

Date published
Oct. 18, 2024

Author(s)
Chloe Williams

Language
English

Word count
1913

Hacker News points
None found.

Pinecone and ClickHouse are two prominent databases with vector search capabilities that play a crucial role in AI applications, such as recommendation engines, image retrieval, and semantic search. Pinecone is a purpose-built vector database designed for machine learning applications, while ClickHouse is an open-source column-oriented database with vector search capabilities as an add-on. Both databases have their unique features and strengths, making them suitable for different use cases in vector search. Pinecone uses a proprietary indexing technique for fast similarity searches across billions of vectors and supports real-time updates, machine learning model compatibility, metadata filtering, and hybrid search. It is designed for storing and querying vector embeddings and integrates with popular ML frameworks and multiple languages. Pinecone's serverless offering makes database management easy and cost-effective. ClickHouse is an open-source OLAP database that supports fast query processing, especially for large datasets. It has a SQL interface, making it powerful for combining vector search with traditional data operations like filtering and aggregation. ClickHouse also offers experimental Approximate Nearest Neighbour (ANN) indices for faster approximate matching and exact matching through linear scans with parallel processing. When choosing between Pinecone and ClickHouse, consider factors such as search method, data types, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost, and security. Ultimately, the decision should be based on your specific requirements and long-term scalability needs.

Date published
Oct. 18, 2024

Author(s)
Chloe Williams

Language
English

Word count
1726

Hacker News points
None found.

Pinecone and Vearch are two prominent databases with vector search capabilities that play a crucial role in AI applications such as recommendation engines, image retrieval, and semantic search. Both offer robust capabilities for handling vector search but have different strengths. Pinecone is great for ease of use, managed infrastructure, and strong ML ecosystem integration, while Vearch offers deployment flexibility, indexing methods, and hardware optimization. The best fit will depend on how you align their strengths with your project's needs.

Date published
Oct. 18, 2024

Author(s)
Chloe Williams

Language
English

Word count
1741

Hacker News points
None found.

Pinecone and Vald are two prominent databases with vector search capabilities that play a crucial role in AI applications, such as recommendation engines, image retrieval, and semantic search. Both databases have their own strengths and can handle large scale vector data but differ in features like search methodology, data handling, scalability, flexibility, integration, ease of use, cost, and security. Pinecone is a fully managed service with strong machine learning integration, real-time updates, hybrid search, metadata filtering, and auto scaling for large datasets. Vald is highly customizable, can handle billions of vectors, has a distributed architecture that allows concurrent indexing and searching, and works well in cloud environments. The choice between the two should be based on factors like data volume, level of control required, resources for infrastructure management, and integration with existing systems.

Date published
Oct. 18, 2024

Author(s)
Chloe Williams

Language
English

Word count
1900

Hacker News points
None found.

Pinecone and Rockset are two prominent databases with vector search capabilities that play a crucial role in AI applications such as recommendation engines, image retrieval, and semantic search. While both offer robust vector search capabilities, they have different approaches that may fit different use cases. Pinecone is designed for vector embeddings and associated metadata, works well with unstructured data converted into vector representations, and has auto-scaling to handle billions of vectors efficiently. Rockset can handle structured, semi-structured, and unstructured data, including vector embeddings, supports multiple query types out of the box, and is algorithm-agnostic, allowing users more control over search implementation. The choice between Pinecone and Rockset depends on factors such as the scale of vector data, complexity of queries, need for real-time analytics, and team expertise in database management.

Date published
Oct. 17, 2024

Author(s)
Sydney Blanchard

Language
English

Word count
518

Hacker News points
None found.

The article discusses the importance of data engineering in supporting AI projects at an enterprise level. It highlights how adhering to best practices in data engineering can help resolve common challenges associated with deploying and scaling effective AI usage. Airbyte, an open-source data movement company, enables over 20,000 data and AI professionals to manage diverse data across multi-cloud environments. Zilliz's Milvus is a high-performance, open-source vector database built for scale, which makes unstructured data searchable and helps organizations make sense of it. The article emphasizes the need for efficient handling of unstructured data in enabling AI success.

Date published
Oct. 16, 2024

Author(s)
Chloe Williams

Language
English

Word count
2211

Hacker News points
None found.

OpenSearch and ClickHouse are two prominent databases with vector search capabilities that play a crucial role in AI applications such as recommendation engines, image retrieval, and semantic search. Both databases have evolved to include vector search capabilities as an add-on. OpenSearch is built on Apache Lucene and supports various machine learning-powered methods for vector search, while ClickHouse has integrated vector search capabilities into its SQL engine. Key differences between the two include their search methodology, data handling, scalability, flexibility, integration, ease of use, cost considerations, and security features. Depending on specific application needs, developers may choose OpenSearch or ClickHouse for GenAI applications. For large-scale, high-performance vector search tasks, specialized vector databases like Milvus and Zilliz Cloud are recommended.

Date published
Oct. 16, 2024

Author(s)
Simon Mwaniki

Language
English

Word count
3865

Hacker News points
None found.

RGB-X models are advanced machine learning models in computer vision that extend traditional RGB (Red, Green, Blue) data by incorporating additional channels such as depth, infrared, or surface normals. These models have found applications across various industries and use cases, including object tracking across frames and surveying difficult terrain. Recent advancements in RGB-X model development have led to significant improvements in performance and capabilities, with challenges and considerations related to data complexity, model interpretability, and ethics and privacy. Integrating RGB-X models with vector databases like Milvus enhances their applications by enabling efficient storage, indexing, and retrieval of the rich embeddings produced by these models.

Date published
Oct. 15, 2024

Author(s)
Chloe Williams

Language
English

Word count
2155

Hacker News points
None found.

OpenSearch and Aerospike are two prominent databases with vector search capabilities that play a crucial role in AI applications such as recommendation engines, image retrieval, and semantic search. Both platforms have evolved to address modern data challenges, offering powerful and flexible solutions tailored to diverse application needs. While OpenSearch is highly scalable and excels in handling complex searches, Aerospike offers peak performance and efficient management of large data volumes. The choice between the two largely depends on specific use cases, requirements for search capabilities, performance needs, and system architecture.

Date published
Oct. 15, 2024

Author(s)
ShriVarsheni R and Fendy Feng

Language
English

Word count
2238

Hacker News points
None found.

As organizations increasingly adopt AI tools like Large Language Models (LLMs), concerns about data privacy and security are rising. To mitigate these risks, companies are exploring advanced privacy strategies such as compliant SaaS, data anonymization, local execution, in-house development, and on-prem infra agnostic solutions. PrivateGPT is a framework designed to develop context-aware LLMs with enhanced data privacy controls, offering flexibility for users to customize configurations and select the APIs or models that best meet their needs. By integrating tools like PrivateGPT with vector databases such as Milvus, businesses can create robust and efficient AI systems while upholding strict data protection standards.

Date published
Oct. 13, 2024

Author(s)
Chloe Williams

Language
English

Word count
1935

Hacker News points
None found.

OpenSearch and Deep Lake are two prominent databases with vector search capabilities that play a crucial role in AI applications such as recommendation engines, image retrieval, and semantic search. Both databases have evolved to include vector search capabilities as an add-on. OpenSearch is a robust, open-source search and analytics suite that manages diverse data types and supports various machine learning-powered search methods. Deep Lake is a specialized database system designed for handling vector and multimedia data, making it ideal for complex media search applications. Choosing between the two depends on specific application needs, such as advanced text search capabilities, scalable analytics and visualization, or robust support for storing and searching vector embeddings.

Date published
Oct. 12, 2024

Author(s)
Chloe Williams

Language
English

Word count
2105

Hacker News points
None found.

Weaviate and MyScale are two popular vector databases that offer efficient storage and retrieval of high-dimensional vectors, which are numerical representations of unstructured data. These databases play a crucial role in AI applications by enabling advanced data analysis and retrieval. While both databases have their strengths, they differ in search methodology, data handling capabilities, scalability, flexibility, integration, ease of use, and security features. Weaviate is an open-source vector database designed for simplicity and efficiency in AI application development. It supports fast and accurate similarity searches using HNSW indexing and hybrid queries that combine vector searches with traditional filters. Weaviate is suitable for projects requiring quick implementation, flexibility with different data types, and easy integration with the GenAI ecosystem. MyScale, on the other hand, is a cloud-based database built on top of ClickHouse designed for AI and machine learning workloads. It supports both structured and vector data and offers native SQL support, making it perfect for teams familiar with relational databases. MyScale's architecture can handle large datasets and high query loads, making it ideal for enterprise-level applications that require high performance analytics and machine learning workloads. When choosing between Weaviate and MyScale, consider your use cases, data types, and performance requirements. Weaviate might be suitable for teams looking for a user-friendly approach to vector search with fast similarity searches, hybrid queries, and easy integration with AI ecosystems. In contrast, MyScale may be better for organizations that need a full SQL-based solution for large-scale data processing and AI-driven analytics.

Date published
Oct. 12, 2024

Author(s)
Chloe Williams

Language
English

Word count
1895

Hacker News points
None found.

Weaviate and Rockset are two popular vector databases that offer efficient similarity searches, making them crucial in AI applications. While both have their strengths, they cater to different needs. Weaviate is an open-source vector database designed for simplifying AI application development, offering built-in vector and hybrid search capabilities, easy integration with machine learning models, and a focus on data privacy. On the other hand, Rockset is a real-time search and analytics database that excels in ingesting, indexing, and querying data in real-time. When choosing between Weaviate and Rockset, consider factors such as search methodology, data types supported, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, and security features. Ultimately, the choice should align with your project's specific needs, taking into account data volume, update frequency, query complexity, and the balance between vector and traditional search.

Date published
Oct. 12, 2024

Author(s)
Chloe Williams

Language
English

Word count
1802

Hacker News points
None found.

Weaviate and Vald are two purpose-built vector databases designed to store and query high-dimensional vectors, which represent unstructured data such as text semantics, image features, or product attributes. Both technologies enable efficient similarity searches, playing a crucial role in AI applications for advanced data analysis and retrieval. Weaviate is an open-source vector database that offers built-in vector and hybrid search capabilities, easy integration with machine learning models, and focuses on data privacy. It uses HNSW indexing to enable fast vector searches and supports combining vector searches with traditional filters for powerful hybrid queries. Weaviate is suitable for developers building AI applications, semantic search systems, or recommendation engines when working with different data types like text, images, and audio. Vald is a high-performance tool designed to handle large amounts of vector data quickly and reliably. It uses NGT for fast approximate nearest neighbor searches and can handle billions of vectors. Vald is built for scalability from the ground up, using distributed indexing so searches can continue even while the index is being updated. The choice between Weaviate and Vald depends on specific project needs such as data volume, search complexity, and integration with existing systems. For projects that require versatility and ease of integration, especially for smaller to medium-sized projects, Weaviate may be a better choice. On the other hand, if handling massive vector datasets with high performance and scalability is crucial, Vald would be more suitable.

Date published
Oct. 12, 2024

Author(s)
Chloe Williams

Language
English

Word count
1894

Hacker News points
None found.

Weaviate and Deep Lake are two popular vector databases designed to store and query high-dimensional vectors, which represent unstructured data such as text, images, audio, video, or product attributes. Both technologies play a crucial role in AI applications by enabling efficient similarity searches for advanced data analysis and retrieval. Weaviate is an open-source vector database that offers built-in vector and hybrid search capabilities, easy integration with machine learning models, and focuses on data privacy. It uses HNSW (Hierarchical Navigable Small World) indexing to enable fast and accurate similarity searches and supports combining vector searches with traditional filters for powerful hybrid queries. Deep Lake is a specialized database system designed to handle the storage, management, and querying of vector and multimedia data, such as images, audio, video, and other unstructured data types. It provides robust vector search capabilities for various data types like text, JSON, images, audio, and video files. When choosing between Weaviate and Deep Lake, consider the project requirements, data types, scalability, data complexity, integration needs, and long-term technology strategy. Weaviate is suitable for fast similarity search and hybrid queries, great for structured data, and quick AI development. In contrast, Deep Lake is ideal for unstructured multimedia data and complex deep learning scenarios with large datasets.

Date published
Oct. 12, 2024

Author(s)
Chloe Williams

Language
English

Word count
2056

Hacker News points
None found.

Weaviate and ClickHouse are two open-source vector databases with different strengths and use cases. Weaviate is designed for AI focused applications, offering built-in vector search capabilities, easy integration with machine learning models, and a focus on data privacy. It supports multi-modal data and has deep integration with the GenAI ecosystem. ClickHouse, on the other hand, is an OLAP database for real-time analytics with full SQL support and fast query processing. It can handle large vector datasets without being memory bound and supports filtering and aggregation on metadata. Weaviate is best for AI focused projects with diverse data types, while ClickHouse is great for massive datasets and powerful SQL based vector operations alongside traditional analytics.

Date published
Oct. 12, 2024

Author(s)
Chloe Williams

Language
English

Word count
1777

Hacker News points
None found.

Weaviate and Vearch are both purpose-built vector databases designed to store and query high-dimensional vectors, which represent unstructured data such as text, images, audio, or video. They enable efficient similarity searches in AI applications, playing a crucial role in tasks like recommendation systems, content discovery platforms, anomaly detection, medical image analysis, and natural language processing (NLP). Weaviate is an open-source vector database that offers built-in vector and hybrid search capabilities, easy integration with machine learning models, and focuses on data privacy. It uses HNSW indexing for fast and accurate similarity searches and supports combining vector searches with traditional filters. Weaviate is suitable for developers building AI applications, data engineers working with large datasets, and data scientists deploying machine learning models. Vearch is a tool for developers building AI applications that need fast and efficient similarity searches. It uses hybrid search capabilities to search by vectors and filter by regular data types like numbers or text. Vearch supports multiple indexing methods, including IVFPQ and HNSW, and has both CPU and GPU versions. The choice between Weaviate and Vearch depends on the specific use case, considering factors such as data types, scale, performance requirements, development resources, and integration needs. Both tools have their strengths and are suitable for different contexts.

Date published
Oct. 12, 2024

Author(s)
Stephen Batifol

Language
English

Word count
1622

Hacker News points
None found.

ColPali is a document retrieval model that uses Vision Language Models (VLMs) to index documents through their visual features, capturing both textual and visual elements. It generates ColBERT-style multi-vector representations of text and images, encoding document images directly into a unified embedding space. This approach bypasses complex extraction processes, improving retrieval accuracy and efficiency. The model is built upon Google's PaliGemma-3B model and uses a late interaction similarity mechanism to compare query and document embeddings at query time. ColPali faces challenges due to its high storage demands and computational complexity but has significant potential in transforming how we retrieve visually rich content with textual context in Retrieval Augmented Generation (RAG) systems.

Date published
Oct. 12, 2024

Author(s)
Chloe Williams

Language
English

Word count
1939

Hacker News points
None found.

OpenSearch and MyScale are two prominent databases with vector search capabilities that play a crucial role in AI applications such as recommendation engines, image retrieval, and semantic search. OpenSearch is an open-source search and analytics suite built on Apache Lucene, while MyScale is a cloud-based database built on ClickHouse designed for AI and machine learning workloads. Both offer robust search capabilities but with different focuses: OpenSearch emphasizes advanced search functionalities like vector search, semantic search, and hybrid models, whereas MyScale integrates SQL with vector and full-text searches. When selecting the right database for GenAI applications, developers should consider factors such as search methodology, data handling, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost considerations, and security features. OpenSearch is suitable for complex search needs across various data types, real-time analytics and visualization, scalable search operations, and community-driven features and support. On the other hand, MyScale is ideal for AI and machine learning workloads, unified database solutions, high-performance requirements for large datasets, and ease of use with SQL. To evaluate and compare vector databases on your own, you can use VectorDBBench, an open-source benchmarking tool designed to test the performance of different vector database systems using custom datasets.

Date published
Oct. 11, 2024

Author(s)
Stephen Batifol

Language
English

Word count
1093

Hacker News points
None found.

Milvus is an open-source vector database designed for scalable and high-performance vector search, specifically tailored for AI and large-scale data applications. It efficiently handles and searches billion-scale high-dimensional vectors, making it an excellent choice for AI-powered systems such as retrieval-augmented generation (RAG), image and video search, and recommendation engines. Milvus offers a wide range of search functionalities, including traditional full-text search, scalar filtering, hybrid search, and multimodal search capabilities. This comprehensive feature set allows Milvus to serve diverse search needs, making it a versatile and scalable platform for AI-driven and data-intensive applications.

Date published
Oct. 11, 2024

Author(s)
Chloe Williams

Language
English

Word count
2003

Hacker News points
None found.

OpenSearch and Vald are two prominent databases with vector search capabilities, essential for recommendation engines, image retrieval, and semantic search in AI-driven applications. OpenSearch is a robust open-source search and analytics suite that supports various data types and machine learning-powered search methods. Vald is a powerful tool for searching through massive amounts of vector data quickly and reliably. Comparing the two, OpenSearch offers advanced text search capabilities, real-time analytics, diverse data type handling, scalability, customization options, and an extensive integration ecosystem. It's ideal for applications requiring complex text-based querying and analysis, real-time analytics, and diverse data types. Vald is designed for high-performance vector search, efficient resource management, real-time indexing updates, and handling large volumes of high-dimensional vector data. Choosing between OpenSearch and Vald depends on the specific needs of your application, such as whether advanced text search capabilities or high-performance vector search is more critical. Additionally, users can utilize VectorDBBench to evaluate and compare vector databases based on their own datasets.

Date published
Oct. 9, 2024

Author(s)
Simon Mwaniki

Language
English

Word count
2816

Hacker News points
None found.

The semiconductor industry faces a critical shortage of specialized expertise, impacting project timelines and innovation. General-purpose AI models often fall short in specialized industrial applications. Domain-specific language models like SemiKong are being developed to address this gap by incorporating domain-specific knowledge. Aitomatic's Open Small Specialist Agents (OpenSSA) architecture leverages the deep industry knowledge embedded in SemiKong to create agentic AI systems capable of complex decision-making in semiconductor manufacturing. Milvus, a high-performance vector database, plays a crucial role in enabling advanced AI applications in industrial settings by providing efficient retrieval and storage of complex manufacturing data. The combination of domain-specific language models, agentic AI systems, and vector databases has several implications for the semiconductor industry, including addressing expertise shortages, accelerating innovation in manufacturing processes, and enhancing process optimization and efficiency.

Date published
Oct. 9, 2024

Author(s)
Chloe Williams

Language
English

Word count
2026

Hacker News points
None found.

OpenSearch and Vearch are two prominent databases with vector search capabilities, essential for recommendation engines, image retrieval, and semantic search in AI-driven applications. OpenSearch is an open-source search and analytics suite that supports a variety of machine learning-powered search methods, while Vearch specializes in fast and efficient similarity searches for AI applications. Key differences between the two include their search methodology, data handling capabilities, scalability and performance features, flexibility and customization options, integration and ecosystem support, ease of use, cost considerations, and security features. OpenSearch is ideal for comprehensive search and analytics needs, real-time data visualization, and multi-purpose applications, while Vearch is best suited for AI-driven similarity searches, hybrid search requirements, scalability in AI applications, and developer-friendly rapid AI development workflows.

Date published
Oct. 8, 2024

Author(s)
Chloe Williams

Language
English

Word count
2032

Hacker News points
None found.

OpenSearch and Rockset are two prominent databases with vector search capabilities that play a crucial role in AI applications such as recommendation engines, image retrieval, and semantic search. Both offer robust capabilities for handling vector search but have different strengths and use cases. OpenSearch is an open-source search and analytics suite that manages diverse data types and integrates machine learning-powered search methods, making it ideal for complex queries and large datasets. Rockset focuses on real-time search and analytics with advanced indexing and querying techniques, making it highly efficient in delivering up-to-the-second insights for real-time applications. The choice between OpenSearch and Rockset depends on specific needs such as data type management, scalability requirements, and the complexity of search and query needs.

Date published
Oct. 7, 2024

Author(s)
Denis Kuria

Language
English

Word count
3002

Hacker News points
None found.

In this blog post, we explored Generalized Contrastive Learning (GCL), a solution introduced by Marqo to address the limitations of traditional embedding models in modern data retrieval systems. GCL enhances these models by incorporating rank and query awareness into the training process, significantly improving the relevance and ranking of retrieval results. We discussed how GCL can be fine-tuned for specific tasks and real-world applications, such as e-commerce search optimization and academic research paper retrieval. Additionally, we examined advanced techniques in GCL that further improve performance in production environments. Finally, we looked at how to integrate GCL with Milvus, a leading vector database, to create optimized Retrieval-Augmented Generation (RAG) systems.

Date published
Oct. 7, 2024

Author(s)
Chloe Williams

Language
English

Word count
2480

Hacker News points
None found.

Annoy and Voyager are two widely used vector search tools that offer distinct advantages. Vector search is a key element in recommendation systems, image retrieval, natural language processing (NLP), and other fields where finding similarities between high-dimensional data is critical. Both libraries focus on approximate nearest neighbor search but have different strengths and use cases. Annoy is known for its speed in performing approximate nearest-neighbor searches and is particularly useful when working with large datasets where exact matches aren't as important as quickly finding "close enough" results. Voyager, on the other hand, offers more than 10 times the speed of Annoy while maintaining the same recall rate and delivers up to 50% more accuracy for the same level of speed. It is also highly memory-efficient and supports multithreaded index creation and querying, making it ideal for memory-constrained environments and large-scale data environments where multiple data types are involved.

Date published
Oct. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
1915

Hacker News points
None found.

Redis and MyScale are two options in the vector database space, designed to store and query high-dimensional vectors. Both technologies have vector search capabilities as an add-on. Redis is known for its in-memory speed and ability to combine vector similarity search with attribute filtering, making it great for applications that need low latency and real-time data processing. MyScale is a unified platform for SQL, vector, and full-text search, with strong scalability for large AI and ML workloads. It can handle diverse data types and complex queries, making it ideal for advanced analytics platforms, complex search engines, or AI-driven business intelligence tools. The choice between Redis and MyScale depends on the specific use case, data volume, query complexity, and existing infrastructure.

Date published
Oct. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
1917

Hacker News points
None found.

Redis and Deep Lake are two popular vector databases used in AI applications. Redis is an in-memory database with vector search capabilities, while Deep Lake is a data lake optimized for vector embeddings. Both technologies have their strengths and use cases. Redis is great for high performance in-memory processing and hybrid search for real time applications with structured data. On the other hand, Deep Lake is ideal for managing and querying many data types, particularly unstructured multimedia data in AI and machine learning workflows. The choice between these two technologies should be based on specific use cases, the type of data being worked with, and performance requirements.

Date published
Oct. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
1922

Hacker News points
None found.

A vector database is a type of database specifically designed to store and query high-dimensional vectors, which are numerical representations of unstructured data such as text, images, or product attributes. They play a crucial role in AI applications by enabling efficient similarity searches for advanced data analysis and retrieval. Common use cases include e-commerce recommendations, content discovery platforms, anomaly detection in cybersecurity, medical image analysis, and natural language processing tasks. pgvector is an extension for PostgreSQL that adds support for vector operations, allowing users to store and query vector embeddings directly within their PostgreSQL database. It supports both exact and approximate nearest neighbor search with two types of approximate indexes: HNSW (Hierarchical Navigable Small World) and IVFFlat (Inverted File Flat). Aerospike is a distributed, scalable NoSQL database that has added support for vector indexing and searching. Its vector capability, called Aerospike Vector Search (AVS), only supports HNSW indexes for vector search. AVS uses concurrent indexing across all nodes in the cluster and builds the index asynchronously from an indexing queue. When choosing between pgvector and Aerospike for vector search, consider factors such as search methodology, data handling, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost, and security. The choice should be based on the specific use case, existing infrastructure, data volume, and performance requirements.

Date published
Oct. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
1828

Hacker News points
None found.

Redis and Rockset are two popular vector databases that offer efficient similarity searches in high dimensional spaces, making them crucial for AI applications. While both technologies have their strengths, the choice between them depends on specific use cases. Redis is best for low latency real-time applications with simple data models, while Rockset is suitable for complex, changing data with analytics and real-time search and analytics on multiple data types. To make an informed decision, users should evaluate these databases based on their requirements, including data types, query complexity, latency, and scalability. VectorDBBench, an open-source benchmarking tool, can assist in this process by allowing users to test and compare the performance of different vector database systems using their own datasets.

Date published
Oct. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
1957

Hacker News points
None found.

Redis and Aerospike are two options in the vector database space, with each having its own strengths and weaknesses. Redis is known for its in-memory data storage and has added vector search capabilities through the Redis Vector Library. It uses FLAT and HNSW algorithms for approximate nearest neighbor search and supports hybrid search, combining vector similarity with attribute filtering. Aerospike, on the other hand, is a distributed NoSQL database that supports vector indexing and searching. Its vector capability, called Aerospike Vector Search (AVS), only uses HNSW indexes for vector search and updates vector records asynchronously across all AVS nodes in the cluster. When choosing between Redis and Aerospike for vector search, consider factors such as search methodology, data handling, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost, and security. Redis is great for applications that need real-time vector search and traditional data operations, while Aerospike is better for high scalability and performance with large datasets especially when dealing with high dimensional vectors. Ultimately, the best choice will be the one that fits your project's unique needs and long term scalability requirements.

Date published
Oct. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
1672

Hacker News points
None found.

Redis and Vearch are two popular vector databases used in AI applications. A vector database is designed to store and query high-dimensional vectors, which represent unstructured data such as text semantics or image features. They enable efficient similarity searches, crucial for tasks like recommendation systems, content discovery platforms, and natural language processing (NLP). Redis is an in-memory database with added vector search capabilities through its Redis Vector Library. It uses FLAT and HNSW algorithms for approximate nearest neighbor search and supports hybrid queries combining vector similarity and attribute filtering. Vearch is a purpose-built vector database designed for developers working on AI applications requiring fast and efficient similarity searches. It has hybrid search capability, can handle vector embeddings and regular data types in one system, and uses a cluster setup to distribute tasks and scale horizontally. When choosing between Redis and Vearch, consider factors such as search method, data handling, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost, and security. Redis is best for applications needing real-time vector search with traditional data operations, while Vearch is ideal for large-scale AI applications requiring complex similarity searches across massive data. VectorDBBench is an open-source benchmarking tool that helps users evaluate and compare the performance of different vector databases using their own datasets. It's crucial to thoroughly benchmark with specific datasets and query patterns to make informed decisions between these two powerful vector search approaches.

Date published
Oct. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
1918

Hacker News points
None found.

Redis and Vald are two popular vector databases used in AI applications. A vector database is designed to store and query high-dimensional vectors, which represent unstructured data such as text semantics or image features. They enable efficient similarity searches, making them crucial for advanced data analysis and retrieval. Redis is an in-memory database with vector search capabilities added through the Redis Vector Library. It uses FLAT and HNSW algorithms for approximate nearest neighbor search, allowing hybrid search combining vector similarity with attribute filtering. Redis supports both structured and unstructured data and can handle real-time processing. Vald is a purpose-built vector database designed for handling billions of vectors. It uses the NGT algorithm for fast similarity searches across large datasets. Vald's distributed indexing allows it to spread data across multiple machines, ensuring high availability during index updates. When choosing between Redis and Vald, consider factors such as search methodology, data handling, scalability, flexibility, integration, ease of use, cost, and security. Redis is suitable for diverse real-time applications with moderate data size, while Vald excels in massive vector datasets with high speed searches and scalability. Ultimately, the right choice depends on your specific project requirements and team expertise.

Date published
Oct. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
1754

Hacker News points
None found.

Couchbase and OpenSearch are both open source tools that can be used for vector search in AI applications. Couchbase is a distributed, multi-model NoSQL document-oriented database that allows developers to store vector embeddings within JSON documents. It supports Full Text Search (FTS) and application-level computations for vector similarity searches. OpenSearch is an open source search and analytics platform with built-in vector search capabilities through its k-NN plugin, supporting both approximate and exact k-NN search methods. Both tools have their strengths and can be used depending on the specific use case, existing tech stack, and performance requirements.

Date published
Oct. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
2016

Hacker News points
None found.

Redis and ClickHouse are two popular vector databases that offer efficient similarity searches, making them crucial in AI applications. While both have vector search capabilities, they differ in their core technologies, features, and use cases. Redis is an in-memory database with hybrid search capabilities, combining vector similarity search with traditional filtering on other attributes. It's great for real-time applications that need low latency and can handle datasets that fit in memory. ClickHouse, on the other hand, is an open-source column-oriented database designed for real-time analytics with full SQL support. It can handle large-scale vector datasets and combines vector search with metadata filtering or aggregation. The choice between Redis and ClickHouse depends on specific use cases, considering data volume, query complexity, response time, and integration requirements.

Date published
Oct. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
1746

Hacker News points
None found.

A vector database is a type of database specifically designed to store and query high-dimensional vectors, which are numerical representations of unstructured data such as text, images, or product attributes. They enable efficient similarity searches and play a crucial role in AI applications like e-commerce recommendations, content discovery platforms, cybersecurity anomaly detection, medical image analysis, and natural language processing (NLP) tasks. pgvector is an extension for PostgreSQL that adds support for vector operations, allowing users to store and query vector embeddings directly within their PostgreSQL database. It supports exact and approximate nearest neighbor search with HNSW and IVFFlat indexing methods. ClickHouse is an open-source OLAP database for real-time analytics with full SQL support and fast query processing. It has vector search functionality through SQL functions, including exact matching with parallel processing and experimental Approximate Nearest Neighbour (ANN) indices. When choosing between pgvector and ClickHouse for vector search, consider factors such as search methodology, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost, and security. Use pgvector when you're already using PostgreSQL and want to add vector search to your existing relational database setup, while ClickHouse is better for very large vector datasets with high-performance analytical processing and vector search needs.

Date published
Oct. 6, 2024

Author(s)
Yesha Shastri

Language
English

Word count
1552

Hacker News points
None found.

The integration of Milvus and Qarbine can transform the way unstructured data is analyzed, offering excellent efficiency and insight. Milvus is a leading vector database designed to store, manage, and query high-dimensional data represented as vectors, while Qarbine simplifies the analytics and reporting process by acting as a bridge between developers and analysts. The combination of these two tools can be used to create advanced Generative AI (GenAI) applications, such as Retrieval Augmented Generation (RAG), which combines retrieval-based and generation-based methods to enhance the capabilities of language models. This collaboration enhances efficiency and grants stakeholders across various departments access to harness the power of AI without needing deep technical knowledge.

Date published
Oct. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
2157

Hacker News points
None found.

HNSWlib and Voyager are both libraries designed to efficiently perform nearest-neighbor searches in high-dimensional spaces, a key component of many AI applications. While HNSWlib is known for its speed and accuracy, Spotify's Voyager addresses some limitations of HNSWlib and offers additional features such as multithreading and support for both Python and Java. The choice between the two depends on factors like data size, infrastructure requirements, and desired level of customization. Additionally, purpose-built vector databases like Milvus offer comprehensive solutions for large-scale vector data management, including persistent storage, real-time updates, and advanced querying capabilities. Benchmarking tools such as ANN benchmarks and VectorDBBench can help evaluate the effectiveness of different ANN algorithms and vector database systems.

Date published
Oct. 5, 2024

Author(s)
Chloe Williams

Language
English

Word count
1795

Hacker News points
None found.

The choice between pgvector and Rockset as a vector database depends on specific use cases, existing tech stack, data scale, real-time requirements, and search complexity. Pgvector integrates with PostgreSQL for adding vector search to existing applications, suitable for moderate scale vector search within a single database instance, and preferable for those who prefer an open source, self-hosted solution with full control. On the other hand, Rockset is designed for real-time analytics across multiple data types, ideal for large scale, distributed data environments that need to handle multiple data formats and sources, and for those who prefer a managed service that scales automatically.

Date published
Oct. 5, 2024

Author(s)
Chloe Williams

Language
English

Word count
1799

Hacker News points
None found.

Couchbase and Deeplake are two popular vector databases used in AI applications. Couchbase is a distributed, open source NoSQL document-oriented database with vector search capabilities as an add-on, while Deep Lake is a data lake optimized for vector embeddings. Both systems have their strengths and weaknesses depending on the use case, data types, and performance requirements. Couchbase excels in handling structured and semi-structured data, primarily working with JSON documents, and can store vector embeddings within these documents. It uses Full Text Search (FTS) for approximate vector search by converting vector data into searchable fields or allows developers to store raw vector embeddings with similarity calculations done at the application level. Deep Lake is designed to handle unstructured data types like images, audio, and video, alongside vector embeddings and metadata. It provides built-in support for vector operations and similarity search, making it a good fit for machine learning and AI projects focused on vector and multimedia data management. When choosing between Couchbase and Deep Lake, consider your use case, data types, performance requirements, existing infrastructure, size of your vector search operations, and team's expertise. Test both with your data and use cases to get more insight into their performance and suitability for your specific needs.

Date published
Oct. 5, 2024

Author(s)
Chloe Williams

Language
English

Word count
1837

Hacker News points
None found.

Couchbase and Singlestore are both distributed databases that offer vector search capabilities as an add-on. Couchbase is a NoSQL document-oriented database, while SingleStore is a SQL database with vector processing features. Key differences between the two include their search methodology, data handling, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost considerations, and security features. The choice between Couchbase and Singlestore depends on factors such as data types, use cases, team expertise, existing tech stack, scalability requirements, and the importance of vector search in the overall application architecture. VectorDBBench is an open-source benchmarking tool that can assist users in evaluating and comparing vector databases based on their specific datasets and query patterns.

Date published
Oct. 5, 2024

Author(s)
Chloe Williams

Language
English

Word count
1562

Hacker News points
None found.

This article compares two vector databases, pgvector and Deeplake, which are designed to store and query high-dimensional vectors that represent unstructured data such as text, images, or product attributes. Both technologies play a crucial role in AI applications by enabling efficient similarity searches for advanced data analysis and retrieval. pgvector is an extension for PostgreSQL that adds support for vector operations, allowing users to store and query vector embeddings directly within their PostgreSQL database. It supports exact and approximate nearest neighbor search algorithms with HNSW and IVFFlat indexes for approximate search. Deeplake is a specialized database system designed to handle the storage, management, and querying of vector and multimedia data, such as images, audio, video, and other unstructured data types. It can be used as a data lake and a vector store, offering seamless integration with AI/ML tools like LangChain and LlamaIndex. The key differences between the two technologies include their search methodology, data handling capabilities, scalability and performance, flexibility and customization options, integration and ecosystem support, ease of use, cost considerations, and security features. Choosing between pgvector and Deeplake depends on factors such as current infrastructure, data types, scale of vector search requirements, and need for specialized AI features. For projects that require seamless integration with PostgreSQL-based systems and moderate-sized datasets, pgvector is a suitable choice. On the other hand, Deep Lake is best suited for machine learning workflows dealing with diverse data types, especially unstructured multimedia data. The article also introduces VectorDBBench, an open-source benchmarking tool designed to compare vector database performance using custom datasets and query patterns. This can help users make informed decisions when selecting a vector database for their specific use case.

Date published
Oct. 5, 2024

Author(s)
Chloe Williams

Language
English

Word count
1628

Hacker News points
None found.

Couchbase and LanceDB are both vector databases designed to store and query high-dimensional vectors, which are numerical representations of unstructured data. They play a crucial role in AI applications by enabling efficient similarity searches for tasks such as recommendation systems or retrieval-augmented generation. While Couchbase is a distributed multi-model NoSQL document-oriented database with vector search added on, LanceDB is a serverless vector database. Couchbase allows developers to store vector embeddings within its JSON structure and perform vector search through Full Text Search (FTS) or by storing raw vector embeddings for application-level calculations. It can be used for various AI and machine learning use cases that require similarity search. LanceDB, on the other hand, is an open-source vector database for AI applications, offering both exhaustive k-nearest neighbors (kNN) and approximate nearest neighbor (ANN) search using an IVF_PQ index. It supports various distance metrics for vector similarity and can handle large scale multi modal data and embeddings. The choice between Couchbase and LanceDB depends on the specific use case, data types, performance requirements, and integration needs. Couchbase is suitable for large-scale distributed systems that require both traditional database features and vector search, while LanceDB is ideal for AI applications with a primary focus on efficient vector search operations.

Date published
Oct. 4, 2024

Author(s)
Benito Martin

Language
English

Word count
1659

Hacker News points
None found.

Recent advancements in AI have led to sophisticated Large Language Models (LLMs) with potential transformative impacts across high-stakes domains such as healthcare, financial services, and legal industries. However, their use in critical decision-making requires thorough evaluation to ensure safety, accuracy, and ethical standards. Companies like Hydrox AI and AI Alliance are working on comprehensive evaluation frameworks for LLMs tailored to sensitive environments. Safety evaluations must consider factors such as accuracy, legal regulations, and ethical responsibilities, with regular testing and improvements essential to adapt to the changing landscape. The implications of inaccurate or biased AI outputs can be critical in high-stakes environments, making robust evaluation methodologies imperative.

Date published
Oct. 3, 2024

Author(s)
Stefan Webb

Language
English

Word count
1128

Hacker News points
None found.

Open source software (OSS) relies on community contributions from developers, testers, writers, and designers to improve projects. The core team of maintainers or lead developers manage the project's direction, review contributions, ensure code quality, and make key decisions. Contributions are reviewed through issue tracking, pull requests, code reviews, feedback iterations, and automated testing before being merged into the main branch for release. To submit a pull request to an open source repository on GitHub, developers should fork the repository, clone it locally, create a new branch, make changes, commit them, push the changes to their fork, and finally create a pull request with a clear title and description. The maintainers will review the contribution and may ask for revisions or suggest improvements before merging it into the original project's codebase.

Date published
Oct. 2, 2024

Author(s)
Chloe Williams

Language
English

Word count
1837

Hacker News points
None found.

Couchbase and Vearch are both distributed databases designed to handle high-dimensional vectors, which are numerical representations of unstructured data. They play a crucial role in AI applications by enabling efficient similarity searches. While Couchbase is a general-purpose NoSQL database with vector search capabilities as an add-on, Vearch is a purpose-built vector database designed for fast and efficient similarity searches. Couchbase offers flexibility in data modeling and queries, leveraging its JSON structure, while Vearch provides built-in vector search capabilities with options to customize indexing methods and supports multiple vector fields in a single document. Both systems offer scalable solutions and have their own strengths and weaknesses depending on the use case. When choosing between Couchbase and Vearch for vector search, factors such as search methodology, data handling, scalability, flexibility, integration, ease of use, and cost should be considered. Ultimately, thorough benchmarking with specific datasets and query patterns will be essential in making an informed decision between these two powerful approaches to vector search in distributed database systems.

Date published
Oct. 2, 2024

Author(s)
Steffi Li

Language
English

Word count
2622

Hacker News points
None found.

The article presents five reasons to migrate from Milvus, an open-source vector database, to Zilliz Cloud, a fully managed service built on Milvus. These reasons include performance advantages due to advanced automation and optimization tools in Zilliz Cloud; scalability benefits provided by its cloud native architecture and elastic scaling features; superior security and compliance measures offered by Zilliz Cloud; better availability and data management capabilities; and cost-effectiveness and resource optimization features that make it a more economical choice. The article also discusses the migration process, expert support from Milvus experts, and when to consider migrating from Milvus to Zilliz Cloud.

Date published
Oct. 1, 2024

Author(s)
Chloe Williams

Language
English

Word count
1826

Hacker News points
None found.

Couchbase and Vald are two popular vector databases used in AI applications. A vector database is specifically designed to store and query high-dimensional vectors, which are numerical representations of unstructured data. Common use cases include e-commerce product recommendations, content discovery platforms, anomaly detection in cybersecurity, medical image analysis, and natural language processing (NLP) tasks. Couchbase is a distributed multi-model NoSQL document-oriented database with vector search capabilities as an add-on. It combines the best of relational databases with the flexibility of JSON and allows developers to store vector embeddings within Couchbase documents as part of their JSON structure. These vectors can be used in similarity search use cases such as recommendation systems or retrieval-augmented generation based on semantic search. Vald is a purpose-built vector database designed for handling billions of vectors and can easily grow as your needs get bigger. It uses a super quick algorithm called NGT to find similar vectors and spreads the index across different machines, allowing searches to continue even during updates. Vald also automatically backs up your index data. When selecting between Couchbase and Vald for vector search, consider factors such as search methodology, data handling, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost, and security features. Ultimately, the choice will depend on specific needs and priorities.

Date published
Oct. 1, 2024

Author(s)
Chloe Williams

Language
English

Word count
2026

Hacker News points
None found.

Couchbase and ClickHouse are both distributed databases with vector search capabilities as add-ons, but they differ in their core technologies and use cases. Couchbase is a NoSQL document-oriented database that combines the strengths of relational databases with JSON flexibility, making it suitable for diverse applications requiring both traditional database functionalities and vector search capabilities. ClickHouse is an open-source OLAP database known for its full SQL support and high-speed query processing, excelling in handling large-scale vector datasets without memory constraints and combining vector search operations with complex SQL queries. The choice between Couchbase and ClickHouse depends on factors such as dataset size, query complexity, team familiarity with SQL, and scalability requirements.

Date published
Oct. 1, 2024

Author(s)
Chloe Williams

Language
English

Word count
1991

Hacker News points
None found.

Couchbase and Aerospike are both distributed NoSQL databases with vector search capabilities, but they differ in their approach to handling vector data and their primary use cases. Couchbase is a flexible database that combines the features of relational databases with JSON support, allowing developers to implement custom vector search within a familiar environment. It's suitable for recommendation systems, content retrieval, and applications that can store and query both structured and unstructured data alongside vector embeddings. On the other hand, Aerospike excels in its dedicated high-performance vector search feature, optimized for real-time applications requiring fast and efficient processing of high dimensional vector data at scale. It's great for machine learning, artificial intelligence, and advanced analytics where similarity searches are critical. Choose Couchbase when you need a flexible database that can handle many data types and vector search alongside other database operations, while Aerospike is more suitable if high-performance vector search in real-time applications is your primary focus.

Date published
Oct. 1, 2024

Author(s)
Chloe Williams

Language
English

Word count
2100

Hacker News points
None found.

Couchbase and Rockset are both distributed databases with vector search capabilities, but they differ in their approach to handling vector data and their primary use cases. Couchbase is a flexible general-purpose NoSQL database that allows developers to implement custom vector search within a familiar environment. It's great for applications that need to balance traditional database operations with vector search and can handle diverse data types, including JSON documents. On the other hand, Rockset is designed for real-time search and analytics applications that require immediate insights from rapidly changing data. Its Converged Indexing and high-dimensional vectors make it a good choice for applications that need to process high velocity data streams and frequent updates to vector embeddings. When choosing between Couchbase and Rockset, consider your use cases, data types, performance requirements, existing infrastructure, development team's expertise, and the type of data (static vs streaming).

Date published
Oct. 1, 2024

Author(s)
Simon Mwaniki

Language
English

Word count
3342

Hacker News points
None found.

The modality gap is a significant challenge in multimodal embedding models, which are used to interpret text and images across various industries. This gap arises due to the spatial separation between embeddings from different input types, such as texts and images that are semantically similar but far apart in the vector space. Despite advancements in multimodal embedding models like OpenAI's CLIP, these models still face challenges in accurately capturing semantic relationships within data. To address this issue, JinaCLIP was developed to build upon the original CLIP architecture and improve its performance by expanding text input and using an adapted BERT v2 architecture for text encoding. The training process of JinaCLIP focuses on overcoming the challenges posed by short text inputs in image captions and introducing hard negatives, which significantly improves the model's text-only performance while maintaining strong performance in multimodal tasks. A practical example of how to build a multimodal retrieval system using Milvus, an open-source vector database, and JinaCLIP is also discussed. This system allows users to input either text or images and retrieve the most semantically relevant results from a mixed dataset. By understanding the reasons behind the modality gap and implementing strategies to mitigate its impact, multimodal retrieval systems can be optimized for more accurate and efficient performance across various applications.

Date published
Sept. 30, 2024

Author(s)
Chloe Williams

Language
English

Word count
1707

Hacker News points
None found.

Couchbase and Kdb are both distributed databases with vector search capabilities, but they differ in their core technologies and use cases. Couchbase is a NoSQL document-oriented database that can handle JSON documents with vector embeddings, making it suitable for cloud, mobile, AI, and edge computing applications requiring vector search capabilities. It offers flexibility in implementing vector search through various approaches, such as adapting Full Text Search or integrating with specialized libraries. Kdb is a time series database designed for real-time data processing without needing GPUs, handling raw data, generating vector embeddings, and running similarity searches all in real-time. It's suitable for use cases that require multi-modal performance across various data types, including streaming data and time-series. Users should evaluate these databases based on their specific use case and perform thorough benchmarking with their own datasets to make an informed decision.

Date published
Sept. 30, 2024

Author(s)
Jason Koo and Stephen Batifol

Language
English

Word count
1579

Hacker News points
None found.

This blog post details how to build a GraphRAG agent using Neo4j graph database and Milvus vector database. The agent combines the power of graph databases and vector search to provide accurate and relevant answers to user queries. In this example, we use LangGraph, Llama 3.1 8B with Ollama, and GPT-4o. The architecture of our GraphRAG agent follows three key concepts: routing, fallback mechanisms, and self-correction. These principles are implemented through a series of LangGraph components including retrieval, graph enhancement, and LLMs integration. The GraphRAG Architecture is visualized as a workflow with several interconnected nodes such as question routing, retrieval, generation, evaluation, and refinement if needed.

Date published
Sept. 30, 2024

Author(s)
Chloe Williams

Language
English

Word count
2119

Hacker News points
None found.

Couchbase and Apache Cassandra are both distributed NoSQL databases with vector search capabilities as an add-on. Couchbase is a flexible option that allows developers to implement custom vector search solutions, while Cassandra provides integrated vector search capabilities through its Storage-Attached Indexes (SAI) feature. The choice between the two depends on specific project requirements and team expertise. Couchbase is more suitable for projects that require a flexible NoSQL database with customizable vector search solutions, whereas Apache Cassandra is better suited for large-scale, distributed applications that demand native vector search functionality.

Date published
Sept. 30, 2024

Author(s)
Chloe Williams

Language
English

Word count
2007

Hacker News points
None found.

Couchbase and MyScale are two popular vector databases used in AI applications. Couchbase is a distributed, open-source NoSQL document-oriented database with vector search capabilities as an add-on. It combines the strengths of relational databases with the versatility of JSON and can be adapted to handle vector search functionality through various methods like adapting Full Text Search or integrating external libraries. MyScale is a cloud-based database solution built on ClickHouse, designed specifically for AI and machine learning workloads. It provides native vector search capabilities and supports various vector index types and similarity metrics. When choosing between Couchbase and MyScale for vector search applications, consider factors such as your specific needs, team's expertise, the importance of native vector search support, and whether you need a general-purpose database or a specialized solution for AI and analytics tasks.

Date published
Sept. 30, 2024

Author(s)
Chloe Williams

Language
English

Word count
2009

Hacker News points
None found.

Couchbase and Milvus are both distributed databases designed to handle high-dimensional vectors, which are numerical representations of unstructured data. They play a crucial role in AI applications by enabling efficient similarity searches. While Couchbase is a general-purpose NoSQL database with vector search capabilities as an add-on, Milvus is a purpose-built vector database designed specifically for vector search and similarity search at its core. Couchbase offers more flexibility as a general-purpose NoSQL database but may require additional integration with specialized libraries for vector search tasks. In contrast, Milvus provides extensive customization options for vector indexing and search algorithms, making it more efficient for native vector similarity searches. The choice between Couchbase and Milvus depends on the specific needs and project requirements of the user.

Date published
Sept. 30, 2024

Author(s)
Chloe Williams

Language
English

Word count
1931

Hacker News points
None found.

Couchbase and TiDB are both distributed databases with vector search capabilities as add-ons, making them suitable for AI applications that require efficient similarity searches. Couchbase is a NoSQL document-oriented database that can store vector embeddings within JSON structures, while TiDB is a SQL database with hybrid transactional and analytical processing (HTAP) capabilities. Key differences between the two include their search methodology, data handling, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost considerations, and security features. When choosing between Couchbase and TiDB for vector search, it's essential to evaluate your specific data management needs and existing infrastructure.

Date published
Sept. 27, 2024

Author(s)
Chris Churilo

Language
English

Word count
488

Hacker News points
None found.

Zilliz has been named a Leader in Forrester's Wave™ Vector Database Report, recognized for its cutting-edge, high-performance database for cloud scalability. The company scored highly in criteria such as vector dimensionality, indexing, performance, and scalability. As the creators of Milvus, the world's most popular open-source vector database, Zilliz is committed to innovation that benefits everyone. Their roadmap includes distributed indexing, advanced result reranking, more admin tools, data security certifications, multi-cloud support, and enhanced data intelligence.

Date published
Sept. 26, 2024

Author(s)
Fendy Feng and ShriVarsheni R

Language
English

Word count
1907

Hacker News points
None found.

Poor data curation can significantly impact AI models' performance and reliability. Organizations must shift their focus from collecting large datasets to ensuring high-quality data. Effective data curation involves organizing, managing, and preparing data for model training or labeling, ensuring it is relevant and structured for the specific task. Cleaning and refining training data at scale is a major challenge, but meticulous curation and cleaning can improve model accuracy and performance. Modern pipelines should incorporate additional stages for enhanced data curation, such as verification, cleaning, and curating before proceeding to model training. Encord offers innovative approaches to tackle common data quality challenges like duplicates, corrupted data, and noisy samples through embedding-based approaches, NLP for data curation, persistence layers, metadata validation, and data cleaning techniques.

Date published
Sept. 25, 2024

Author(s)
Stefan Webb

Language
English

Word count
484

Hacker News points
None found.

Stefan is a newly appointed Developer Advocate at Zilliz, creators of Milvus—the leading open-source vector database. He shares his journey to becoming a Developer Advocate and explains that he was inspired by the advancements in Generative AI. Stefan realized that he enjoyed face-to-face interactions and community engagement most in his previous roles, particularly in developing and managing open-source software and sharing knowledge about new technologies. At Zilliz, he is excited to contribute to the growth of the Milvus open-source community, leveraging his passion for knowledge sharing and open-source development.

Date published
Sept. 23, 2024

Author(s)
Jiang Chen and Charles Wang

Language
English

Word count
912

Hacker News points
None found.

Fivetran now supports Milvus as a destination, making it easier to onboard every data source for retrieval-augmented generation (RAG) and AI-powered search. With the integration of Fivetran's automated data movement platform and Milvus's high-performance vector database, businesses can quickly build AI-powered search tools to extract insights from their unstructured datasets. The partnership simplifies data ingestion from various sources into Milvus, allowing developers to focus on creating business value rather than managing infrastructure complexities.

Date published
Sept. 21, 2024

Author(s)
Chloe Williams

Language
English

Word count
2095

Hacker News points
None found.

Chroma and OpenSearch are two popular vector databases used in AI applications. A vector database is designed to store and query high-dimensional vectors, which represent unstructured data such as text's semantic meaning or images' visual features. These technologies play a crucial role in AI applications, enabling efficient similarity searches for advanced data analysis and retrieval. Chroma is an open-source, AI-native vector database that simplifies the process of building AI applications by providing tools for managing vector data and associated metadata. It focuses on vector similarity search for AI applications and is particularly well-suited for projects that primarily deal with vector data and require quick integration of vector search capabilities. OpenSearch is a versatile search and analytics engine derived from Elasticsearch, designed to handle full-text search, log analytics, and vector search. It supports various data types, including structured, semi-structured, and unstructured data, making it suitable for diverse applications. OpenSearch offers more extensive customization through its query DSL, scripting capabilities, and plugin system. The choice between Chroma and OpenSearch depends on the specific needs of a project or organization. Chroma is ideal for AI-centric applications that primarily rely on vector similarity search, while OpenSearch provides a more comprehensive solution for diverse search and analytics needs. Additionally, specialized vector databases like Milvus and Zilliz Cloud are better suited for large-scale, high-performance vector search tasks.

Date published
Sept. 21, 2024

Author(s)
Chloe Williams

Language
English

Word count
2626

Hacker News points
None found.

Chroma and MyScale are two popular vector databases used in AI applications. A vector database is designed to store and query high-dimensional vectors, which represent unstructured data such as text's semantic meaning or images' visual features. These databases enable efficient similarity searches, playing a crucial role in AI applications for advanced data analysis and retrieval. Chroma is an open-source, AI-native vector database that simplifies the process of building AI applications by providing tools for managing vector data and associated metadata. It supports various types of data and different embedding models, allowing users to choose the best approach for their specific use case. Chroma's API is designed to be intuitive and easy to use, reducing the learning curve for developers new to vector databases. MyScale is a cloud-based database solution built on the open-source ClickHouse database, designed specifically for AI and machine learning workloads. It can handle both structured and vector data, supporting real-time analytics and machine learning tasks. MyScale offers native SQL support, simplifying complex AI-driven queries by integrating vector search, full-text search, and traditional SQL queries in a unified system. The choice between Chroma and MyScale depends on the specific requirements of your project, including the complexity of your data operations, the size of your datasets, your team's expertise, and your long-term scalability requirements. Both technologies offer valuable tools for implementing vector search in modern AI and data-driven applications, each catering to different use cases and preferences.

Date published
Sept. 21, 2024

Author(s)
Chloe Williams

Language
English

Word count
2428

Hacker News points
None found.

Chroma and Rockset are two popular vector databases used in AI applications. A vector database is specifically designed to store and query high-dimensional vectors, which represent complex information such as text's semantic meaning or images' visual features. These technologies play a crucial role in AI applications, enabling efficient data analysis and retrieval. Chroma is an open-source, AI-native vector database that simplifies the process of building AI applications. It focuses on vector similarity search and embedding management, making it ideal for projects integrating vector search capabilities with large language models (LLMs) or AI frameworks. Chroma's API is designed to be intuitive and easy to use, offering flexible querying options. Rockset is a real-time search and analytics database designed to handle both structured and unstructured data, including vector embeddings. It supports streaming and bulk data ingestion, processing high-velocity event streams and change data capture (CDC) feeds within 1-2 seconds. Rockset's Converged Indexing technology allows for efficient handling of a wide range of query patterns out of the box. The choice between Chroma and Rockset should be driven by your project's specific requirements, such as primary use case, data types, need for real-time analytics, scale of vector operations, and your broader ecosystem of tools. For large-scale, high-performance vector search tasks, specialized vector databases like Milvus or Zilliz Cloud are recommended.

Date published
Sept. 21, 2024

Author(s)
Chloe Williams

Language
English

Word count
2322

Hacker News points
None found.

Chroma and TiDB are two popular options for handling vector data in AI applications. Chroma is an open-source, AI-native vector database that simplifies the process of building AI applications by providing tools for managing vector data and enabling efficient similarity searches. It focuses on simplicity and developer productivity, offering flexibility in terms of embedding models and data types. On the other hand, TiDB is an open-source distributed SQL database with HTAP capabilities, making it suitable for large enterprises or growing businesses that require MySQL compatibility but need to scale beyond traditional MySQL. The choice between Chroma and TiDB should be guided by specific use cases, data types, and performance requirements.

Date published
Sept. 21, 2024

Author(s)
Benito Martin

Language
English

Word count
1233

Hacker News points
None found.

The text discusses challenges in structured document data extraction at scale with large language models (LLMs). It highlights that while LLMs have advanced the ability to analyze and extract information from documents, they face notable limitations such as handling diverse data formats and varying layouts. Unstract, an open-source platform designed for unstructured data extraction and transformation into structured formats, is introduced as a solution to simplify data management by automating the structuring process. The text also explores how Unstract tackles various scenarios, including its integration with vector databases like Milvus, to bring structure to previously unmanageable data.

Date published
Sept. 20, 2024

Author(s)
Tim Mugabi

Language
English

Word count
2035

Hacker News points
None found.

Testcontainers is an open-source framework that streamlines the development of AI-powered applications by providing lightweight, modular instances of databases, browsers, message brokers, and other pre-configured dependencies that can run in a container. This reduces the operational cost of projects while encouraging experimentation and facilitating streamlined development. Testcontainers also enhances productivity by simplifying the integration of AI components within applications, allowing developers to easily make LLM calls from within the code and automating the deployment of AI models.

Date published
Sept. 19, 2024

Author(s)
Chloe Williams

Language
English

Word count
2560

Hacker News points
None found.

HNSWlib and ScaNN are two popular vector search tools used in AI applications such as recommendation systems, image retrieval, natural language processing (NLP), and more. Both libraries offer fast approximate nearest neighbor searches but differ in their methodologies, data handling approaches, scalability, and flexibility. HNSWlib is a graph-based search algorithm that performs well for mid-sized datasets and real-time applications with minimal latency. ScaNN, on the other hand, uses partitioning and quantization techniques to handle large-scale datasets efficiently while maintaining a good balance between speed and accuracy. Developers should choose HNSWlib for smaller, static datasets and faster search speeds, while ScaNN is better suited for larger datasets and applications requiring integration with TensorFlow. Additionally, purpose-built vector databases like Milvus offer comprehensive systems designed for large-scale vector data management, including features like persistent storage, real-time updates, distributed architecture, and advanced querying capabilities.

Date published
Sept. 19, 2024

Author(s)
Stephen Batifol

Language
English

Word count
1479

Hacker News points
None found.

Retrieval Augmented Generation (RAG) has evolved from a text-based technique to Multimodal RAG, which integrates different data types such as images and videos to provide more reliable knowledge to AI models. The Milvus vector database enables the storage and search of diverse data types, while NVIDIA GPUs accelerate these complex operations. Key components of a multimodal RAG pipeline include Vision Language Models (VLMs), vector databases like Milvus, text embedding models, large language models (LLMs), and orchestration frameworks. Multimodal RAG systems offer multi-format processing, image analysis via VLMs, and efficient indexing and retrieval capabilities.

Date published
Sept. 19, 2024

Author(s)
Denis Kuria

Language
English

Word count
4362

Hacker News points
None found.

In this tutorial, we will create a real-time pose estimation system using Raspberry Pi and Milvus, an open-source vector database. The system leverages edge AI processing capabilities of the Raspberry Pi to perform object detection and pose estimation on live video streams. It utilizes a YOLOv8 model for object detection and a Hailo AI accelerator for efficient inference. The processed data is then stored in Milvus, allowing for fast and accurate similarity searches. We will also demonstrate how to integrate the system with Slack for real-time notifications and updates. This tutorial assumes that you have basic knowledge of Python programming and GStreamer, a framework for building multimedia applications. Here is an overview of the steps we will follow: 1. Set up the environment and install required dependencies. 2. Create a YOLOv8 model for pose estimation. 3. Implement a callback function to process video frames using Hailo SDK. 4. Create a utility function for COCO keypoints. 5. Create the GStreamer pipeline. 6. Execute the program and observe the results. 7. Explore use cases of combining AI and vector databases. By the end of this tutorial, you will have built a real-time pose estimation system that can be easily adapted for various applications in robotics, smart cities, industrial automation, healthcare, and more.

Date published
Sept. 18, 2024

Author(s)
Benito Martin

Language
English

Word count
2562

Hacker News points
None found.

Retrieval Augmented Generation (RAG) is a powerful approach to enhance the capabilities of generative models such as OpenAI's GPT series and Google's Gemini. However, with great potential comes significant responsibility, particularly when it comes to safeguarding sensitive data and ensuring compliance with privacy regulations. Organizations increasingly rely on AI-driven solutions, making understanding the security implications of these technologies crucial. Implementing strong security measures that not only protect data but also build user trust is essential for production-ready RAG applications. Key aspects of secure and permission-aware RAG deployments include data anonymization, strong encryption, input/output validation, and robust access controls.

Date published
Sept. 18, 2024

Author(s)
Chloe Williams

Language
English

Word count
2424

Hacker News points
None found.

Faiss and ScaNN are two popular tools that offer vector search capabilities, each with distinct strengths optimized for different use cases. Faiss is designed to handle large-scale nearest neighbor searches and clustering of dense vectors, offering flexibility in choosing between exact and approximate nearest neighbor (ANN) searches. It supports GPU acceleration and various indexing methods to optimize memory usage and speed. ScaNN focuses on fast, approximate nearest neighbor searches in large-scale datasets, particularly those involving embeddings. It integrates seamlessly with TensorFlow and uses partitioning and quantization techniques to reduce the search space for faster query times. Faiss is better suited for applications requiring exact search capabilities or handling very large datasets, while ScaNN is ideal for machine learning models where fast approximate nearest neighbor searches are required.

Date published
Sept. 17, 2024

Author(s)
Simon Kiruri

Language
English

Word count
2794

Hacker News points
None found.

Large language models (LLMs) have evolved to handle more complex tasks through function calling, enabling interaction with external tools, databases, and APIs. This allows LLMs to work with real-world data and services beyond text generation. Function calling in LLMs involves a structured interaction between the model and an external API or service, allowing it to perform dynamic operations such as querying live databases, executing commands, or performing real-time calculations. The integration of function calling with other techniques like Retrieval Augmented Generation (RAG) can create more interactive systems capable of handling complex, real-world interactions in industries such as healthcare, finance, and customer service. However, challenges include ensuring security and privacy during data access, managing latency issues, and addressing ethical concerns around transparency and user consent.

Date published
Sept. 16, 2024

Author(s)
Jiang Chen and Gunther Hagleitner

Language
English

Word count
1824

Hacker News points
None found.

The article discusses the challenge of handling high-cardinality categorical data in text-to-SQL systems and how integrating vector databases with agentic workflows can address this issue. Traditional methods such as preprocessed database techniques and LLM-based translation often fall short when dealing with high-cardinality data, leading to a significant gap in translating natural language queries to accurate SQL. Vector databases like Milvus offer a solution by storing and efficiently querying high-dimensional vector representations of data, enabling semantic searches rather than keyword matches. By combining Waii's intelligent text-to-SQL capabilities with Zilliz Cloud's powerful vector storage, users can create robust, scalable, and accurate systems for handling high-cardinality categorical data in their text-to-SQL applications.

Date published
Sept. 16, 2024

Author(s)
Chloe Williams

Language
English

Word count
2568

Hacker News points
None found.

Faiss and HNSWlib are two leading vector search libraries designed to handle large-scale datasets efficiently. While both tools focus on fast, approximate nearest neighbor searches, they differ in key areas such as search methodology, data handling, scalability, and performance. Faiss offers multiple ways to perform searches, including exact brute-force methods and approximate searches using product quantization or inverted file indices. It is designed to handle large datasets efficiently by leveraging various algorithms to balance speed and accuracy. HNSWlib uses a graph-based algorithm for vector search, which creates a navigable graph where each node is connected to its nearest neighbors, forming a structure that dramatically reduces the number of comparisons needed to find approximate nearest neighbors. Faiss is better suited for large datasets and applications requiring GPU acceleration, while HNSWlib excels when search speed is the primary concern, and your dataset can fit into memory.

Date published
Sept. 15, 2024

Author(s)
Ruben Winastwan

Language
English

Word count
2308

Hacker News points
None found.

Zilliz has introduced a new offering called Zilliz Cloud Serverless that allows users to store, index, and query massive amounts of vector embeddings at only a fraction of the cost compared to in-memory vector databases. The performance of Zilliz Cloud Serverless is also very competitive with other in-memory vector databases. This serverless offering is available on major cloud providers including AWS and GCP and will be available on Azure soon. It offers up to 50x cost savings through features such as pay-as-you-go pricing and auto-scaling that adapt to various workloads. Zilliz Cloud Serverless implements four key technologies: logical clusters and auto-scaling, disaggregation of streaming and historical data, tiered storage catered to different data storage needs, and multi-tenancy and hot-cold data separation.

Date published
Sept. 15, 2024

Author(s)
Chloe Williams

Language
English

Word count
2447

Hacker News points
None found.

Annoy and ScaNN are two popular vector search tools that differ in their search methodology, data handling, scalability, performance, flexibility, integration, ease of use, cost considerations, and security features. Annoy is a lightweight library designed for fast approximate searches on large static datasets, while ScaNN is an open-source tool optimized for high-dimensional vector data in machine learning applications. Both tools have their strengths and are suitable for different use cases. When choosing between the two, consider factors such as dataset size, data dynamics, search accuracy requirements, integration with existing systems, and available computational resources.

Date published
Sept. 14, 2024

Author(s)
Yesha Shastri

Language
English

Word count
1825

Hacker News points
None found.

In August 2024, James Le from Twelve Labs presented an insightful talk on advanced video search for semantic retrieval at the Unstructured Data Meetup in San Francisco. He discussed how cutting-edge multimodal models like those developed by Twelve Labs can help machines understand videos as intuitively as humans do, and how integrating these models with efficient vector databases such as Milvus by Zilliz can create exciting applications for semantic retrieval. Video understanding involves analyzing, interpreting, and extracting meaningful information from videos using computer vision and deep learning techniques. Twelve Labs' latest state-of-the-art video foundation model, Marengo 2.6, is capable of performing 'any-to-any' search tasks, significantly enhancing video search efficiency and allowing robust interactions across different modalities. By harnessing the power of advanced multimodal embeddings and integrating it with Milvus, developers can unlock new possibilities in video content analysis by creating applications such as search engines, recommendation systems, and content-based video retrieval.

Date published
Sept. 13, 2024

Author(s)
Steffi Li

Language
English

Word count
861

Hacker News points
None found.

Zilliz has introduced comprehensive monitoring and observability features in its cloud platform to help users maintain high-performance vector database applications. The new Metrics dashboard provides a detailed view of cluster performance, including resource usage, query performance, and data metrics. Customizable alerts have also been added for organization-related matters and operational aspects of clusters. Key features include real-time monitoring, customizable dashboards, flexible alert configuration, multiple notification channels, and access to historical data. The platform is designed to be easily accessible within the Zilliz Cloud console, with additional enhancements planned for future updates.

Date published
Sept. 12, 2024

Author(s)
Ruben Winastwan

Language
English

Word count
2516

Hacker News points
None found.

NVIDIA's latest advancements in GPU-accelerated vector search through their cuVS library and CAGRA algorithm significantly improve the performance of AI applications, particularly in cases involving high recall values, high vector dimensionality, and a large number of vectors. The integration of cuVS into Milvus, a popular open-source vector database, allows for efficient scaling and improved cost-performance ratio compared to CPU-based solutions. While GPU operational costs are higher than CPUs, the performance benefits often outweigh the expenses in large-scale applications.

Date published
Sept. 11, 2024

Author(s)
Stephen Batifol

Language
English

Word count
1271

Hacker News points
None found.

Agents are AI systems capable of autonomous thought and action, distinguishing them from traditional systems. They can reason, plan, and learn to perform complex tasks beyond simple input-output responses. To effectively learn and adapt, agents need a robust memory system like Milvus, an open-source vector database that provides efficient storage, rapid vector retrieval, and scalability. By offering these capabilities, Milvus equips agents with the power to store and retrieve massive amounts of data, make smarter decisions, and learn from past interactions, ultimately improving their performance over time.

Date published
Sept. 11, 2024

Author(s)
James Luan

Language
English

Word count
1161

Hacker News points
None found.

Zilliz introduces its open-source Migration Services to address challenges in efficiently moving unstructured data across platforms, such as data fragmentation and format heterogeneity. The service is built on Apache Seatunnel and supports real-time data streaming and offline batch imports. It also simplifies unstructured data transformation and ensures end-to-end data quality with robust monitoring and alerting mechanisms. By open-sourcing Migration Services, Zilliz aims to foster an open vector data ecosystem, attract contributors, enhance cloud service offerings, and gain valuable community input for future development.

Date published
Sept. 10, 2024

Author(s)
Steffi Li

Language
English

Word count
1140

Hacker News points
None found.

Zilliz Cloud has introduced new features to enhance support for running AI workloads in production environments, including Migration Service, Fivetran Connector, Multi-replica, and Auto-scaling. These updates aim to provide developers with advanced tools to efficiently deploy and scale AI-driven applications while maintaining full ownership of their unstructured data. The new features address critical challenges such as managing large volumes of unstructured data, ensuring high performance at scale, and maintaining operational robustness in production environments.

Date published
Sept. 9, 2024

Author(s)
Chloe Williams

Language
English

Word count
1799

Hacker News points
None found.

Apache Cassandra and Rockset are two popular options for handling vector data in AI applications. Both databases have their strengths, with Cassandra excelling in managing large-scale distributed data and offering high availability, fault tolerance, and scalability across multiple data centers. On the other hand, Rockset shines in real-time search and analytics scenarios, supporting quick ingestion and indexing of high-velocity data streams, in-place updates, and flexible vector search capabilities through its Converged Indexing technology. The choice between these technologies should be driven by specific project requirements, such as the scale of data distribution needed, the importance of real-time processing, the complexity of vector operations required, and how vector search fits into the overall data architecture of the application.

Date published
Sept. 9, 2024

Author(s)
Chloe Williams

Language
English

Word count
1819

Hacker News points
None found.

Apache Cassandra and Redis are two popular options for handling vector data in AI applications. Both databases have evolved to include vector search capabilities, but they cater to different use cases and requirements. Cassandra is ideal for large-scale distributed data with strong consistency and fault tolerance across multiple data centers, while Redis excels in scenarios demanding high-speed, real-time vector operations, particularly for datasets that can fit in memory. The choice between these technologies ultimately depends on specific project requirements, such as dataset size, the need for real-time processing, scalability needs, and the complexity of your data model.

Date published
Sept. 8, 2024

Author(s)
Chloe Williams

Language
English

Word count
2254

Hacker News points
None found.

Vector search has become a crucial element in modern AI applications such as recommendation engines, image retrieval systems, and natural language processing tasks. Unlike traditional search engines that rely on keyword matching, vector search allows us to retrieve information based on vector similarity, unlocking deeper insights from unstructured data like images, audio, and text embeddings. Two standout vector search solutions are Annoy and HNSWlib. Both are designed for fast and efficient vector search, but their strengths and use cases differ, making the choice between them crucial. Annoy (Approximate Nearest Neighbors Oh Yeah) is a lightweight open-source library developed by Spotify. It is specifically designed to handle large-scale, read-heavy vector searches. Its primary advantage lies in its minimal memory consumption and simplicity, making it ideal for static datasets that don't change frequently. HNSWlib (Hierarchical Navigable Small World Library) is a high-performance, graph-based library designed for approximate nearest neighbor (ANN) search. Its search algorithm relies on building a hierarchical graph structure, where nodes represent vectors, and edges represent the proximity between them. HNSWlib is widely used for vector similarity search tasks, where the goal is to find the closest vectors (or "neighbors") to a query vector from a large dataset of high-dimensional vectors. The key differences between Annoy and HNSWlib include their search methodology, data handling capabilities, scalability and performance, flexibility and customization options, integration and ecosystem support, ease of use, and cost considerations. When choosing between the two libraries, developers should consider factors such as dataset size, update frequency, memory resources, required accuracy, and desired level of control over the search algorithm.

Date published
Sept. 8, 2024

Author(s)
Chloe Williams

Language
English

Word count
1393

Hacker News points
None found.

Apache Cassandra and Deep Lake are both robust vector databases designed to handle complex data structures like vector embeddings essential for AI applications. While Cassandra is an open-source, distributed NoSQL database system that integrates vector search through extensions, Deep Lake is a specialized database system built with a focus on vector search and management. The choice between the two depends heavily on specific application needs, such as scalability, data handling, performance, flexibility, integration, cost, and ease of use. Apache Cassandra is suitable for applications requiring massive scalability, high availability, and flexible data management, while Deep Lake is ideal for projects involving vector data, AI workflows, and large volumes of multimedia or unstructured data.

Date published
Sept. 8, 2024

Author(s)
Chloe Williams

Language
English

Word count
2324

Hacker News points
None found.

Apache Cassandra and ClickHouse are two popular options for handling vector data in AI applications. Both technologies have their strengths, with Cassandra excelling at large-scale, distributed systems that prioritize high availability and fault tolerance, while ClickHouse shines in environments requiring fast, real-time analytics on large datasets with advanced query capabilities. The choice between the two depends on specific use cases and requirements for handling vector data efficiently.

Date published
Sept. 8, 2024

Author(s)
Chloe Williams

Language
English

Word count
2009

Hacker News points
None found.

Apache Cassandra and TiDB are both scalable distributed databases that can handle large datasets, but they differ in their core architecture and how they handle vector search functionality. Cassandra is a NoSQL database designed to handle massive amounts of unstructured or semi-structured data with its flexible schema, while TiDB is an open-source SQL database offering hybrid transactional and analytical processing (HTAP) capabilities. Both systems support vector search through integration with external libraries and plugins, but specialized vector databases like Milvus and Zilliz Cloud are better suited for large-scale, high-performance vector search tasks. When choosing between Cassandra and TiDB for vector search, consider factors such as data handling, scalability, flexibility, integration, ease of use, cost, and security features.

Date published
Sept. 8, 2024

Author(s)
Simon Kiruri

Language
English

Word count
2332

Hacker News points
None found.

Load testing is crucial when building applications with large language models (LLMs) to ensure they can handle varying demand levels and maintain performance under different conditions. This approach helps identify potential bottlenecks and areas for improvement, ensuring the application remains reliable and responsive. Gatling, an open-source performance-testing framework, can be used to load test javascript web applications and LLM APIs like RAG apps powered by vector databases like Milvus. Load testing involves capacity tests, stress tests, and soak tests to evaluate the system's behavior under specific load conditions, identify bottlenecks, and improve performance, load, and response times.

Date published
Sept. 7, 2024

Author(s)
Chloe Williams

Language
English

Word count
1841

Hacker News points
None found.

Apache Cassandra and Vald are two popular options for handling vector data in AI applications. Cassandra is a traditional NoSQL database that has evolved to include vector search capabilities, while Vald is a purpose-built vector database designed from the ground up for efficient similarity searches. Both systems offer robust scalability but through different mechanisms: Cassandra provides a masterless architecture with tunable consistency, while Vald distributes vector indexes across multiple agents and supports horizontal scaling of memory and CPU resources. The choice between these technologies depends on specific use cases, data types, and performance requirements.

Date published
Sept. 7, 2024

Author(s)
Chloe Williams

Language
English

Word count
1845

Hacker News points
None found.

Apache Cassandra and Qdrant are two popular options for handling vector data in AI applications. While both support vector search capabilities, they cater to different use cases. Cassandra is a distributed NoSQL database known for its scalability and availability, with vector search implemented as an extension of its existing architecture. On the other hand, Qdrant is a purpose-built vector database designed specifically for similarity search and machine learning applications. Key differences between the two include their search methodology, data handling capabilities, scalability and performance optimization, flexibility and customization options, integration with ecosystems, ease of use, cost considerations, and security features. The choice between these technologies ultimately depends on specific use cases, scale of vector data operations, and how they fit into an overall data architecture.

Date published
Sept. 7, 2024

Author(s)
Chloe Williams

Language
English

Word count
2097

Hacker News points
None found.

Apache Cassandra and Vespa are two popular options for handling vector data in AI applications. While both databases offer scalability, performance, and flexibility, they differ in their approach to search methodology, data handling, and ecosystem integration. Cassandra is best suited for large-scale distributed data applications with basic vector search functionality, while Vespa excels in search-heavy applications requiring advanced multi-modal search capabilities. Choosing between the two depends on whether your focus is distributed data management or powerful, real-time search capabilities.

Date published
Sept. 7, 2024

Author(s)
Chloe Williams

Language
English

Word count
1919

Hacker News points
None found.

Apache Cassandra and MongoDB are two leading NoSQL databases known for their scalability and flexibility, but they have fundamental differences that influence their suitability for different workloads. Both databases can handle vector search tasks, but specialized vector databases like Milvus and Zilliz Cloud offer better performance for large-scale, high-performance vector search tasks. Apache Cassandra is better for environments requiring high availability, fault tolerance, and massive scalability, particularly for write-heavy workloads. MongoDB offers more flexibility in handling unstructured data, real-time performance, and ease of use, making it a strong choice for AI applications that require similarity searches, recommendation engines, or NLP.

Date published
Sept. 7, 2024

Author(s)
Chloe Williams

Language
English

Word count
2160

Hacker News points
None found.

Apache Cassandra and Faiss are two technologies that handle vector data differently. While both can perform vector searches, they approach the task from different angles. Apache Cassandra is a distributed NoSQL database designed to handle large-scale structured data across many servers, ensuring high availability and scalability. It can be extended for vector search through integrations with vector search libraries or custom plugins like the DataStax integration. Faiss (Facebook AI Similarity Search) is an open-source library that provides highly efficient tools for fast similarity search and clustering of dense vectors, designed for large-scale nearest neighbor search in high-dimensional vector spaces. Key differences between the two include their search methodology, data handling capabilities, scalability and performance, flexibility and customization, integration and ecosystem support, ease of use, cost considerations, and security features. Apache Cassandra is suitable when vector search is not the primary focus, while Faiss is a better fit for high-performance vector search tasks. For large-scale, high-performance, and production vector search tasks, specialized vector databases like Milvus and Zilliz Cloud are recommended.

Date published
Sept. 7, 2024

Author(s)
Chloe Williams

Language
English

Word count
2009

Hacker News points
None found.

Apache Cassandra and Elasticsearch are both traditional databases that have evolved to include vector search capabilities, making them suitable options for applications involving AI-driven tasks such as recommendation systems, image recognition, and natural language processing. While both technologies support vector search, they differ significantly in how they handle data, scale, and perform. Apache Cassandra is optimized for handling structured and semi-structured data with a strong focus on write-heavy workloads, while Elasticsearch excels at handling unstructured and semi-structured data, particularly in scenarios where real-time indexing and retrieval are needed. Both technologies have robust communities and ecosystems, but their ease of use, cost considerations, and security features vary. Apache Cassandra is a better choice when managing large-scale, distributed data with high write throughput and fault tolerance, while Elasticsearch is the go-to solution for real-time search and analytics, particularly when handling unstructured data or complex queries. For applications that rely on fast, accurate similarity searches over millions or billions of high-dimensional vectors, specialized vector databases like Milvus and Zilliz Cloud are a better fit.

Date published
Sept. 7, 2024

Author(s)
Ruben Winastwan

Language
English

Word count
2739

Hacker News points
None found.

Time series analysis plays a crucial role in many fields, particularly in Internet of Things (IoT) devices. With time series data, we can detect patterns and trends over particular periods, enabling us to forecast and analyze future time-dependent events. Common examples of time series use cases include forecasting weather temperatures and stock prices and monitoring sensor data. InfluxDB is a highly optimized time series database for storing vast amounts of time series data. It offers efficient solutions for operations such as aggregations and downsampling. However, relying on time-series databases alone can be challenging, especially if our use case demands us to perform a similarity search. In a recent talk at the Zilliz Unstructured Data Meetup, Zoe Steinkamp, Developer Advocate at InfluxDB, discussed an approach to combining InfluxDB with Milvus to store, query, and perform similarity searches on time-dependent use cases. Milvus is a vector database that stores data in vectors, enabling efficient similarity searches using techniques like cosine similarity or Euclidean distance. By combining the two databases, the strengths of both systems can be fully utilized. As you can see in the example above, time series data from sensors can be stored in InfluxDB, while vector data can be stored in Milvus. This integration allows for advanced use cases like anomaly detection in real-time traffic conditions.

Date published
Sept. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
2089

Hacker News points
None found.

Apache Cassandra and Milvus are both vector databases designed to handle high-dimensional vectors, which are numerical representations of unstructured data like text, images, and videos. They differ in their search methodology, data handling capabilities, scalability, flexibility, integration with other tools, ease of use, and cost considerations. Milvus is a specialized vector database designed for high-performance vector search and supports at least 11 indexing methods. It is suitable for AI-centric applications that rely on fast, accurate similarity searches over large volumes of high-dimensional vectors. Milvus offers three deployment options: Milvus Lite, Standalone, and Distributed. On the other hand, Apache Cassandra is a distributed NoSQL database known for its high availability, fault tolerance, and scalability across large clusters. It has added vector search capabilities through DataStax but remains primarily focused on traditional data management. Cassandra's strengths include linear scalability, handling various data types, and integrating with popular big data tools. The choice between Milvus and Apache Cassandra depends on the specific use case and the complexity of the data. Milvus is better suited for AI-heavy applications that require fast vector search capabilities, while Cassandra offers more versatility for environments where vector search is an add-on rather than the core focus.

Date published
Sept. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
1917

Hacker News points
None found.

Apache Cassandra and Vearch are two popular options for handling vector data in AI applications. While both technologies offer strong scalability, they differ in their approach to vector search and data handling. Cassandra is a NoSQL database designed to handle structured and semi-structured data efficiently, with the addition of vector search capabilities through its Storage-Attached Indexes (SAI) feature. Vearch, on the other hand, is purpose-built for vector search and offers hybrid search capabilities, allowing users to perform complex queries that combine similarity searches with traditional filtering. When choosing between these two technologies, consider your specific needs in terms of data management, scalability, performance, and flexibility.

Date published
Sept. 6, 2024

Author(s)
Chloe Williams

Language
English

Word count
1935

Hacker News points
None found.

Apache Cassandra and MyScale are two popular databases that offer vector search capabilities, but they have different strengths. Apache Cassandra is an open-source NoSQL database designed to handle large amounts of structured data across multiple servers, while MyScale is built on the ClickHouse database for AI and machine learning workloads. Both can perform vector search, but MyScale has native support for it, making it more straightforward to use for AI-heavy workloads. Cassandra excels in environments where scalability and high availability are critical, while MyScale is better suited for applications that rely heavily on vector search and real-time data processing. For large-scale, high-performance vector search tasks, specialized vector databases like Milvus and Zilliz Cloud are recommended.

Date published
Sept. 6, 2024

Author(s)
Fendy Feng

Language
English

Word count
1831

Hacker News points
None found.

Multimodal architectures are gaining prominence in Generative AI (GenAI) as organizations increasingly build solutions using multimodal models such as GPT-4V and Gemini Pro Vision. These models can semantically embed and interpret various data types, making them more versatile and effective than traditional large language models across a broader range of applications. However, challenges arise in ensuring their reliability and accuracy due to hallucinations where they produce incorrect or irrelevant outputs. Multimodal Retrieval Augmented Generation (RAG) addresses these limitations by enriching models with relevant contextual information from external sources. Evaluation tools like Trulens help developers monitor performance, test reliability, and identify areas for improvement in multimodal RAG systems to ensure accuracy and relevance while minimizing hallucinations.

Date published
Sept. 5, 2024

Author(s)
Chloe Williams

Language
English

Word count
1518

Hacker News points
None found.

Apache Cassandra and Pinecone are two popular vector databases used in AI applications. While both can handle large amounts of data, they differ in their approach to vector search. Cassandra is an open-source database that has evolved to include vector search capabilities, while Pinecone is a proprietary SaaS built specifically for vector search. Cassandra's main advantage lies in its flexibility and ability to handle various types of data, including vectors. It also benefits from being part of the Apache ecosystem, which includes other popular tools like Spark and Hadoop. However, it can be complex to set up and manage, especially for those new to distributed systems. On the other hand, Pinecone is simpler to start with as a managed service that handles infrastructure and security. It's designed to work easily with machine learning frameworks and cloud services, making it an attractive choice for developers focusing on vector search performance. However, its specialized nature means less room for customization compared to Cassandra. The best choice between the two depends on specific project needs and team capabilities. Factors such as open-source availability, customization requirements, and expertise in managing distributed systems should be considered when making a decision.

Date published
Sept. 5, 2024

Author(s)
Chloe Williams

Language
English

Word count
2533

Hacker News points
None found.

In this blog post, we explored two powerful vector search tools, Annoy and Faiss, which are popular in high-dimensional data applications such as natural language processing (NLP), semantic search, or image retrieval. We clarified what vector search is and provided an overview of various solutions available on the market for performing vector searches. Annoy is an open-source library developed by Spotify that focuses on speed and memory efficiency for static data. It uses a method based on random projection trees to quickly find items similar to a given query item, making it suitable for applications where speed is critical and exact results aren't necessary. Annoy is widely praised for its simplicity, speed, and ease of use, especially for developers needing a fast static data search tool. Faiss is an open-source library developed by Meta (formerly Facebook) that provides highly efficient tools for fast similarity search and clustering of dense vectors. Faiss is designed for large-scale nearest-neighbor search and can handle both approximate and exact searches in high-dimensional vector spaces. It stands out for its ability to leverage GPU acceleration, providing a major boost in performance for large-scale applications. When deciding between Annoy and Faiss, several key factors must be considered, including search methodologies, data handling, performance, and scalability. While both tools perform well in terms of scalability, they are built with different goals in mind. Vector search libraries like Annoy and Faiss focus solely on search algorithms and require the developer to manage all other aspects, such as data storage, scalability, and infrastructure. In contrast, purpose-built vector databases like Milvus and Zilliz Cloud provide a more comprehensive solution, including data storage, scaling, indexing, replication, and query management. To ensure your search algorithm returns accurate results and does so at lightning speed, we need a benchmarking tool. Two efficient tools are ANN Benchmarks and VectorDBBench, which allow developers to measure metrics like search speed, accuracy, and memory usage across various datasets. By using these tools, you can assess the trade-offs between speed and precision for algorithms like those found in libraries such as Faiss, Annoy, HNSWlib, and others.

Date published
Sept. 5, 2024

Author(s)
Chloe Williams

Language
English

Word count
1518

Hacker News points
None found.

Apache Cassandra and Pinecone are two popular vector databases that differ in their approach and capabilities. Cassandra is an open-source distributed database designed to handle large amounts of data across multiple computers, while Pinecone is a proprietary SaaS built specifically for vector search. Both can handle lots of data but in different ways: Cassandra allows users to add more machines to handle more data, and being open-source, developers have full control over this process; Pinecone handles scaling as a managed service. Apache Cassandra is good if you need to handle various types of data, not just vectors, and want control over your infrastructure or are already using other Apache tools. On the other hand, consider Pinecone when focusing on vector search without managing infrastructure, wanting to get started quickly, or needing a system that's easy to use with machine learning models.

Date published
Sept. 5, 2024

Author(s)
Haziqa Sajid

Language
English

Word count
2136

Hacker News points
None found.

Embedding models and vector embeddings are crucial in handling vast amounts of unstructured data, particularly when dealing with modern datasets that require understanding meaning and context. These models transform unstructured data into numerical representations, enabling computers to understand, process, and analyze it more effectively. They capture the relationships and meanings within the data, allowing for tasks like question-answering, translation, and summarization. Advanced embedding models can handle multiple languages and data types such as text, images, and audio, making them important in building modern search systems that understand and retrieve relevant content using meaning rather than keywords.

Date published
Sept. 4, 2024

Author(s)
Chloe Williams

Language
English

Word count
1932

Hacker News points
None found.

Apache Cassandra and pgvector are two popular options in the vector database space. Both technologies have evolved from traditional databases to include vector search capabilities, enabling efficient similarity searches on high-dimensional data. Key differences between them include their search methodology, data handling, scalability, flexibility, integration, ease of use, cost considerations, and security features. Cassandra is well-suited for large-scale systems that require distributed architecture and vector similarity searches at scale, while pgvector offers a more accessible entry point into vector search for teams already familiar with relational databases. The choice between these technologies should depend on specific use cases, data volume, existing technology stack, and team expertise.

Date published
Sept. 4, 2024

Author(s)
Benito Martin

Language
English

Word count
2481

Hacker News points
None found.

The concept of Compound AI Systems is introduced by Bill Zhang, Director of Engineering at Zilliz, in his talk on the evolution of LLM app architectures. This modular approach integrates multiple components to handle various tasks rather than relying on a single AI model, delivering more tailored and efficient results. The architecture development of LLM applications is discussed, along with the concepts of Retrieval Augmented Generation (RAG) and Agentic RAG. Challenges and benefits of these systems are also highlighted. An example of building an Agentic RAG using Claude 3.4 Sonnet, LlamaIndex, and Milvus vector database is provided in a step-by-step manner. The complete architecture of the agentic RAG built with Milvus, LlamaIndex, and Cluade 3.5 Sonnet is also presented.

Date published
Sept. 4, 2024

Author(s)
Chloe Williams

Language
English

Word count
1932

Hacker News points
None found.

Apache Cassandra and pgvector are two options in the vector database space. A vector database is specifically designed to store and query high-dimensional vectors, which are numerical representations of unstructured data. These databases play a crucial role in AI applications, allowing for more advanced data analysis and retrieval. Both technologies continue to evolve, so it's worth monitoring their progress as you make your decision. Consider Cassandra when handling very large amounts of data across a distributed system, while pgvector is suitable for scenarios where vector search needs to be tightly integrated with traditional relational data.

Date published
Sept. 3, 2024

Author(s)
Fendy Feng

Language
English

Word count
1610

Hacker News points
None found.

Weaviate and Elasticsearch are two technologies that offer search capabilities but cater to different needs and use cases. Weaviate is an open-source, purpose-built vector database designed for semantic searches, while Elasticsearch is a NoSQL database with vector search capabilities as an add-on. Key differences between the two include their search methodologies (vector search vs inverted index-based search), data handling capabilities, integrations with AI and machine learning, scalability and performance, use cases, ease of use, ecosystems, data modeling and query languages, community support, and licensing. The choice between Weaviate and Elasticsearch depends on specific needs, nature of the data, and future scalability requirements.

Date published
Sept. 3, 2024

Author(s)
Chloe Williams

Language
English

Word count
1765

Hacker News points
None found.

Apache Cassandra and Aerospike are two popular distributed NoSQL databases that have evolved to include support for vector search capabilities, making them suitable for AI-driven applications requiring efficient handling of high-dimensional vector data. Both systems leverage their existing strengths while addressing the growing demand for efficient vector data storage and retrieval. Cassandra integrates vector search into its core database using Storage-Attached Indexes (SAI), allowing for flexible schema design with vector data stored alongside other attributes. Aerospike introduces a dedicated vector search layer (AVS) on top of its core database, focusing on low-latency, high-throughput operations. The choice between these two databases largely depends on specific use case requirements, such as data scale and complexity, performance needs, team expertise, and production timeline. Conducting proof-of-concept tests with specific datasets and query patterns is essential in making an informed decision. Additionally, using open-source benchmarking tools like VectorDBBench can assist in evaluating and comparing vector database performance based on actual results.

Date published
Sept. 3, 2024

Author(s)
Chloe Williams

Language
English

Word count
2101

Hacker News points
None found.

Apache Cassandra and Kdb are two popular options for handling vector data in AI applications. Both databases have their strengths, with Cassandra excelling in large-scale distributed data management and Kdb offering superior real-time data processing and advanced vector search capabilities. The choice between the two depends on specific use cases, such as scalability, performance, flexibility, integration, ease of use, cost considerations, and security features. To make an informed decision, developers should evaluate these databases based on their own datasets and query patterns using tools like VectorDBBench.

Date published
Sept. 3, 2024

Author(s)
Fendy Feng

Language
English

Word count
1610

Hacker News points
None found.

Weaviate and Elasticsearch are two technologies that offer search capabilities but cater to different needs and use cases. Weaviate is an open-source, purpose-built vector database designed for semantic searches, while Elasticsearch is a NoSQL database with vector search capabilities as an add-on. The primary distinction between the two lies in their search methodologies: Weaviate uses vector search, whereas Elasticsearch primarily uses inverted index-based search. Both technologies are scalable and have different strengths in handling data and integrating AI and machine learning. Choosing between them depends on specific use cases, nature of data, and future scalability needs.

Date published
Sept. 2, 2024

Author(s)
Chris Churilo

Language
English

Word count
1454

Hacker News points
None found.

Apache Cassandra and OpenSearch are two options in the vector database space that have evolved to include vector search capabilities as an add-on. Both technologies offer distributed architectures, support for structured and unstructured data, and scalability features. However, they differ in their search methodology, data handling, flexibility, integration with other tools, ease of use, cost considerations, and security features. The choice between Cassandra and OpenSearch should depend on the specific use case, data types, scalability needs, and existing technology stack.

Date published
Sept. 2, 2024

Author(s)
Chris Churilo

Language
English

Word count
1454

Hacker News points
None found.

Apache Cassandra and OpenSearch are two popular options in the vector database space. Both technologies have evolved to include vector search capabilities as an add-on, making them suitable for AI-driven applications. Key differences between the two include their search methodology, data handling, scalability and performance, flexibility and customization, integration and ecosystem, ease of use, cost considerations, and security features. The choice between Cassandra and OpenSearch should depend on specific use cases, data types, scalability needs, and existing technology stacks.

Date published
Aug. 26, 2024

Author(s)
Stephen Batifol

Language
English

Word count
3015

Hacker News points
None found.

Milvus is a powerful open-source vector database designed to handle massive datasets with ease. Its key features include a distributed architecture, optimized indexing techniques, and the ability to search through billions of vectors efficiently. In this blog post, we explore how Milvus can be used to work with 40 million vectors and demonstrate its metadata filtering capabilities, which significantly enhance search results. We also discuss advanced features like data partitioning and hybrid search for enhanced scalability.

Date published
Aug. 25, 2024

Author(s)
Chris Churilo

Language
English

Word count
2144

Hacker News points
None found.

The article discusses the shift from traditional relational databases to specialized databases tailored to specific use cases, such as graph, search, time series, key-value, in-memory, and vector databases. It highlights that while relational databases remain dominant, purpose-built databases are gaining traction due to increasing demands for performance and advanced features. The article also provides an overview of vector databases and compares them with traditional relational databases, emphasizing the importance of selecting the right indexing strategy and benchmarking tools like VectorDBBench to optimize performance. Finally, it outlines various use cases for vector databases, such as Retrieval Augmented Generation (RAG), recommender systems, multimodal similarity search, and molecular similarity search.

Date published
Aug. 21, 2024

Author(s)
Fendy Feng

Language
English

Word count
1426

Hacker News points
None found.

The management and versioning of massive datasets and models in machine learning (ML) have become increasingly complex, requiring specialized solutions beyond traditional tools like Git. XetHub is a tool that extends Git's capabilities to handle petabyte-scale data efficiently, addressing the challenges of scalability, data management, collaboration, and observability in ML development. Vector databases such as Milvus and Zilliz Cloud are also crucial for managing high-dimensional unstructured data, particularly in applications like Retrieval Augmented Generation (RAG). By combining solutions like XetHub with vector databases and machine learning models, we can enhance the effectiveness of ML projects, ensuring they are well-managed and adaptable to new data.

Date published
Aug. 19, 2024

Author(s)
Fendy Feng and ShriVarsheni R

Language
English

Word count
1533

Hacker News points
None found.

As AI technologies like large language models (LLMs) and Retrieval Augmented Generation (RAG) continue to evolve, the demand for flexible and efficient data infrastructure is growing. Metadata lakes are emerging as a key solution in this regard, offering a unified approach to data management by storing metadata from various sources in an organization. Metadata provides context and understanding of the stored data, including data source, quality, lineage, ownership, content, structure, and context. Metadata lakes can assist with RAG development, model registration, AI governance, and implementing advanced analytics. By providing a unified plane for data operations, metadata lakes empower teams to maintain observability in metadata analysis, ensure smooth transitions between different cloud environments and data sources like the Milvus vector database, and uphold governance frameworks seamlessly. As AI technologies advance, metadata lakes will play a key role in supporting next-generation AI/ML applications.

Date published
Aug. 18, 2024

Author(s)
Haziqa Sajid

Language
English

Word count
3647

Hacker News points
None found.

RoBERTa (Robustly Optimized BERT Pretraining Approach) is an improved version of BERT designed to address its limitations and enhance performance across various NLP problems. It introduced several key improvements, including dynamic masking, removal of the next sentence prediction task, larger training data and extended duration, increasing batch sizes, and byte text encoding. These modifications led to significant improvements in model performance on downstream tasks compared to the originally reported BERT results.

Date published
Aug. 15, 2024

Author(s)
ShriVarsheni R and Fendy Feng

Language
English

Word count
1123

Hacker News points
None found.

Streamlining the Deployment of Enterprise GenAI Apps with Efficient Management of Unstructured Data is a challenge faced by many companies due to the complexity and volume of unstructured data. Aparavi, a data management service provider, offers a comprehensive platform designed to simplify the management and utilization of unstructured data. The platform integrates seamlessly with various data sources and ensures data privacy by keeping it securely on-premises. It also supports advanced OCR capabilities for extracting text from images and includes built-in features for automating processes and controlling data ownership at a granular level. Integration with Milvus, an open-source vector database, enables Aparavi's platform to offer Enterprise RAG solutions with the Semantic Search Retriever and AI Data Loader. While there are still some challenges, such as heavy footprint and complex user interface, leveraging advanced data management platforms like Aparavi can help enterprises streamline their AI projects and scale their applications as their business grows.

Date published
Aug. 12, 2024

Author(s)
Fendy Feng and Fariba Laiq

Language
English

Word count
1119

Hacker News points
None found.

Generative AI (GenAI) is transforming business operations by automating mundane tasks, enhancing productivity, and offering deeper insights. Advanced tools like Large Language Models (LLMs), multimodal models, vector databases, and embedding models are central to GenAI's success. Applications of GenAI span across industries, from customer service automation to supply chain optimization. Upstage AI is an example of a platform that utilizes these technologies to automate workflows and solve industry-specific challenges. The transformative potential of GenAI is evident in various applications such as process automation, customer support automation, content creation and personalization, supply chain optimization, and automated news generation.

Date published
Aug. 9, 2024

Author(s)
Robert Guo

Language
English

Word count
2061

Hacker News points
None found.

Milvus is an open-source vector database that offers three deployment options: Milvus Lite, Standalone, and Distributed. Milvus Lite is a lightweight Python library ideal for rapid prototyping and small-scale experiments. Milvus Standalone is suitable for early production environments with moderate data sizes and growing user demands. Milvus Distributed is designed for large-scale production deployments requiring high availability, scalability, and flexibility. The choice of deployment mode depends on the stage of application development, data size, and use case.

Date published
Aug. 9, 2024

Author(s)
Jiang Chen

Language
English

Word count
2374

Hacker News points
None found.

The landscape of Generative Artificial Intelligence (GenAI) has significantly expanded beyond Large Language Models (LLMs) and vector databases, with a focus on Retrieval-Augmented Generation (RAG) and multimedia generation. RAG combines information retrieval techniques with generative language models to produce relevant outputs, while multimedia generation leverages generative models for complex visual content creation. The GenAI ecosystem includes various components such as data connectors, embedding models, LLM inference frameworks, agentic frameworks, and frontend UI experiences. Key projects within the ecosystem include LlamaIndex, Ragas, Airbyte, Voyage AI, vLLM, MemGPT, Bing API, Streamlit, WhyHow, AnythingLLM, Midjourney, and Zilliz Cloud.

Date published
Aug. 8, 2024

Author(s)
Denis Kuria

Language
English

Word count
2693

Hacker News points
None found.

Vector databases are revolutionizing unstructured data search in AI applications by enabling efficient and semantically meaningful retrieval of relevant information. They store and search data based on semantic similarity rather than exact matches, allowing for more nuanced and context-aware information retrieval. Applications of vector databases include retrieval-augmented generation (RAG), recommender systems, molecular similarity search, and multimodal similarity search. These databases are transforming various fields by providing a unified way to represent and search across different types of data.

Date published
Aug. 6, 2024

Author(s)
Stephen Batifol

Language
English

Word count
2813

Hacker News points
None found.

This blog post explores how to build agents using Llama-agents and Milvus, combining large language models (LLMs) with vector similarity search capabilities to create sophisticated agentic systems. The text discusses the use of Mistral Nemo for simpler tasks and Mistral Large for orchestrating different agents, as well as how to load data into Milvus and define various tools for the agent. It also covers using an LLM to create metadata filters automatically and orchestrating everything with Mistral Large.

Date published
Aug. 5, 2024

Author(s)
Tim Mugabi

Language
English

Word count
2061

Hacker News points
None found.

Retrieval Augmented Generation (RAG) is a popular technique used to build GenAI applications powered by large language models (LLMs). It enhances an LLM's output by providing contextual information on which the model wasn’t pre-trained. Multilingual RAG is an extended RAG that handles text data in multiple languages. Building a multilingual RAG involves using embedding models, vector databases, and LLMs as core components. The choice of embedding model is crucial for supporting multiple languages.

Date published
Aug. 4, 2024

Author(s)
Christy Bergman

Language
English

Word count
1673

Hacker News points
None found.

The University of California – Berkeley has donated vLLM, a fast and easy-to-use library for LLM inference and serving, to LF AI & Data Foundation as an incubation-stage project. Large Language Models (LLMs) and vector databases are usually paired to build Retrieval Augmented Generation (RAG), a popular AI application architecture to address AI Hallucinations. This blog demonstrates how to build and run a RAG with Milvus, vLLM, and Llama 3.1.1. The process includes embedding and storing text information as vector embeddings in Milvus, using this vector store as a knowledge base to efficiently retrieve text chunks relevant to user questions, and leveraging vLLM to serve Meta's Llama 3.1-8B model to generate answers augmented by the retrieved text.

Date published
Aug. 2, 2024

Author(s)
Cheney Zhang

Language
English

Word count
3308

Hacker News points
None found.

Retrieval Augmented Generation (RAG) is a technique that connects external data sources to enhance the output of large language models (LLMs). This technique is perfect for LLMs to access private or domain-specific data and address hallucination issues. Therefore, RAG has been widely used to power many GenAI applications, such as AI chatbots and recommendation systems. Microsoft Research introduced GraphRAG, a brand-new method that augments RAG retrieval and generation with knowledge graphs. Unlike a baseline RAG that uses a vector database to retrieve semantically similar text, GraphRAG enhances RAG by incorporating knowledge graphs (KGs). Knowledge graphs are data structures that store and link related or unrelated data based on their relationships. A GraphRAG pipeline usually consists of two fundamental processes: indexing and querying. The GraphRAG Pipeline includes four key steps in the indexing process: Text Unit Segmentation, Entity, Relationship, and Claims Extraction, Hierarchical Clustering, and Community Summary Generation. In the querying stage, GraphRAG has two different querying workflows tailored for different queries: Global Search and Local Search. Baseline RAG vs. GraphRAG in Output Quality demonstrates that GraphRAG significantly improves multi-hop reasoning and complex information summarization. The research indicates that GraphRAG surpasses Baseline RAG in both comprehensiveness and diversity.

Date published
July 30, 2024

Author(s)
Christy Bergman, David Wang, and Reina Wang

Language
English

Word count
1134

Hacker News points
None found.

The Milvus Multimodal RAG demo is a product recommendation system that uses Google's MagicLens multimodal embedding model to encode both images and text into a single multimodal vector. This vector is then used to search for the closest-matching Amazon products from a Milvus vector database. The technologies used in this demo include Google DeepMind's MagicLens, OpenAI's GPT-4o, Milvus, and Streamlit. The data comes from the Amazon Reviews 2023 dataset, with a subset of 5K items being used for the demonstration. The setup instructions for MagicLens involve setting up an environment, installing dependencies, and downloading model weights. The Milvus server is used to store, index, and search vectors, while Streamlit provides a user-friendly interface for uploading images and entering text instructions. The Ask GPT function utilizes OpenAI's GPT-4o mini multimodal generative model to provide AI-powered recommendations based on the search results.

Date published
July 30, 2024

Author(s)
Stephen Batifol

Language
English

Word count
1242

Hacker News points
None found.

Function calling with LLMs allows developers to create powerful and context-aware applications by integrating Language Learning Models (LLMs) like Llama 3.1 with external tools such as user-defined functions or APIs. This enables the creation of solutions for data extraction, natural language conversion to API calls or database queries, and conversational knowledge retrieval engines that interact with a knowledge base. In this blog post, we explore how to integrate Llama 3.1 with external tools like Milvus and APIs to build advanced applications. The integration of LLMs with external tools opens up new possibilities for developers to create versatile and powerful AI applications catering to specific use cases and practical problems.

Date published
July 24, 2024

Author(s)
Fariba Laiq

Language
English

Word count
2236

Hacker News points
None found.

Large language models (LLMs) are increasingly being adopted across various industries and production environments. Ensuring their outputs are accurate, reliable, and unbiased is crucial as they become more widespread. Traditional human evaluation methods often fall short due to their time-consuming nature and inconsistency in handling the complexity and scale of modern LLMs. One promising approach to this challenge is using LLMs as judges to evaluate their outputs. By leveraging their extensive training data and contextual understanding, LLMs can provide automated, scalable, and consistent assessments. During a meetup hosted by Zilliz, Sourabh Agrawal discussed the real-world difficulties of implementing LLM-as-a-judge techniques and highlighted four primary metrics for assessing LLM performance: response quality, context awareness, conversational quality, and safety. He also shared strategies for addressing challenges associated with using LLMs as judges, such as biases in evaluations, consistency problems, lack of domain-specific knowledge, and the complexity of evaluating complex responses. To tackle these limitations, developers can adopt objective evaluations, check for conciseness, use a grading system with "YES, NO, MAYBE" options, and maintain cost-effective evaluations by leveraging cheaper LLMs as much as possible. Additionally, fine-tuning the judge LLM for specific domains ensures more accurate and relevant evaluations. UpTrain AI is an open-source framework that developers can use to evaluate their LLM applications. It provides scores and explanations, breaking down long responses into subparts and evaluating each for a more objective measure of conciseness. The UpTrain dashboard logs all data, enabling comparison of models and prompts and monitoring performance.

Date published
July 23, 2024

Author(s)
Haziqa Sajid

Language
English

Word count
1740

Hacker News points
None found.

Retrieval Augmented Generation (RAG) is a technique that enhances large language models (LLMs) by providing them with additional knowledge and long-term memories through vector databases like Milvus and Zilliz Cloud. While RAG can address many LLM headaches, it may be insufficient for more advanced requirements such as customization or greater control of the retrieved results. Knowledge Graphs (KG) can be incorporated into the RAG pipeline to improve performance and accuracy. By integrating KGs with RAG systems, users can enhance contextual understanding, improve accuracy and factual consistency, enable multi-hop reasoning capabilities, facilitate efficient information retrieval, provide transparent and traceable outputs, synthesize knowledge across domains, and handle ambiguity more effectively.

Date published
July 16, 2024

Author(s)
Christy Bergman

Language
English

Word count
3240

Hacker News points
None found.

This blog post provides a detailed guide on how to deploy an open-source vector database called Milvus on Amazon Elastic Kubernetes Service (EKS). The author explains the architecture of Milvus and its integration with EKS, AWS S3 for object storage, Amazon Managed Streaming for Apache Kafka (MSK) for message storage, and Amazon Elastic Load Balancing (ELB) as a load balancer. The post also covers prerequisites such as installing the AWS Command Line Interface (CLI), EKS tools like kubectl, eksctl, and helm, creating an S3 bucket with a KMS customer-managed key, and setting up an Amazon MSK instance. Next, the author guides users through creating an Amazon EKS cluster using eksctl, installing the AWS Load Balancer Controller, and deploying Milvus on EKS using Helm. The post also explains how to configure S3 as object storage, MSK as message storage, expose Milvus services for external access, and enable high availability deployment of Milvus core components. Finally, the author demonstrates how to access and manage Milvus endpoints through Kubernetes Services and Attu, an open-source Milvus administration tool. The post concludes with a test using Milvus' official example code to verify if the Milvus database is working properly.

Date published
July 15, 2024

Author(s)
Rok Benko

Language
English

Word count
1894

Hacker News points
None found.

LangChain is an open-source framework that simplifies building conversational AI agents using large language models (LLMs). It provides tools and templates to create smart, context-aware chatbots and other applications. Conversational agents are software programs that interact with users in natural language, handling tasks like answering questions or translating languages. LangChain Agents use LLMs to interact with external tools and data sources, making them more powerful for various applications. To build a conversational agent using LangChain, developers need to install dependencies such as LangChain, langchain-openai, OpenAI API SDK, dotenv, Milvus, pymilvus, and tiktoken. They can then create a conversation chain with the ConversationChain class from langchain.chains, making predictions by passing user input to the conversation chain. To enhance conversational agents with long-term memory, developers can integrate Milvus Lite as a vector store to store and retrieve data efficiently. By incorporating memory into their agents using LangChain and Milvus Lite, developers can create more accurate and personalized responses based on previous interactions. This integration significantly enhances the capabilities of AI agents, allowing them to provide better assistance in various applications.

Date published
July 12, 2024

Author(s)
Stephen Batifol

Language
English

Word count
825

Hacker News points
None found.

Retrieval Augmented Generation (RAG) is a technique that enhances Language Learning Models (LLMs) by integrating additional data sources. Milvus, a vector database, can boost the performance of RAG applications with its Metadata Filtering, Hybrid Search, and Agent capabilities. Metadata Filtering allows for precise and efficient searches by enriching data with additional attributes. Hybrid Search expands search capabilities by allowing queries across multiple vector columns. Agents automate actions based on LLM's output, enabling continuous updates to the RAG system.

Date published
July 11, 2024

Author(s)
Stephen Batifol

Language
English

Word count
1441

Hacker News points
None found.

In this blog post, we explore how Retrieval Augmented Generation (RAG) can be applied to legal data using Ollama and Milvus. RAG is a technique that enhances Language Learning Models (LLMs) by integrating additional data sources. We demonstrate how to set up a RAG system for legal data, leveraging Milvus as our vector database and Ollama for local LLM operations. The process involves indexing the data, retrieval and generation at runtime, and using an LLM to generate a response based on enriched context. This approach can significantly streamline legal research by making it more efficient and easier.

Date published
July 10, 2024

Author(s)
Ruben Winastwan

Language
English

Word count
2372

Hacker News points
None found.

Building a scalable vector search pipeline in production is challenging due to handling massive amounts of unstructured data and high query volumes. To address this, a combination of Milvus, an open-source vector database, and Apache Spark, a distributed computing framework, can be used. Milvus enables efficient vector search operations on large datasets, while Spark accelerates data processing tasks by distributing them across multiple computers in batches. By integrating these tools, developers can create production-ready applications that leverage AI models for improved information retrieval and search processes.

Date published
July 9, 2024

Author(s)
Haziqa Sajid

Language
English

Word count
2600

Hacker News points
None found.

Darren Oberst, CEO of AI Blocks, discussed deploying Retrieval Augmented Generation (RAG) on-premises for large financial and legal services companies during a recent Unstructured Data Meetup session. He highlighted the challenges faced by enterprises in adopting RAG, including data privacy and security concerns, elevated costs, and neglecting retrieval strategies. To address these issues, Darren advocates for deploying RAG on private cloud solutions, offering better data security, lower cost, and enhanced generation with retrieval capabilities. The session also covered the Dragon models designed specifically for Retrieval Augmented Generation (RAG) in the Huggingface Transformers library and LLMware, a library designed for enterprise-level LLM-based applications.

Date published
July 9, 2024

Author(s)
Denis Kuria

Language
English

Word count
1882

Hacker News points
None found.

The talk by Jacob Marks at the Unstructured Data Meetup hosted by Zilliz focused on building robust multimodal Retrieval Augmented Generation (RAG) pipelines using FiftyOne, LlamaIndex, and Milvus. RAG enhances large language models' capabilities by augmenting their knowledge with relevant external data. The architecture of a text-based RAG system is simple, integrating LLMs with vector databases like Milvus or Zilliz Cloud to provide users with more accurate and contextually relevant responses. Multimodal RAG proves invaluable for systems that need multiple data types to make informed decisions. It combines information retrieval and generative modeling to enhance the capabilities of multimodal LLMs, integrating various data types such as text, images, audio, and video. The fiftyone-multimodal-rag-plugin can be used to implement a multimodal RAG pipeline using FiftyOne, LlamaIndex, and Milvus.

Date published
July 8, 2024

Author(s)
Tim Mugabi

Language
English

Word count
2656

Hacker News points
None found.

OpenAI's ChatGPT has sparked a surge of interest in large language models (LLMs) among corporations, leading to increased demand for technology vendors that support LLM operations (LLMOps). These vendors provide comprehensive workflows for developing, fine-tuning, and deploying LLMs into production environments. Sage Elliott, a machine learning engineer at Union.ai, discussed deploying and managing LLMs during a recent Unstructured Data Meetup, focusing on ensuring the reliability and scalability of LLM applications in production settings. LLMOps stands for Large Language Model Operations, which are analogous to MLOps but specifically for large language models (LLMs). MLOps (Machine Learning Operations) refers to the practices and tools used to efficiently deploy and maintain machine learning models in production environments. It is an extension of DevOps (Development and Operations), which integrates application development and operations into a cohesive process. Continuous Integration/Continuous Deployment (CI/CD) is one of the core principles of LLMOps, automating the LLM application development lifecycle. Continuous integration (CI) involves automatically taking application updates and merging them with the main branch, while continuous delivery/deployment (CD) refers to the process of automatically deploying changes to the application in a production environment after integration and validation. LLMOps is essential for production-level AI applications, with the exact infrastructure dependent on the application's needs. Integrating LLMOps into your AI application offers benefits such as resource management and scalability, model updating and improvements, and ethical and responsible AI practices. A simplified LLMOps pipeline includes elements like Sys Prompt, Model, Guardrail, Data Store, Monitor, and CI/CD Orchestrator. The HuggingFace Spaces platform streamlines the shipping of your model into production, offering low-cost cloud GPUs to power LLMs. To get started with LLMOps, follow a simple three-step philosophy: ship the model, monitor its performance, and improve it based on insights gained from monitoring. Tools like LangKit, Ragas, Continuous Eval, TruLens-Eval, LlamaIndex, Phoenix, DeepEval, LangSmith, and OpenAI Evals can help evaluate LLM applications.

Date published
July 6, 2024

Author(s)
Uppu Rajesh Kumar

Language
English

Word count
3730

Hacker News points
None found.

Retrieval Augmented Generation (RAG) systems have significantly enhanced AI applications by providing more accurate and contextually relevant responses. However, scaling and deploying these systems in production have presented considerable challenges as they become more sophisticated and incorporate custom AI models. BentoML is a valuable tool that simplifies the process of building and deploying inference APIs for custom models, optimizes serving performance, and enables seamless scaling. By integrating BentoML with the Milvus vector database, organizations can build more powerful, scalable RAG systems.

Date published
July 5, 2024

Author(s)
Ruben Winastwan

Language
English

Word count
2896

Hacker News points
None found.

The introduction of specialized GenAI frameworks like LangChain has enabled developers to build sophisticated AI applications quickly and easily by leveraging powerful large language models (LLMs) such as ChatGPT and LLaMA. These frameworks allow users to create Retrieval Augmented Generation (RAG) applications in just a few lines of code without requiring deep theoretical AI knowledge. However, these GenAI frameworks are typically written in Python, which may not be familiar to all full-stack engineers and software developers. There is a need for extensions of these GenAI frameworks in other programming languages so that these full-stack engineers can leverage powerful LLMs to build GenAI applications in their software projects. Andrei Bondarev introduced a Ruby extension of LangChain called LangChain.rb to make it easier for full-stack engineers to build GenAI applications in their software projects.

Date published
July 4, 2024

Author(s)
Denis Kuria

Language
English

Word count
2351

Hacker News points
None found.

Jithin James and Shahul Es shared insights on leveraging metrics-driven development to evaluate Retrieval Augmented Generation (RAG) systems at the Zilliz Unstructured Data Meetup. They discussed both the theoretical foundations and practical applications of RAG system evaluation, explaining how understanding the theory behind the evaluation code can provide deeper insights into its functionality. The talk covered key metrics such as factual similarity and semantic similarity to determine the quality and relevance of the generated answer compared to the ground truth. Practical examples were provided on how to evaluate and improve a RAG system powered by Milvus, an open-source vector database known for its efficiency in similarity search and AI applications.

Date published
July 3, 2024

Author(s)
Christy Bergman

Language
English

Word count
1100

Hacker News points
None found.

Retrieval Augmented Generation (RAG) is a technique that uses an AI chatbot with personal data. Three key strategies to optimize RAG include smart text chunking, iterating on different embedding models, and experimenting with various LLMs or generative models. Smart text chunking involves breaking down text into manageable pieces for efficient retrieval by the Vector Database. Different techniques for this process include recursive character text splitting, small-to-big text splitting, and semantic text splitting. Iterating on embedding models determines how data is represented as vectors, which are crucial in AI applications. Lastly, experimenting with different LLMs allows users to choose the most suitable one for their workload.

Date published
June 28, 2024

Author(s)
Ruben Winastwan

Language
English

Word count
3362

Hacker News points
None found.

In a recent talk at the Unstructured Data Meetup, Jiang Chen discussed how to build a Retrieval Augmented Generation (RAG) system using Milvus vector database and Snowflake ecosystem with Snowpark Container Service (SPCS). RAG is an advanced information retrieval method that enhances large language models' response quality by providing relevant context from internal knowledge bases. The integration of Milvus, a powerful open-source vector database, with Snowflake allows users to easily interact with the data stored in Snowflake and build sophisticated applications like RAG systems.

Date published
June 27, 2024

Author(s)
Ken Zhang

Language
English

Word count
1877

Hacker News points
1

Milvus 2.4 introduces multi-vector columns within a single collection, enabling more advanced and flexible data searches by allowing simultaneous queries across multiple vector types and fields. This hybrid search feature supports multimodal search, hybrid sparse and dense search, and hybrid dense and full-text search. The results from each field are integrated and re-ranked using multiple reranking algorithms to deliver more accurate outcomes. Hybrid search is designed to handle complex and multimodal data representations, accommodating diverse facets of information and various types of vector embeddings. It also supports the fusion of multimodal vectors from different unstructured data types such as images, videos, audio, and text files. The latest Milvus releases support hybrid search to meet escalating demands for handling intricate datasets in AI-driven applications.

Date published
June 25, 2024

Author(s)
Stephen Batifol

Language
English

Word count
840

Hacker News points
None found.

This blog post discusses how to build intelligent Retrieval Augmented Generation (RAG) applications using LangServe, LangGraph, and Milvus from the LangChain ecosystem. The author guides readers through setting up a FastAPI application, configuring LangServe and LangGraph, and utilizing Milvus for efficient data retrieval. The post also covers building an LLM agent with LangGraph and integrating Milvus for vector storage and retrieval. Key prerequisites include Python 3.9+, Docker, and basic knowledge of FastAPI and Docker.

Date published
June 24, 2024

Author(s)
Fariba Laiq

Language
English

Word count
1774

Hacker News points
None found.

In April 2024, Jove Zhong, co-founder of Timeplus, delivered a talk on "Processing Streaming Data in Kafka with Timeplus Proton" at the Seattle Unstructured Data Meetup. Timeplus is revolutionizing real-time data handling with its streaming SQL database and real-time analytics platform. The company's core engine, Timeplus Proton, serves as an alternative to platforms like ksqlDB and Apache Flink. It supports diverse data sources, including Apache Kafka, Confluent Cloud, and Redpanda, allowing for real-time insights and alerts. Jove also discussed the integration of streaming data with Large Language Models (LLMs) and vector databases, emphasizing their potential to enhance AI applications. The talk concluded with a look towards the future of streaming SQL and real-time processing, highlighting its growing importance in various industries.

Date published
June 23, 2024

Author(s)
Denis Kuria

Language
English

Word count
1381

Hacker News points
None found.

Storia Lab is a suite of APIs designed to integrate advanced image editing functionalities into applications, making it easier for developers to perform nuanced edits while preserving the integrity of original images. The platform offers solutions such as text correction, background removal and replacement, removing unwanted elements, and sketch-to-image conversion. Storia Lab can also be integrated with Milvus, an open-source vector database designed to handle billion-scale vectors efficiently, for advanced multimodal applications like content creation, image search and recommendation, visual content curation, e-commerce, creative design tools, and visual content moderation.

Date published
June 22, 2024

Author(s)
ShriVarsheni R

Language
English

Word count
1474

Hacker News points
None found.

Large Language Models (LLMs) have revolutionized various tasks such as content generation and customer service chatbots, but ensuring their unbiased knowledge of current news is crucial for reliable responses. Multilingual narrative tracking helps achieve this by analyzing how a narrative is reported in terms of volume and sentiment across different languages and countries. This process involves tracking narratives, which are sequences of interconnected events, such as the Barbie Movie Campaign narrative with its diverse coverage and sentiments across various regions and languages. LLMs should be exposed to diverse news across languages, countries, and other demographics to avoid biased reporting. Multilingual narrative tracking can increase transparency and ensure global perspectives and comprehensive event coverage by including voices from different limits and cultural backgrounds.

Date published
June 21, 2024

Author(s)
Abhiram Sharma

Language
English

Word count
1826

Hacker News points
None found.

Large language models (LLMs) can sometimes produce confident but incorrect information, a phenomenon known as hallucination. This issue is significant in industries like law and healthcare where the accuracy of information generated by LLMs is critical. There are two major categories of hallucinations: intrinsic hallucinations and extrinsic hallucinations. Intrinsic hallucinations tend to contrast the source information given to them, while extrinsic hallucinations occur when LLMs generate information that cannot be verified against the provided source data. Hallucinations can have far-reaching societal implications, undermining trust in reliable information sources and contributing to widespread confusion and mistrust among the public. Several methodologies are used to detect LLM hallucinations: self-evaluation, reference-based detection, uncertainty-based detection, and consistency-based detection. Implementing these approaches ensures the responsible deployment of LLMs and other generative AI technologies, maximizing their positive impact on society.

Date published
June 20, 2024

Author(s)
Ruben Winastwan

Language
English

Word count
1675

Hacker News points
None found.

Recent advancements in artificial intelligence have led to the development of large language models (LLMs), revolutionizing natural language processing. These powerful models, such as ChatGPT and Llama, demonstrate superior capabilities in understanding and generating human-like language but are limited by their training data cut-off date. To unlock their full potential, LLM customization is essential. Customization options include Retrieval Augmented Generation (RAG) and fine-tuning methods like supervised fine-tuning and Reinforcement Learning from Human Feedback (RLHF). RAG enhances response quality by injecting relevant contexts alongside the query, while fine-tuning involves training LLMs on specific data domains.

Date published
June 18, 2024

Author(s)
Christy Bergman

Language
English

Word count
932

Hacker News points
None found.

Misconceptions about data insertion speed in Milvus may arise due to users overlooking the detailed process steps involved. When using libraries like LangChain or LlamaIndex, these platforms convert unstructured data into vectors and then insert them into Milvus Lite. The abstraction of this complex process can create an illusion that the data insertion process takes a long time. However, the actual time-consuming step is generating embeddings from unstructured data, which is computationally intensive. In comparison, the average Milvus vector database insert time is only about a tenth of a second. Thus, around 97% of the "Milvus insert" time observed in LangChain or LlamaIndex is spent on embedding generation, while about 3% is spent on the actual database insertion step.

Date published
June 17, 2024

Author(s)
Abdelrahman Elgendy

Language
English

Word count
1503

Hacker News points
None found.

Personalization is crucial in maintaining long-term customer satisfaction and retention for user-centric products like Netflix, Disney, or food delivery apps. AI recommendation engines leverage historical data to provide personalized experiences. Mike Del Balso, CEO of Tecton, discussed using the RAG architecture to improve AI recommendation engine personalization at a recent Unstructured Data Meetup hosted by Zilliz. He highlighted that AI-powered personalization could add $5 trillion in value to global GDP. RAG (Retrieval Augmented Generation) is an effective technique for enhancing the response quality and relevance of large language models (LLMs). It consists of a retriever, which combines an embedding model and a vector database like Milvus or Zilliz Cloud, and a generator, which is the LLM. The RAG pipeline involves transforming all documents into vector embeddings stored in a vector database, converting user queries into vector embeddings, retrieving top candidates from the vector database based on similarity to the query, and generating a coherent response using the query and Top-K candidates. However, traditional RAG systems lack personalized context for users' likes and dislikes. Full-RAG addresses this by adding context in the retrieval pipeline. This involves providing context on candidate locations (e.g., weather, activities) and user preferences (e.g., historical sites, accommodation). Tecton has developed a feature platform to integrate different business data sources for creating personalized contexts at various levels: Base, Batch Context, Batch + Streaming Data Context, and Batch + Streaming data + Real-time Context. RAG is essential in enhancing AI recommendation engines' effectiveness and long-term customer retention. Tecton simplifies building streaming context by providing a Python SDK for coding context definitions and real-time evaluation of data. However, challenges remain, such as managing trade-offs between speed and costs, integrating third-party real-time data sources, and ensuring proper model governance, debugging, and version control.

Date published
June 16, 2024

Author(s)
Christy Bergman

Language
English

Word count
745

Hacker News points
None found.

Milvus v2.4.3 introduces full-string metadata matching, allowing users to match strings using prefix, infix, postfix, or character wildcard searches. This update makes metadata filtering more versatile and powerful. The blog demonstrates how to use this feature with an example using IMDB movie data. It covers connecting to Milvus Lite, transforming movie text into vectors, inserting vectors and metadata into Milvus, and handling user queries by searching for similar data vectors. Additionally, the blog provides resources and further reading on using array fields in Milvus and filtering searches.

Date published
June 15, 2024

Author(s)
Denis Kuria

Language
English

Word count
1375

Hacker News points
None found.

GitHub Next introduced Copilot Workspace, a task-oriented development environment that integrates generative AI models into coding environments. The workspace allows developers to brainstorm, plan, build, test, and run code using natural language conversations and prompts. It follows a task-to-code workflow, starting with task creation and flowing into specification, planning, and coding. Steering points are implemented between the given task and suggested code, allowing developers to guide the model when it misunderstands requests or misses edge cases. The workspace is useful for tasks such as fixing bugs and implementing features.

Date published
June 14, 2024

Author(s)
Haziqa Sajid

Language
English

Word count
2199

Hacker News points
None found.

The article discusses Retrieval Augmented Generation (RAG), a technique that optimizes large language models by providing context from the query. It explains how embedding models convert unstructured data into vector embeddings, enabling computers to understand semantics. RAG is particularly useful in reducing hallucinations in generative AI models like ChatGPT. The article also introduces Voyage AI's domain-specific and general-purpose embedding models and rerankers that contribute significantly to search and RAG. Furthermore, it demonstrates how to integrate Zilliz Cloud Pipelines with Voyage AI for streamlined embedding generation and retrieval, using Cohere as the LLM to build a RAG application.

Date published
June 14, 2024

Author(s)
Stephen Batifol

Language
English

Word count
1304

Hacker News points
None found.

LLMs can be empowered with important new capabilities through agents that use planning, memory, and tools to accomplish tasks. This post demonstrates how to build agents capable of tool-calling using LangGraph with Llama 3 and Milvus. Agents can perform actions such as web searching, browsing emails, correcting RAGs, and more. The process involves setting up LangGraph, Ollama & Llama 3, and Milvus Lite. Using these tools, a custom local Llama 3 powered RAG agent is built with different approaches like routing, fallback, and self-correction. Examples of agents include the Hallucination Grader and the Answer Grader. The post concludes by compiling the LangGraph graph and testing it.

Date published
June 13, 2024

Author(s)
Abdelrahman Elgendy

Language
English

Word count
1482

Hacker News points
None found.

Large language models (LLMs) have revolutionized AI, particularly in conversational AI and text generation. However, a critical issue that needs to be addressed is the occurrence of logical fallacies in LLM output. Logical fallacies can lead to flawed reasoning and misinformation. There are multiple reasons why these fallacies occur, including imperfect training data, small context window, and the probabilistic nature of LLMs. To tackle this problem, strategies such as human feedback, reinforcement learning, prompt engineering, and more have been proposed. One interesting approach is RLAIF (Reinforcement Learning from AI Feedback), which uses AI to fix itself by detecting and correcting logical fallacies. The FallacyChain module in LangChain has been developed to implement this approach, making LLM outputs more reliable and trustworthy.

Date published
June 11, 2024

Author(s)
Daniella Pontes

Language
English

Word count
1308

Hacker News points
None found.

Bad data can significantly impact AI-powered applications and workflows, leading to inaccurate results and frustrated users. To address this issue, Voxel51 has developed a solution that brings transparency and clarity to visual AI workflows, making it faster and more efficient to build high-quality datasets and models. By integrating vector databases with tools like Voxel51's FiftyOne open source project, users can test and assess models by feeding them the exact datasets they need for robust, accurate results. This approach accelerates the path to success in AI development, as better data leads to better models. Vector search capabilities are essential in computer vision, offering a powerful engine for data exploration, model evaluation, and innovative multimodal search using embeddings, concept interpolation, and traversal. As AI continues to evolve, integrating vector databases will play a crucial role in shaping the future of unstructured data-driven technologies.

Date published
June 10, 2024

Author(s)
Ruben Winastwan

Language
English

Word count
2211

Hacker News points
None found.

Delivery Hero, a multinational online food delivery company, has implemented an AI safety system to generate high-quality images of products. The system consists of two stages: food image generation and building a safety system. For the first stage, they use DALL-E from OpenAI and implement an image inpainting method with Grounding DINO and DALL-E. In the second stage, four components are used to generate a final score for each image: image tagging, image centering, text detection, and image sharpness. The scores obtained from these components are combined with a weighted function to give each image one final score value. By applying a threshold, an image with a final score below the threshold will be filtered out and not recommended to vendors.

Date published
June 9, 2024

Author(s)
Denis Kuria

Language
English

Word count
1913

Hacker News points
None found.

Bo Wang from Jina AI discussed the development of state-of-the-art text embeddings, which power modern vector search and Retrieval-Augmented Generation (RAG) systems. The release of Jina-Embeddings-V2 garnered significant attention in the AI community, with over 3 million downloads on Hugging Face. It has been integrated into various AI frameworks like LangChain and LlamaIndex, as well as vector databases such as Milvus and Zilliz Cloud. Jina embeddings closely compete with OpenAI embeddings. Jina AI initially began by fine-tuning existing models like BERT but soon realized that the industry was not ready for fine-tuning techniques. This led them to develop their own embedding model from scratch, resulting in Jina-Embeddings-V1 and later V2. The latest version, V2, can handle sequences up to 8,192 tokens during inference while training on shorter sequences. Jina-Embeddings-V2 removes position embeddings and introduces Attention with Linear Biases (ALiBi) for dynamic context modeling. It also adapts ALiBi for bidirectional transformers and retrains BERT from scratch, resulting in JinaBERT as the backbone for V2. The model has been successful in handling multilingual data and consistently outperforms competitors like Multilingual E5 and Cohere Embed V3. When developing RAG applications using Jina-Embeddings-V2, it's essential to consider document length and the positioning of relevant information within these documents. The team at Jina AI is already working on Jina-Embeddings-V3, which promises improvements in speed, efficiency, multilingual support, real-world problem solving, task-specific enhancements, and chunk and schema awareness.

Date published
June 8, 2024

Author(s)
Haziqa Sajid

Language
English

Word count
1655

Hacker News points
None found.

During a meetup in May, Charles Packer discussed how MemoryGPT (MemGPT) aims to solve the problem of limited memory in large language models (LLMs). MemGPT introduces a virtually extended context window inspired by computer system design. It divides the LLM context into two parts: main context and external context. The main context has a limited bandwidth, while the external context is stored on persistent storage with an infinite window. MemGPT efficiently manages information flow between the two contexts, allowing for long-context memory applications like personal assistant chatbots.

Date published
June 7, 2024

Author(s)
Denis Kuria

Language
English

Word count
2102

Hacker News points
None found.

In March 2024, AJ Steers discussed utilizing Airbyte and PyAirbyte to integrate structured and unstructured data from various sources across different platforms at the SF Unstructured Data Meetup. AJ Steers is an experienced architect, data engineer, software developer, and data ops expert who has designed end-to-end solutions at Amazon and created a vision for quantified self-data models. He currently works as a staff software engineer at Airbyte. Airbyte's focus so far has been on offering reliability, flexible deployment options, and a robust library of connectors to ensure seamless data integration for traditional tabular data. However, the platform has expanded its capabilities in recent months to cover unstructured data sources as well. This expansion includes support for vector database destinations like Milvus, ensuring effective utilization of data across various applications. PyAirbyte is a Python library that provides an interface to interact with Airbyte and allows users to control and manage their Airbyte instances using Python. It offers several advantages, such as the ability to run anywhere, reduce time to value, fast prototyping, and flexibility. Users can choose between the hosted version of Airbyte (no-code approach) or PyAirbyte (minimal code approach) for integrating data sources with data destinations. In conclusion, whether you prefer a no-code or minimal-code approach, Airbyte and PyAirbyte offer robust solutions for integrating both structured and unstructured data from various sources across different platforms.

Date published
June 7, 2024

Author(s)
Christy Bergman

Language
English

Word count
787

Hacker News points
None found.

Milvus Lite is a new open-source vector database that has become the default method for third-party connectors like LangChain and LlamaIndex to connect to Milvus. Comparing timings using the same HuggingFace embedding model, it was found that using Milvus Lite APIs directly provides the best balance between high control over Milvus settings and fast setup. The full code and timings are available on GitHub. This article covers connecting to Milvus Lite using LlamaIndex, LangChain, and Milvus Lite APIs, as well as choosing the right Milvus Light method based on control and speed trade-offs.

Date published
June 6, 2024

Author(s)
Antony G.

Language
English

Word count
1159

Hacker News points
None found.

The article discusses the role of CPUs in vector search operations and whether they are sufficient to meet modern demands. It highlights a recent talk by George Williams, who explored how new hardware solutions could revolutionize vector search technology. The NeurIPS BigANN competitions aim to push the boundaries of vector search technology, with Zilliz being one of the winners. Zilliz's approach involves optimizing memory layout and access patterns for SSDs, as well as focusing on memory efficiency and maximizing data retrieval speed. The future of vector search may shift from relying on approximation techniques to leveraging brute force methods while still maintaining short timeframes.

Date published
June 5, 2024

Author(s)
Steffi Li

Language
English

Word count
395

Hacker News points
None found.

Zilliz Cloud, a fully managed version of the open-source vector database Milvus, is now available in 11 regions across three major cloud providers: AWS, Azure, and Google Cloud Platform (GCP). This expansion allows users to deploy Zilliz Cloud closer to their user base, reducing latency and improving performance. The availability includes five regions on AWS, four on GCP, and two on Azure, covering key areas in the Americas, EMEA, and APAC. By offering broader coverage than other vector database vendors, Zilliz Cloud provides more deployment options and ensures better service availability. This expansion reflects Zilliz's commitment to providing the best possible infrastructure for development needs, helping users reduce complexity and lower total cost of ownership (TCO).

Date published
June 4, 2024

Author(s)
By Abhiram Sharma

Language
English

Word count
1298

Hacker News points
None found.

Laurie Voss, VP of Developer Relations at LlamaIndex, discussed building advanced Retrieval Augmented Generation (RAG) apps with LlamaIndex in a recent Unstructured Data Meetup. RAG is designed to overcome the limitations of Language Models (LLMs) by assisting them with retrieval capabilities. The main drawback of LLMs is their limited context windows, which can only handle part of an organization's data simultaneously. LlamaIndex is an open-source framework that connects your data to LLMs and simplifies the creation of RAG applications, allowing developers to build functional RAG systems with minimal code. It provides advanced data ingestion and querying features for RAG applications, such as Data Connectors, PDF Parsing, Embedding Models, Vector Stores, Sub-Question Query Engine, Small to Big Retrieval, Metadata Filtering, Hybrid Search, and Agents.

Date published
June 4, 2024

Author(s)
By Mostafa Ibrahim

Language
English

Word count
1131

Hacker News points
None found.

Joan Kusuma's innovative approach to enhancing the fashion retail experience involves using image-based recommendations. By utilizing convolutional neural networks (CNNs) and visual embeddings, she has created a personalized outfit recommendation system that can transform the fashion industry. The process includes image preprocessing, feature extraction, vector search with vector databases, indexing, and image recommendation model in action. Joan's work demonstrates the potential of AI in fashion retail by delivering personalized outfit suggestions using visual embeddings and vector databases.

Date published
June 2, 2024

Author(s)
By Fendy Feng

Language
English

Word count
1538

Hacker News points
None found.

The text discusses the challenges faced by machine learning teams in deploying large language models (LLMs) into production, such as addressing hallucinations and ensuring responsible deployment. It highlights strategies for conducting quick and accurate LLM evaluations shared by Hakan Tekgul, an ML Solutions Architect at Arize AI, during a recent Unstructured Data Meetup. The article emphasizes the importance of leveraging evaluation tools for seamless LLM observability and explores five primary facets of LLM observability: LLM Evaluations, Spans and Traces, Prompt Engineering, Search and Retrieval, and Fine-tuning. It delves into the LLM Evaluation and LLM Spans and Traces categories in more detail to highlight their significance in optimizing LLM observability. The article concludes by reflecting on Hakan Tekgul's talk, emphasizing that deploying LLMs into production is challenging but can be achieved with a robust observability framework.

Date published
June 1, 2024

Author(s)
Abdelrahman Elgendy

Language
English

Word count
2205

Hacker News points
None found.

Large language models (LLMs) have made significant strides in machine learning and natural language processing, but they face a unique issue called AI hallucinations, where incorrect or false information is generated. This can happen due to lack of context, training data issues, overgeneralization, or design limitations. Retrieval Augmented Generation (RAG) is an advanced approach that aims to enhance the accuracy and reliability of AI models by providing relevant, current information related to a user's question. RAG helps ensure that models can access the newest data, like recent news or research, to give better answers and reduce mistakes. Building a Retrieval Augmented Generation (RAG) system involves several complex steps and decisions, including choosing an embedding model, selecting an index structure, chunking, determining keywords or semantic search, and integrating rerankers. RAG's ability to handle trillions of tokens makes it ideal for handling massive, ever-changing datasets. Combining RAG's precision with the adaptability of long-context models could lead to a powerful synergy. Evaluating large language models (LLMs) can be challenging, but one solution is to have LLMs evaluate each other by generating test cases and measuring the model's performance.

Date published
May 31, 2024

Author(s)
By Daniella Pontes

Language
English

Word count
1509

Hacker News points
None found.

Dr. Damon Abraham, a behavioral scientist with a PhD in Psychology, has researched how reappraising an image can shift our valence and arousal emotions. His project aims to create a stimuli repository for experimental psychology using LLM and vector database technologies. The research involves collaboration with the University of Denver and other institutions, and it seeks to develop an open-source normative database of images and techniques to measure the dynamic psychological distance between images and their potential for successful reappraisal. In his presentation at the Zilliz Unstructured Data Meetup in Seattle on February 13, 2024, Dr. Abraham discussed how different contextual interpretations of images can change our feelings, providing insights into emotional regulation. The study also explores the concept of 'reappraisal affordances,' which examines how an image's inherent semantic properties and range of associations may affect its capacity for reinterpretation.

Date published
May 29, 2024

Author(s)
By Tim Spann

Language
English

Word count
608

Hacker News points
None found.

Tim Spann, an advocate of Open Source projects, has been working on the intersection of streaming and AI at Zilliz. He emphasizes the importance of a database for AI that can store and query any type of data in any mode needed. With Milvus, Towhee, Attu, and integrations with Kafka and LlamaX frameworks, Spann aims to build up a global group of unstructured data engineers and data superstars. He believes the future will see a rise in unstructured data engineering and processing like Spark, Flink, and Kafka for structured and semistructured data. The need for powerful, fast ways to do unstructured data processing and Vector ETL is evident and growing.

Date published
May 24, 2024

Author(s)
By Yujian Tang

Language
English

Word count
1531

Hacker News points
None found.

This tutorial demonstrates how to build an AI Agent using LangChain, Milvus, and OpenAI. The agent performs Retrieval Augmented Generation (RAG) tasks by retrieving information from a vector database like Milvus. Additionally, the monitoring tool Portkey is used to track token usage, token count, and request latency. The tech stack includes LangChain for orchestration, Milvus as a vector database, Portkey for monitoring, and OpenAI for the Language Learning Model (LLM).

Date published
May 22, 2024

Author(s)
By Christy Bergman

Language
English

Word count
1051

Hacker News points
None found.

Retrieval Augmented Generation (RAG) is an approach in Generative AI that utilizes data to enhance the knowledge of Language Learning Model (LLM) generators, such as ChatGPT. RAG consists of two LLMs: embedding and generator models, both used in inference mode. The HuggingFace MTEB leaderboard provides a comprehensive list of text embedding models, where users can filter by language or specialty domain like law. Users should be cautious when selecting models as some may be overfitted, resulting in deceptively high rankings. ResNet50 is a popular Convolutional Neural Network (CNN) model for image data and PANNs are commonly used embedding models for audio data. Multimodal embedding models like SigLIP or Unum can handle text, image, audio, or video data simultaneously. For multimodal applications involving sound or video, a generative LLM is often employed to convert the input into text before using RAG techniques.

Date published
May 20, 2024

Author(s)
By Tyler Falcon

Language
English

Word count
1971

Hacker News points
None found.

In February 2024, Yury Malkov discussed Approximate Nearest Neighbor (ANN) and its key role in recommender systems at the SF Unstructured Data Meetup. ANN search is already integrated into the production stacks of popular tools worldwide. The talk covered the key concepts and background that have driven ANN's adoption in large-scale recommender systems. Yuri Malkov, a genius physicist, laser researcher, and inventor of HNSW (a graph-based indexing algorithm), now works as a Research Scientist for OpenAI. ANN search algorithms use various indexing techniques to return approximate nearest neighbors, making them core to many applications and technologies that are customer facing today. From search engines like Google to social media sites, ANN and recommender systems are already integrated through the stack in production. Yuri notes that many mature ANN solutions exist, including LSH, graph-based indexes like HNSW and SCANN, quantization-based indices like IVF_PQ and IVF_HSNW, DiskANN, and ANNOY. ANN benchmarking is done through platforms like ANNBenchmarks, which evaluate various approximate nearest neighbor search algorithms and provide results split by distance measure and dataset on their website. The performance metrics include recall rate and queries per second (QPS). More QPS indicates better performance. The Milvus team built Knowhere, an open-source vector execution engine that incorporates several vector similarity search libraries like Faiss, Hnswlib, and Annoy. It controls on which hardware (CPU or GPU) to execute index building and search requests. Cardinal is Zilliz's core vector search engine, offering a threefold increase in performance compared to the previous version. Recommender systems have large market potential due to their ability to generate consumer behavior. Typical challenges at scale include generability, handling huge corpuses, and efficiency. Traditional recommender systems use a multi-staged funnel approach with candidate generation, lightweight ranking, and full ranking stages. Novel solutions for item-query incompatibility include L2 distance on data vectors, bipartite graph ranking, text-focused graph re-ranking, and cascaded graph search. ANN algorithms have seen extensive implementation due to their good enough matching, flexibility, and maturity. Further resources are available through Yury Malkov's talk on YouTube.

Date published
May 17, 2024

Author(s)
By Ken Zhang

Language
English

Word count
1185

Hacker News points
None found.

Milvus, an open-source vector database, enhances the development of Retrieval Augmented Generation (RAG) applications by streamlining processes and improving efficiency. Its integration with popular embedding models simplifies text transformation into searchable vectors, while its hybrid search capability supports multimodal data retrieval. Additionally, Milvus offers a cost-effective solution for managing large knowledge bases through minimizing memory consumption, implementing tiered data storage, and leveraging intelligent caching and data-sharding techniques. Overall, Milvus helps developers build faster, more accurate, and cost-efficient RAG applications.

Date published
May 17, 2024

Author(s)
By Stephen Batifol

Language
English

Word count
744

Hacker News points
None found.

This tutorial demonstrates how to build a Multimodal Retrieval Augmented Generation (RAG) System, which allows the use of different types of data such as images, audio, videos, and text. The system utilizes OpenAI CLIP for understanding the connection between pictures and text, Milvus Standalone for efficient management of large-scale embeddings, Ollama for Llama3 usage on a laptop, and LlamaIndex as the Query Engine in combination with Milvus as the Vector Store. The tutorial provides code examples available on Github and explains how to run queries that can involve both text and images.

Date published
May 16, 2024

Author(s)
By Sachi Tolani

Language
English

Word count
334

Hacker News points
None found.

Zilliz has achieved AWS Generative AI Competency Partner designation, demonstrating its commitment to advancing generative AI technologies. As an AWS Differentiated Partner, Zilliz provides critical infrastructure and best practices for implementing transformative generative AI applications such as image retrieval, video analysis, NLP, recommendation engines, customized search, intelligent customer service, fraud detection, and more. The company's expertise combined with the scalability, performance, and security of AWS Cloud enables customers to unlock new possibilities and gain a competitive edge in their industries. Zilliz remains dedicated to fostering collaboration, knowledge sharing, and responsible AI practices while working closely with AWS and its customers to shape the future of generative AI.

Date published
May 15, 2024

Author(s)
By Christy Bergman

Language
English

Word count
1801

Hacker News points
None found.

This blog post discusses various ways to run the G-Generation part of Retrieval Augmented Generation (RAG) using different models and inference endpoints. The author provides step-by-step instructions on how to use Llama 3 from Meta, Mixtral from Mistral, and the newly announced GPT-4o from OpenAI. They also cover running these models locally or through Anyscale, OctoAI, and Groq endpoints. Additionally, the author explains how to evaluate answers using Ragas and provides a summary table of results for each model endpoint. The conclusion emphasizes the importance of considering answer quality, latencies, and costs when choosing an appropriate model and inference endpoint for the G-Generation part of RAG.

Date published
May 10, 2024

Author(s)
By Uppu Rajesh Kumar

Language
English

Word count
2958

Hacker News points
None found.

Milvus, an open-source vector database designed to store, index, and search massive amounts of vector data in real-time, can be integrated with LLMs in a generative feedback loop. This allows for continuous learning and improvement of the AI system. Feedback loops are crucial in ensuring the ongoing refinement of model outputs in AI systems, offering benefits such as adaptability to new data, reduced bias and errors, personalized model outputs, and enhanced creativity and innovation. Milvus's features make it suitable for enhancing the data-handling capabilities of LLMs, particularly in scenarios where feedback loops are used to refine predictive and generative accuracies.

Date published
May 9, 2024

Author(s)
By David Wang

Language
English

Word count
2043

Hacker News points
None found.

DSPy is a programmatic framework designed to optimize prompts and weights in language models (LMs), particularly in use cases where you integrate LMs across multiple pipeline stages. It provides various composable and declarative modules for instructing LMs in Pythonic syntax. Unlike traditional prompting engineering techniques that rely on manually crafting and tweaking prompts, DSPy learns query-answer examples and imitates this learning to generate optimized prompts for more tailored results. This allows for the dynamic reassembly of the entire pipeline, explicitly tailored to the nuances of your task, thus eliminating the need for ongoing manual prompt adjustments. DSPy has been integrated into the DSPy workflow as a retrieval module in the form of the MilvusRM Client, making it easier to implement a fast and efficient RAG pipeline. In this demonstration, we'll build a simple RAG application using GPT-3.5 (gpt-3.5-turbo) for answer generation. We use Milvus as the vector store through MilvusRM and DSPy to configure and optimize the RAG pipeline.

Date published
May 9, 2024

Author(s)
By Christy Bergman

Language
English

Word count
1017

Hacker News points
None found.

This blog discusses resource allocation for Milvus, an open-source vector database. It provides reference architectures based on specific numbers of users or requests per second (RPS) and different mixes of READ and WRITE operations. The article emphasizes the importance of understanding workload characteristics to determine Milvus' computational power and memory requirements. It also outlines a method for estimating resource needs, load testing, benchmarking, and concludes with recommendations for resource allocation based on data size and QPS requirements.

Date published
May 2, 2024

Author(s)
By Daniella Pontes

Language
English

Word count
1910

Hacker News points
None found.

Zilliz and Azure OpenAI have integrated to redefine similarity and semantic search, offering remarkable speed, intelligence, and safeguards. The collaboration combines Azure OpenAI's advanced generative AI capabilities with Zilliz's scalable search solutions, enhancing AI search functionalities and data retrieval. This partnership enables seamless integration of AI models and scalable search solutions for developers. Zilliz is a specialized data management system optimized for managing high-dimensional vector data on a large scale, while Azure OpenAI provides additional features like private networking, regional availability, and responsible AI content filtering. The integration of these technologies offers robust data storage, sophisticated indexing options, and comprehensive similarity metrics and retrieval mechanisms, enabling developers to create scalable and efficient AI-driven search solutions.

Date published
April 30, 2024

Author(s)
By Stephen Batifol

Language
English

Word count
1100

Hacker News points
None found.

Milvus 2.4 introduces multi-vector search and hybrid search capabilities, allowing simultaneous queries across multiple vector fields and integrating the results with re-ranking strategies. Hybrid search is a process of conducting searches across various vector fields within the same dataset. This tutorial demonstrates how to leverage Milvus's hybrid search capabilities using the eSci dataset and BGE-M3 model. The steps include preparing the dataset, generating embeddings with BGE-M3, setting up a Milvus collection, inserting data into the collection, and executing hybrid searches in Milvus.

Date published
April 28, 2024

Author(s)
By Ken Zhang

Language
English

Word count
1523

Hacker News points
None found.

Implementing Retrieval Augmented Generation (RAG) technology in chatbots can significantly enhance customer support by combining large language models with knowledge stored in vector databases from various fields. RAG systems consist of two core components: the Retriever and the Generator, which work synergistically to handle complex queries effectively. Compared to traditional LLMs, RAG offers several advantages such as reduced hallucination issues, enhanced data privacy and security, and real-time information retrieval. While advancements in LLMs also address these challenges, RAG remains a robust, reliable, and cost-effective solution due to its transparency, operability, and private data management capabilities. RAG technology is often integrated with vector databases, leading to the development of popular solutions like the CVP stack. Vector databases are favored in RAG implementations for their efficient similarity retrieval capabilities, superior handling of diverse data types, and cost-effectiveness. Ongoing engineering optimizations aim to enhance the retrieval quality of vector databases by improving precision, response speed, multimodal data handling, and interpretability. As demand for RAG applications grows across various industries, RAG technology will continue to evolve and revolutionize information retrieval and knowledge acquisition processes.

Date published
April 28, 2024

Author(s)
By Emily Kurze

Language
English

Word count
1467

Hacker News points
None found.

This guide provides an overview of open-source licensing in the context of AI technology, specifically vector databases and large language models (LLMs). Open source allows creators to make software or hardware available for free, often developed and maintained by community efforts. Understanding different license types is crucial as changes can significantly impact companies and businesses that rely on open-source software. The benefits of open-source vector databases and LLMs include rapid prototyping, increased trust and transparency, and reduced costs for developers. Various types of licenses exist, including permissive licenses (e.g., MIT License), copyleft licenses (e.g., GNU General Public License), weak copyleft licenses (e.g., GNU Affero General Public License), non-commercial licenses (e.g., Creative Commons Non-Commercial License), and public domain releases. Key organizations like the Open Source Initiative, Free Software Foundation, and Apache Software Foundation govern open-source licensing standards. The degrees of openness in different licensing models influence collaboration, innovation, and transparency in AI development. Licensing plays a vital role in shaping AI technologies' trajectory by governing accessibility, adaptability, and equitable distribution.

Date published
April 27, 2024

Author(s)
By Antony G.

Language
English

Word count
1330

Hacker News points
None found.

LangChain and Zilliz Cloud offer an effective combination to create AI-powered search systems. These systems use natural language processing (NLP) and machine learning algorithms to enhance the accuracy and relevance of information retrieval across business-specific data. With the rise of generative models, AI-powered search applications have become more prominent compared to traditional search methods. However, ensuring user privacy in these applications is critical due to ethical and legal implications. The integration of LangChain with Zilliz Cloud allows for the creation of custom search engines that prioritize data privacy while offering tailored solutions based on specific needs and data. Both tools provide robust frameworks for ensuring privacy and safety when utilizing large language models (LLMs), effectively preventing private data misuse and generating harmful or unethical content.

Date published
April 27, 2024

Author(s)
By James Luan

Language
English

Word count
2804

Hacker News points
None found.

Vector search is a technique used in data retrieval for RAG applications and information retrieval systems to find items or data points that are similar or closely related to a given query vector. While many vector database providers market their capabilities as easy, user-friendly, and simple, building a scalable real-world application requires considering various factors beyond the coding, including search quality, scalability, availability, multi-tenancy, cost, security, and more. To effectively deploy your vector database in your RAG application production environment with Milvus, follow these best practices: design an effective schema, plan for scalability, and select the optimal index and fine-tune performance.

Date published
April 26, 2024

Author(s)
By Christy Bergman

Language
English

Word count
658

Hacker News points
None found.

Milvus is an open source vector database that enables efficient search over large amounts of data. When deploying Milvus, it's crucial to select the optimal configuration to ensure efficient performance and resource utilization. Key points to consider include index selection, balancing memory usage, disk space, cost, speed, and accuracy; segment size and deployment configuration; and additional customization options available in the Enterprise version of Zilliz Cloud. The Milvus sizing tool provides a starting point for these configurations, but users should also consider their specific needs and requirements when choosing an index algorithm or segment size.

Date published
April 24, 2024

Author(s)
By Fendy Feng, and Jay Zhu

Language
English

Word count
1593

Hacker News points
None found.

This guide explores Milvus, an open-source vector database known for its horizontal scalability and fast performance. At the core of Milvus lies its robust storage system, which comprises meta storage, log broker, and object storage. The architecture is organized into four key layers: access layer, coordinator service, worker nodes, and storage. Milvus uses three main storage components to ensure data integrity and availability: meta storage (etcd), object storage (MinIO), and a log broker (Pulsar or Kafka). To evaluate and optimize the performance of Milvus storage, it is crucial to monitor disk write latency, I/O throughput, and disk drive performance. The guide provides recommendations for selecting appropriate block storage options from various cloud providers and offers strategies to enhance MinIO's throughput performance by using SSD or NVMe-type drives.

Date published
April 23, 2024

Author(s)
By Yujian Tang

Language
English

Word count
2820

Hacker News points
None found.

This tutorial demonstrates how to build retrieval augmented generation (RAG) applications using large language models (LLMs) without relying on OpenAI. The process involves serving embeddings with BentoML, inserting data into a vector database for RAG, setting up an LLM for RAG, and providing instructions to the LLM. Key components include BentoML for serving embeddings, OctoAI for accessing open-source models, and Milvus as the vector database. The example uses BentoML's Sentence Transformers Embeddings repository, a local Milvus instance using Docker Compose, and the Nous Hermes fine-tuned Mixtral model from OctoAI for RAG.

Date published
April 22, 2024

Author(s)
Abhiram Sharma

Language
English

Word count
1377

Hacker News points
None found.

Milvus is an open-source vector database designed to efficiently manage and retrieve high-dimensional vector data, making it ideal for use in artificial intelligence and machine learning applications. By integrating Milvus with Spring AI, developers can leverage advanced search capabilities and optimize their applications' performance and scalability. This integration allows users to perform complex queries and similarity searches quickly and accurately, enhancing user experiences and enabling more intelligent application behavior. Key features of Milvus include support for various indexing strategies, compatibility with different metric types, and the ability to handle large volumes of vector data through partitioning and sharding. Use cases for Milvus in Spring AI applications span across recommendation systems, content search engines, image and video recognition, and AI-driven chatbots and customer support.

Date published
April 19, 2024

Author(s)
By Stephen Batifol

Language
English

Word count
844

Hacker News points
8

This guide provides a beginner's approach to setting up a Retrieval Augmented Generation (RAG) system using Ollama, Llama 3, Milvus, and Langchain. The RAG technique enhances large language models (LLMs) by integrating additional data sources. In this tutorial, we will build a question-answering chatbot that can answer questions about specific information. Key components of the setup include indexing data using Milvus, retrieval and generation with Llama 3, and interaction with data using Langchain. The guide assumes familiarity with Docker and Docker Compose, as well as installation of Milvus Standalone, Ollama, and other necessary tools.

Date published
April 17, 2024

Author(s)
By Christy Bergman

Language
English

Word count
682

Hacker News points
None found.

Milvus is an open-source vector database with significant traction in Generative AI and RAG use cases. It offers flexible deployment options, including local and cloud (Zilliz) services. The main dependencies for Milvus standalone server include FAISS, etcd, Pulsar/Kafka, Tantivy, RocksDB, Minio/S3/GCS/Azure Blob Storage, Kubernetes, StorageClass, Persistent Volumes, Prometheus, and Grafana. The Docker image size for Milvus standalone container is around 300MB. It has a frequent release cycle with approximately one major release per month. Six SDKs are available in Python, Node, Go, C#, Java, and Ruby. Understanding these details can help organizations better plan and prepare for integrating Milvus into their technology stack.

Date published
April 16, 2024

Author(s)
By Li Liu

Language
English

Word count
2159

Hacker News points
2

The future of vector databases is closely tied to the evolution of product requirements and user demands. Key areas of development include cost-efficiency, hardware advancements, collaboration with advanced machine learning models, prioritizing retrieval accuracy, optimizing for offline use cases, expanding feature sets for diverse industries, and more. As AI continues to mature, these advancements will enable vector databases to support a broader range of applications across various sectors, enhancing their overall functionality and versatility in production environments.

Date published
April 16, 2024

Author(s)
Ehsanullah Baig

Language
English

Word count
3056

Hacker News points
None found.

Streamlining data processing using Zilliz Cloud Pipelines involves examining document chunking, a component of transforming unstructured data into a searchable vector collection. The platform enables use cases with semantic search in text documents and provides a critical building block for Retrieval-Augmented Generation (RAG) applications. Zilliz Cloud Pipelines include various functions like SEARCH_DOC_CHUNK, which convert the query text into vector embedding. It will then retrieve the top-K relevant document chunks, making it easier to find the related information based on the query’s meaning. The engineers at Zilliz designed Zilliz Cloud Pipelines to transform unstructured data from various sources into a searchable vector collection for busy Gen AI developers. This pipeline will take unstructured data, split it, convert it to embeddings, index it, and store it in Zilliz Cloud with the designated metadata.

Date published
April 15, 2024

Author(s)
By Charles Xie

Language
English

Word count
1604

Hacker News points
None found.

Charles Xie, CEO of Zilliz, discusses the evolution and future of AI and its influence on vector databases. He highlights how Zilliz developed Milvus, a vector database, before the advent of large language models (LLMs), emphasizing the importance of data management for unstructured data. The article also explores the transition from enterprise-centric to democratized AI, as well as the significance of vector databases in the age of Foundation Models and LLMs. Furthermore, it delves into the role of Milvus 3.0 in enhancing retrieval accuracy for RAG systems and how ChatGPT and vector databases complement each other in semantic search. Lastly, Xie shares his vision for Affordable General Intelligence within five years, aiming to make AI-solutions accessible to all individuals and businesses.

Date published
April 12, 2024

Author(s)
By Christy Bergman, and Cheng Su

Language
English

Word count
1761

Hacker News points
None found.

This blog discusses the use of Retrieval Augmented Generation (RAG) applications with open-source tools such as Ray Data and Milvus. The author highlights the performance boost achieved using Ray Data during the embedding step, where data is transformed into vectors. By using just four workers on a Mac M2 laptop with 16GB RAM, Ray Data was found to be 60 times faster than Pandas. The blog also presents an open-source RAG stack that includes BGM-M3 embedding model, Ray Data for fast, distributed embedding inference, and Milvus or Zilliz Cloud vector database. The author provides a step-by-step guide on how to set up these tools and use them to generate embeddings from data downloaded from Kaggle IMDB poster. Additionally, the blog discusses the benefits of using bulk import features in Milvus and Zilliz Cloud for efficient batch loading of vector data into a vector database.

Date published
April 11, 2024

Author(s)
By Stephen Batifol

Language
English

Word count
1333

Hacker News points
None found.

This guide provides step-by-step instructions on setting up Grafana and Loki to effectively monitor Milvus deployments. Milvus is a distributed vector database designed for storing, indexing, and managing massive embedding vectors. Grafana is an open-source platform for monitoring and observability, while Loki pairs with Grafana as a log aggregation system. Together, they offer a solid monitoring setup for Milvus and beyond. The prerequisites include Docker, Kubernetes, Helm, and kubectl. After setting up the K8s cluster, users can deploy Grafana and Loki using Helm. Finally, configure Grafana data sources and dashboard to visualize and query logs effectively.

Date published
April 8, 2024

Author(s)
Steffi Li

Language
English

Word count
1764

Hacker News points
None found.

The cost of open source vector databases can be complex and challenging to quantify. Engineers often start projects using free software like Milvus, but hardware costs soon arise. Running a distributed database requires setting up dependencies such as Kafka or Pulsar for WAL, etcd for metadata storage, and Kubernetes for orchestration. Additionally, costs include load balancers, monitoring and logging tools, EC2 instances for worker nodes, and storage solutions like S3 or Azure Blob. Some aspects of running an open-source vector database are difficult to quantify, such as capacity planning, setup phase tasks, routine maintenance, troubleshooting latency issues, and disaster recovery plans. Other costs include time to market, engineering morale and retention, and risk mitigation. To assess costs in vector database management, performance tests should be conducted to gather data on how the database handles real-life workloads. Optimizing for cost involves adopting dynamic scaling, adjusting recall accuracy, latency, and throughput according to project needs, and using MMap to store less data in memory. The decision on how to manage a vector database ultimately depends on comparing costs and making an intelligent economic choice based on the most cost-effective option.

Date published
April 5, 2024

Author(s)
James Luan

Language
English

Word count
1076

Hacker News points
None found.

Redis, an open-source database software, has transitioned from the BSD license to the Server Side Public License (SSPLv1), causing some controversy. This change may lead to multiple Linux distributors dropping Redis from their codebases, but alternative options like Valkey and Microsoft's Garnet are available. The shift in open-source licensing has been driven by cloud computing's impact on the traditional business model of open-source software companies. Some open-source projects have adopted more restrictive licenses to protect their profits, while others continue to offer permissive licenses and focus on commercial services. Companies like Zilliz are finding new ways to balance open-source and commercialization by offering unique capabilities in their managed services while maintaining compatibility with the open-source API.

Date published
April 4, 2024

Author(s)
Charles Xie

Language
English

Word count
1737

Hacker News points
1

Charles, CEO of Zilliz, discusses the evolution and future of vector databases in AI applications. He explains that vector databases are designed to manage and query unstructured data like images, videos, and natural languages through deep learning algorithms and semantic queries. They are widely used in recommendation systems, chatbots, and semantic search. The current landscape of vector databases includes purpose-built ones like Milvus, traditional databases with a vector search plugin like Elasticsearch, lightweight vector databases like Chroma, and more technologies with vector search capabilities like FAISS. Charles shares insights into building the Milvus vector database system, emphasizing its support for heterogeneous computing, both vertical and horizontal scalability, and offering a smooth developer experience from prototyping to production. He also provides guidance on choosing the right vector database for businesses based on performance requirements and projected data volume growth. Charles predicts that future vector databases will extend their capabilities beyond similarity-based search to include exact search or matching, as well as support additional vector computing workloads like clustering and classification.

Date published
April 3, 2024

Author(s)
Ash Naik

Language
English

Word count
794

Hacker News points
1

A group of four strangers, including a Product Manager, full-stack developers, and an AI enthusiast, came together during a monthly Hackathon in Seattle to build the SaveHaven project. The team developed a Retrieval Augmented Generation (RAG) app called SaveHaven that helps individuals contest property and income tax assessments by leveraging technologies like LlamaIndex, Milvus, and GPT from OpenAI. By automating data collection and analysis from public records, the app simplifies the tax appeal process for the general public. The team's experience serves as an example for future entrepreneurs to build meaningful innovations using GenAI technologies.

Date published
April 2, 2024

Author(s)
Werner Oswald

Language
English

Word count
797

Hacker News points
None found.

The author discovered their love for open-source image-generating AI systems and started searching through webpages to find cool images and the prompts that made them. They used those prompts to make their own images, but it took a lot of time. To speed up the process, they downloaded millions of prompts and put them into a Milvus vector database. The system was able to fetch similar results based on simple prompts entered into a UI. Users found that the system produced better results than what they were doing before with their regular prompts. The author chose Milvus for performance reasons, as it was five times faster than pgvector with almost the same code. They also added instructions telling the LLM that it was a prompt engineer and provided some example conversation history to get it to start producing wonderful images. The next step is to add the same function for negative prompts, which have a positive influence on how prompts can be used to generate images.

Date published
March 26, 2024

Author(s)
Christy Bergman

Language
English

Word count
1140

Hacker News points
None found.

JSON, or JavaScript Object Notation, is a flexible data format used for storage and transmission. It employs key-value pairs adaptively, making it ideal for NoSQL databases and API results. Milvus Client, a wrapper around the Milvus collection object, uses a flexible JSON "key":value format to allow schema-less data definitions. This makes it faster and less error-prone than defining a full schema upfront. The schema-less schema includes fields for id (str) and vector (str), with the rest of the fields determined flexibly when the data is inserted into Milvus. JSON data can be uploaded directly into Milvus, which also supports metadata filtering on JSON fields and JSON array data types.

Date published
March 26, 2024

Author(s)
Stephen Batifol

Language
English

Word count
1077

Hacker News points
None found.

Vector databases, designed to store high-dimensional data points, are particularly useful in handling unstructured data such as image recognition, natural language processing, and recommendation systems. The open-source nature of many vector database projects allows for diverse contributions from various individuals and organizations, fostering innovation and transparency. Open source also promotes accessibility, enabling a wider range of projects and innovations. Community collaboration is crucial in the development of vector databases, with knowledge sharing and inclusive participation playing significant roles. Resources such as well-maintained documentation, chat channels, hackathons, meetups, and conferences contribute to fostering a sense of community and driving innovation. Contributing to open-source vector databases involves finding contribution opportunities, engaging with the community, and understanding that contributions are not limited to coding. Success stories include improvements in scalability, performance, usability, and accessibility of vector databases due to open-source contributions and active community engagement. Challenges faced by these projects include managing a high volume and variety of contributions and balancing diverse interests and visions. However, with robust systems for tracking, reviewing, and integrating contributions, as well as transparent decision-making processes, these challenges can be addressed effectively. In conclusion, the open-source model has proven to be a driving force in advancing vector databases, breaking down barriers, and democratizing access to cutting-edge technology. The diverse community of contributors ensures that these tools are continually improving in terms of robustness, efficiency, and versatility.

Date published
March 20, 2024

Author(s)
Li Liu

Language
English

Word count
1587

Hacker News points
4

Milvus 2.4 introduces CAGRA (CUDA Anns GRAph-based), a GPU-based graph index that significantly enhances vector search performance. Leveraging the parallel capabilities of GPUs, CAGRA offers improved efficiency in both small and large batch queries compared to traditional methods like HNSW. Additionally, CAGRA accelerates index building by approximately 10 times. The integration of CAGRA into Milvus marks a significant milestone in overcoming challenges associated with GPU-based vector search algorithms and sets the stage for future advancements in high recall, low latency, cost efficiency, and scalability in vector search.

Date published
March 20, 2024

Author(s)
Steffi Li

Language
English

Word count
629

Hacker News points
None found.

Milvus 2.4, a significant update in search capabilities for large datasets, has been released. This version accelerates search efficiency and broadens the horizons towards a unified search platform capable of fulfilling diverse search use cases with exceptional speed and precision. Key highlights include support for NVIDIA's CAGRA Index, Multi-vector Search, Grouping Search, beta support for sparse vector embeddings, and other key enhancements. These updates significantly boost Milvus's performance and versatility for complex data operations.

Date published
March 19, 2024

Author(s)
Jiang Chen

Language
English

Word count
762

Hacker News points
None found.

Zilliz Cloud has partnered with Confluent to unlock semantic search for real-time updates powered by Apache Kafka, Apache Flink, and the Milvus vector database. The new cloud-native, serverless Apache Flink service is now available directly alongside cloud-native Apache Kafka on Confluent's fully managed data streaming platform. This integration enables users to easily build high-quality, reusable data streams for real-time GenAI applications. By leveraging Kafka and Flink as a unified platform, teams can connect to data sources across any environment, clean and enrich data streams on the fly, and deliver them in real-time to the Milvus vector database for efficient semantic search or recommendation.

Date published
March 19, 2024

Author(s)
Stephen Batifol

Language
English

Word count
1207

Hacker News points
None found.

The author discusses the problem of losing valuable content from Meetup events and how similarity search techniques can be used to address this issue. They introduce Milvus, an open-source vector database that excels in managing complex data landscapes, and SentenceTransformers, a Python framework for generating text embeddings. The author demonstrates how to use these tools to create a system that searches for similar content within Meetup descriptions. By using OpenAI GPT-3.5-turbo to summarize the content of Meetups, they aim to improve search results by reducing noise in event descriptions.

Date published
March 18, 2024

Author(s)
Christy Bergman

Language
English

Word count
1018

Hacker News points
2

Retrieval Augmented Generation (RAG) is an approach to building AI-powered chatbots that answer questions based on data the model has been trained on. However, natural language retrieval accuracy remains low, necessitating experiments to tune RAG parameters before deployment. Large Language Models (LLMs) are increasingly being used as judges for modern RAG evaluation, automating and speeding up evaluation while offering scalability and saving time and cost spent on manual human labeling. Two primary flavors of LLM-as-judge for RAG evaluation include MT-Bench and Ragas, with the latter emphasizing automation and scalability for RAG evaluations. Key data points needed for Ragas evaluation include the question, contexts, answer, and ground truth answer.

Date published
March 13, 2024

Author(s)
Lin Liu

Language
English

Word count
467

Hacker News points
None found.

The AI-driven car repair assistant project aims to create an interactive and reliable platform for drivers seeking automotive advice and solutions. Using the OpenAI LLM model with Milvus vector database, the product combines user inputs with AI capabilities to provide relevant diagnostic suggestions. This tool hopes to revolutionize car maintenance and repair in today's digital world by refining the process of identifying car issues and broadening access to expert advice.

Date published
March 11, 2024

Author(s)
Steffi Li

Language
English

Word count
414

Hacker News points
None found.

Zilliz Cloud is now available on Azure Marketplace, following its successful integration into AWS and GCP marketplaces. This expansion simplifies subscription management and billing, allowing smoother integration into developers' existing Azure workflows. Getting started with Zilliz Cloud on Azure Marketplace involves searching for "Zilliz Cloud," subscribing, configuring the project and SaaS details, linking the Azure Marketplace subscription with a Zilliz Cloud account, and setting Azure Marketplace as the payment method. This integration enables developers to easily incorporate Zilliz Cloud's powerful capabilities into their AI projects.

Date published
March 11, 2024

Author(s)
Yujian Tang

Language
English

Word count
1380

Hacker News points
None found.

In 2023, large language models (LLMs) gained immense popularity, leading to the development of two main types of LLM applications: retrieval augmented generation (RAG) and AI agents. RAG involves using a vector database like Milvus to inject contextual data, while AI Agents use LLMs to utilize other tools. This article combines these two concepts by building an AI Agent for RAG using Milvus and LlamaIndex. The tech stack includes Milvus, LlamaIndex, and OpenAI (or alternatively OctoAI or HuggingFace). The process involves spinning up Milvus, loading data into it via LlamaIndex, creating query engine tools for the AI Agent, and finally building the AI Agent for RAG. This architecture allows an AI Agent to perform RAG on documents by providing it with the necessary tools for querying a vector database.

Date published
March 6, 2024

Author(s)
Stephen Batifol

Language
English

Word count
371

Hacker News points
None found.

Stephen Batifol, Developer Advocate at Zilliz in Berlin, is organizing events and creating content to help people understand and use Milvus. With experience as an Android developer, data scientist, machine learning engineer, and now a developer advocate, he has always aimed to simplify the work of data scientists and software engineers. His interest in open-source projects led him to Zilliz, where he is excited to build a community from scratch and engage with people at various events. Batifol plans to immerse himself technically in the domain, start a new Meetup series in Berlin, and release open-source projects soon. He encourages interested candidates to join Zilliz as Developer Advocates across different regions.

Date published
March 5, 2024

Author(s)
James Luan

Language
English

Word count
1858

Hacker News points
38

Google's Gemini 1.5, an LLM capable of handling contexts up to 10 million tokens, and OpenAI's Sora, a text-to-video model, have sparked discussions about the future of AI, particularly the role and potential demise of Retrieval Augmented Generation (RAG). Gemini 1.5 Pro supports ultra-long contexts of up to 10 million tokens and multimodal data processing. In a "needle-in-a-haystack" evaluation method, Gemini 1.5 Pro achieves 100% recall from up to 530,000 tokens and maintains over 99.7% recall from up to 1M tokens. Even with a super long document of 10M tokens, the model retains an impressive 99.2% recall rate. While Gemini excels in managing extended contexts, it grapples with persistent challenges encapsulated as the 4Vs: Velocity, Value, Volume, and Variety. LLMs’ 4Vs Challenges include hurdles in achieving sub second response times for extensive contexts, considerable inference costs associated with generating high-quality answers in long contexts, vastness of unstructured data that may not be adequately captured by an LLM, and diverse range of structured data. Strategies for optimizing RAG effectiveness include enhancing long context understanding, utilizing hybrid search for improved search quality, and leveraging advanced technologies to enhance RAG’s performance. The RAG framework is still a linchpin for the sustained success of AI applications. Its provision of long-term memory for LLMs proves indispensable for developers seeking an optimal balance between query quality and cost-effectiveness.

Date published
March 4, 2024

Author(s)
Frank Liu

Language
English

Word count
1436

Hacker News points
43

The blog post discusses the use of vector databases, such as Milvus or Zilliz Cloud, as a JSON (or relational) datastore. It explains how to create a collection in Milvus and perform CRUD operations on JSON data stored within it. The author demonstrates querying, updating, and deleting records using Python code snippets. Additionally, the post introduces a package called milvusmongo that implements basic CRUD functionality across collections using Milvus as the underlying database instead of MongoDB. The author emphasizes that vector databases are not meant to replace NoSQL databases or lexical text search engines but can be used as an efficient data store for solo developers and small teams, with the option to optimize infrastructure usage later as they grow.

Date published
Feb. 29, 2024

Author(s)
Steffi Li

Language
English

Word count
820

Hacker News points
None found.

Zilliz has introduced Zilliz Cloud Bring Your Own Cloud (BYOC) to provide greater data sovereignty and compliance. This solution allows customers to use Zilliz Cloud's managed services while keeping their data within their private network. The architecture of Zilliz Cloud BYOC is built on two main pillars: the Data Plane, which encompasses all essential components for data collection, management, and query processing; and the Control Plane, responsible for deployment, management, and seamless coordination across all instances of the Zilliz Data Plane. The new deployment model in BYOC lets customers deploy the Data Plane within their own Virtual Private Cloud (VPC) while the Control Plane remains managed by Zilliz. This setup offers benefits such as data security and compliance, fine-grained control, and cost savings. Security measures include adherence to the Principle of Least Privilege, controlled access for software updates, and data plane access restrictions. BYOC is currently available on AWS with plans to expand to other cloud providers in the future.

Date published
Feb. 28, 2024

Author(s)
Fendy Feng

Language
English

Word count
650

Hacker News points
None found.

Sohu, a NASDAQ-listed company, partnered with Milvus to enhance its news recommendation system. The outdated legacy vector search stack in the recommender system was struggling to deliver real-time, personalized news due to slow retrieval and scalability issues. Milvus, an open-source vector database, provided a solution for handling large datasets and improving classification accuracy of short-text news articles. Sohu News integrated Milvus into its recommender system using a dual-tower structure and achieved a 10x faster vector retrieval speed and significantly improved recommendation accuracy. The collaboration with Milvus has transformed the user experience by offering more personalized and engaging news content.

Date published
Feb. 27, 2024

Author(s)
Christy Bergman

Language
English

Word count
1579

Hacker News points
None found.

This blog post discusses the use of embedding models in Retrieval Augmented Generation (RAG) applications. RAG is an approach used to enhance question-answering bots by integrating domain knowledge into AI's knowledge base. The process involves using embedding models to generate vector embeddings of chunks of text from all documents, followed by indexing and search using the same embedding model. Finally, a large language model (LLM) generates an answer based on the given domain knowledge. The most common type of embedding model is SBERT (Sentence-BERT), which specializes in understanding complete sentences. The HuggingFace MTEB Leaderboard provides a list of embedding models sorted by retrieval performance, making it easier for developers to choose the best model for their needs. Zilliz Cloud Pipelines support various embedding models, including BAAI/bge-base-en(or zh)-v1.5, VoyageAI's voyage-2 and voyage-code-2, and OpenAI's text-embedding-3-small(or large). Each model has its advantages and is best suited for different use cases. In conclusion, embedding models play a crucial role in enhancing AI retrieval capabilities by integrating domain knowledge into the AI's knowledge base. The choice of an appropriate embedding model depends on factors such as context length, embedding dimensions, and specific use case requirements.

Date published
Feb. 26, 2024

Author(s)
Yujian Tang

Language
English

Word count
2044

Hacker News points
None found.

This blog discusses building Retrieval Augmented Generation (RAG) applications without using OpenAI's GPT models. The authors demonstrate how to build RAG apps with Mixtral, Milvus, and OctoAI. They also provide an overview of the tools involved in this process: Mixtral as the LLM, Milvus as the vector database, OctoAI for serving the LLM and embedding model, and LangChain as the orchestrator. The tutorial covers setting up RAG tools, loading data into a vector database, querying data with OctoAI and Mixtral, and leveraging Mixtral's multilingual capabilities.

Date published
Feb. 23, 2024

Author(s)
Yujian Tang

Language
English

Word count
1514

Hacker News points
None found.

This tutorial explores the concept of multimodal embeddings using open-source tools like Voxel51 and Milvus. It covers the meaning of "multimodal", how Milvus handles multimodal embeddings, examples of multimodal models, and how to use FiftyOne and Milvus for multimodal embedding exploration. The tutorial uses Fashion MNIST dataset with CLIP-VIT model from OpenAI to demonstrate the process. It also discusses how to further customize FiftyOne for data exploration with Milvus and provides a summary of exploring multimodal embeddings with Voxel51 and Milvus.

Date published
Feb. 16, 2024

Author(s)
James Luan

Language
English

Word count
3009

Hacker News points
2

The article details the creation of Zilliz Cloud, a fully managed service powered by Milvus, the most adopted open-source vector database, developed from the ground up over eighteen months. It covers the design choices and invaluable insights gained during the journey to build this cloud service. The author emphasizes maximizing the use of mature third-party products, simplifying architecture, anticipating day 2 challenges from day 1, and focusing on cloud finops as key principles for building a successful cloud service. They also discuss the lessons learned while creating a scalable Vector Search Service on the public cloud and acknowledge the support of their users in this endeavor.

Date published
Feb. 12, 2024

Author(s)
Christy Bergman

Language
English

Word count
577

Hacker News points
None found.

A recent regression in Milvus has caused an error when using Langchain v0.1.5 to connect with it, specifically a "KeyError: 'pk'" error due to the absence of an automatically generated primary key field. The temporary solution is to downgrade to Langchain version <= v0.1.4 until the fix is officially merged. A permanent solution will be provided in an upcoming update that addresses this issue by handling cases where "pk" is not present during insertion. Until then, users can workaround the problem by downgrading their Langchain version or waiting for the official fix.

Date published
Feb. 9, 2024

Author(s)
Jiang Chen

Language
English

Word count
857

Hacker News points
None found.

Zilliz has released an update to its Cloud Pipelines, focusing on embedding models and usability improvements. The February release includes new 3rd-party embedding models from OpenAI and Voyage AI, providing a total of six options for users. Additionally, the platform now supports all dedicated vector db clusters in GCP's us-west-2 region, enhancing performance and reliability. Usability improvements include a new "Run Pipeline" page, local file upload feature, and support for running pipelines on any type of vector database cluster.

Date published
Feb. 8, 2024

Author(s)
Charles Xie

Language
English

Word count
393

Hacker News points
None found.

Zilliz has joined the AI Alliance, a consortium promoting open innovation in AI for responsible development and safe practices. The company's journey into open source began with its vector database Milvus, which was donated to the Linux Foundation. Open-source projects foster transparency, collaboration, innovation, and accessibility. Zilliz is committed to working alongside other industry players within the AI Alliance to shape a future where AI benefits everyone and positively impacts society.

Date published
Feb. 8, 2024

Author(s)
Jiang Chen

Language
English

Word count
1107

Hacker News points
None found.

This integration enables developers to effortlessly transfer data from Spark/Databricks to Milvus/Zilliz Cloud, whether in real-time or batch mode. By leveraging the Databricks Connector for Apache Arrow, developers can streamline their workflow and focus on building efficient and scalable AI solutions using these powerful technologies. The integration approach involves connecting Spark to Milvus through a shared filesystem such as S3 or MinIO buckets. By granting access to Spark or Databricks, the Spark job can use Milvus connectors to write data to the bucket in batch and then bulk-insert the entire collection for serving. To help developers get started quickly, we have prepared a notebook example that walks them through the streaming and batch data transfer processes with Milvus and Zilliz Cloud. This integration empowers developers to build efficient and scalable AI solutions, unlocking the full potential of these powerful technologies. For more information on this integration and its use cases, check out the official documentation for Databricks Connector for Apache Arrow.

Date published
Feb. 7, 2024

Author(s)
Steffi Li

Language
English

Word count
623

Hacker News points
None found.

Zilliz Cloud, a fully managed Milvus vector database that supports various AI applications, is now available on Google Cloud Marketplace. This integration simplifies billing as charges will appear directly on the developer's regular Google Cloud bill. Users can easily subscribe to the Zilliz service using their existing GCP account and access all features without upfront costs. A 100 credit bonus is available for new sign-ups, enabling developers to kickstart their journey with Zilliz Cloud on GCP.

Date published
Feb. 7, 2024

Author(s)
Jiang Chen

Language
English

Word count
694

Hacker News points
None found.

Zilliz Cloud Pipelines has integrated the Voyage AI embedding models, voyage-2 and voyage-code-2, which have shown outstanding performance in retrieval tasks related to source code, technical documentation, and general tasks. The incorporation of these models enhances the RAG system implemented with various embedding models for code-related tasks. Notably, when compared to other popular embedding models on code datasets, Voyage's models demonstrate significantly better retrieval capability and lead to over ten percentage point improvements in Answer Correctness and overall performance scores.

Date published
Feb. 6, 2024

Author(s)
Sarah Tang

Language
English

Word count
1157

Hacker News points
None found.

Zilliz Cloud has introduced enhanced Role-Based Access Control (RBAC) functionality, providing more nuanced RBAC capabilities to improve access management and data isolation. The updated system features two primary categories of roles - Operation Layer Roles and Data Layer Roles - catering to diverse developer requirements. In the operational layer, Zilliz Cloud has four predefined Organization and Project Roles: Organization Owner, Organization Member, Project Owner, and Project Member. Additionally, it offers three predefined Cluster Roles in the data layer: Admin, Read-Write, and Read-Only. Users can also create custom roles to fine-tune permissions for specific collections or operations. The enhanced RBAC capabilities are exemplified through real-world use cases such as cross-team collaboration in a medium-sized company and managing a RAG-based knowledge base. These features ensure effective data management, improved security, and efficient resource allocation.

Date published
Feb. 5, 2024

Author(s)
Fendy Feng

Language
English

Word count
1401

Hacker News points
None found.

In this comparison, we delve into the functionalities and performance of two open-source vector databases: Milvus and Chroma. We assess these platforms based on their capabilities in handling vector data storage, indexing, searching, scalability, and ecosystem support. Additionally, we examine the purpose-built features and performance trade-offs between Milvus and Chroma. Milvus is a versatile and comprehensive open-source vector database, offering extensive support for various index types, including 11 different options. It supports hybrid search operations and offers flexible in-memory and on-disk indexing configurations. Furthermore, Milvus ensures strong consistency and provides multi-language SDKs encompassing Python, Java, JavaScript, Go, C++, Node.js, and Ruby. On the other hand, Chroma is a relatively simpler vector database with a primary focus on enabling easy initiation and usage. It currently supports only the HNSW algorithm for its KNN search operations and lacks advanced features such as RBAC support. Additionally, it offers limited SDK options, primarily focusing on Python and JavaScript. While Chroma's simplicity may be adequate for specific applications, its limitations could restrict its adaptability across diverse use cases. With its comprehensive functionality and extensive feature set, Milvus emerges as a more versatile and scalable solution for addressing a broader spectrum of vector data management needs. In the upcoming Milvus 2.4 release, we plan to support the inverted index with tantivy, which promises significant enhancements to prefiltering speed. This update further solidifies Milvus as a cutting-edge open-source vector database that continues to evolve and adapt to emerging requirements in the AI ecosystem. In summary, while Chroma offers simplicity and ease of use, Milvus distinguishes itself with its comprehensive feature set, extensive index type support, and robust multi-language SDKs. As a result, Milvus remains a highly recommended open-source vector database for developers and organizations seeking to optimize their applications' performance, scalability, and data management capabilities. Milvus Lite, a lightweight alternative to the full Milvus version, has also been introduced. It aims to preserve the ease of initiation while retaining an extensive set of features, making it particularly useful for specific use cases such as integration into Python applications without adding extra weight or spinning up a Milvus instance in Colab or Notebook for quick experiments.

Date published
Feb. 2, 2024

Author(s)
Yujian Tang

Language
English

Word count
1420

Hacker News points
None found.

Milvus is a distributed system designed to scale vector operations, addressing the challenges of scalability in vector databases. Unlike traditional databases, vector data doesn't require complex transactions and has diverse use cases that necessitate tunable tradeoffs between performance and consistency. Some vector data operations are computationally expensive, requiring elastic resource allocation. Milvus achieves horizontal scaling through its deliberate design as a distributed system, overcoming the limitations of single-instance databases. It contains four layers: access, coordination, worker, and storage. The separation of concerns in querying, data ingestion, and indexing allows for independent scaling of each operation. Milvus ensures large-scale write consistency through sharding and supports pre-filtering metadata search to enhance efficiency. Its unique architecture provides benefits such as horizontal scaling and flexibility, making it a suitable choice for cloud-native vector databases catering to diverse use cases.

Date published
Feb. 1, 2024

Author(s)
Alexandr Guzhva

Language
English

Word count
1665

Hacker News points
None found.

Cardinal is a new vector search engine developed by Zilliz, which has demonstrated a threefold increase in performance compared to the previous version. It offers a search performance (QPS) that reaches tenfold that of Milvus. Cardinal is capable of performing brute-force search, creating and modifying ANNS indices, working with various input data formats, and filtering results during the search based on user-provided criteria. The key to Cardinal's speed lies in its algorithm optimizations, engineering optimizations, low-level optimizations, and AutoIndex feature for search strategy selection.

Date published
Jan. 30, 2024

Author(s)
James Luan

Language
English

Word count
580

Hacker News points
None found.

James Luan, VP of Engineering at Zilliz, discusses the company's commitment to innovation and community collaboration through open-source projects like Milvus. The four essential freedoms of open source, as emphasized by Richard Stallman, guide their approach to feature deployment from Milvus to Zilliz Cloud. They follow three fundamental principles: iteration with precision, testing the waters, and quality over speed. Despite occasional delays in feature deployment, they prioritize maintaining a robust and reliable platform while encouraging community feedback for continuous improvement.

Date published
Jan. 30, 2024

Author(s)
Frank Liu

Language
English

Word count
1034

Hacker News points
None found.

In 2023, vector databases gained popularity due to the widespread adoption of ChatGPT and other large language models (LLMs). Zilliz Cloud, a vector database service, has seen increased usage in retrieval-augmented generation systems as well as various search and retrieval applications. The platform aims to help computers understand human-generated data such as text, images, bank transactions, and user behaviors. Zilliz Cloud recently introduced new features like range search, multi-tenancy & RBAC, up to 10x improved search & indexing performance, and more in response to customer demand. These enhancements have proven critical for users developing applications that require a purpose-built vector database supporting essential database features and various workloads. Three real-world use cases demonstrate the importance of these new features: efficient autonomous agents, product recommendation systems, and AI-powered drug discovery. In each case, Zilliz Cloud's performance optimizations, adaptability, and range search feature have enabled users to overcome challenges in their respective applications. The platform's ability to handle diverse data types and workloads makes it a valuable tool for developers working with vector databases.

Date published
Jan. 30, 2024

Author(s)
Steffi Li

Language
English

Word count
1575

Hacker News points
1

Zilliz has introduced new features to its cloud product, enhancing vector search performance and ensuring enterprise-grade security. The latest updates include the Cardinal Search Engine, which delivers a 10x performance boost; Milvus 2.3, offering advanced vector search capabilities for production workloads; GCP Marketplace integration, simplifying budget planning, payment, and procurement processes; and the Databricks Connector, enabling data migration and transformation without custom code. Additionally, Zilliz Cloud now supports role-based access control (RBAC) across both control and data layers for enhanced security and compliance.

Date published
Jan. 29, 2024

Author(s)
Christy Bergman

Language
English

Word count
1219

Hacker News points
None found.

This blog delves into the concepts of sharding, partitioning, and segments in distributed databases like Milvus. Sharding refers to horizontal data partitioning across multiple servers, enabling faster writing by utilizing distributed systems. Partitioning organizes data for efficient retrieval, optimizing targeted reads. Automatic partitioning is recommended as it minimizes errors and ensures optimal performance. Each shard and partition has segments of data, with growing and sealed segments being the smallest unit in Milvus for load balancing. The default segment size is 512 MB, but adjustments should only be made if there are large machine resources available.

Date published
Jan. 26, 2024

Author(s)
Li Liu

Language
English

Word count
1651

Hacker News points
5

The BigANN challenge is an important competition in the vector search domain, fostering the development of indexing data structures and search algorithms. Zilliz's solution dominated all four tracks of BigANN 2023, achieving a remarkable up to 2.5x performance improvement. This year's BigANN introduced more significant challenges with larger datasets and complex scenarios across four tracks: filtered, out-of-distribution, sparse, and streaming variants of ANNS. Zilliz's solution is based on graph algorithms and optimizations driven by the specific characteristics of each track. The company plans to integrate these insights into their products, extending their impact on a broader range of issues.

Date published
Jan. 17, 2024

Author(s)
Yujian Tang

Language
English

Word count
1615

Hacker News points
None found.

This post discusses the creation of a Conversational Retriever Augmentation Generator (RAG) application without using OpenAI. The tech stack includes LangChain, Milvus, and Hugging Face for embedding models. The process involves setting up the conversation RAG stack, creating a conversation, asking questions, and testing the app's memory retention. The example demonstrates how to use Nebula, a conversational LLM created by Symbl AI, in place of OpenAI's GPT-3.5.

Date published
Jan. 16, 2024

Author(s)
Fendy Feng

Language
English

Word count
564

Hacker News points
None found.

Singapore-based tech company Mozat has developed an innovative wardrobe management approach with its app, Stylepedia. The app is designed to redefine how users engage with fashion by integrating Milvus, an open-source vector database, to power its smart image search system. This integration allows Stylepedia to manage a rapidly growing database of clothing images, respond to user queries in milliseconds, and handle user-uploaded photos with varying resolutions. By leveraging Milvus, Stylepedia offers personalized style recommendations, facilitates user connections, and enables image searches for similar clothing items.

Date published
Jan. 15, 2024

Author(s)
Steffi Li

Language
English

Word count
476

Hacker News points
None found.

Milvus 2.3.4, the latest update of the vector database platform, introduces enhancements to improve availability and usability. The release focuses on streamlining monitoring, data import, and search efficiency. Key highlights include access logs for improved system performance insights, Parquet file support for efficient large-scale data operations, Binlog index on growing segments for faster search within expanding datasets, and other improvements such as increased collection/partition support, enhanced memory efficiency, clearer error messaging, faster data loading speeds, and better query shard balance. Developers are encouraged to visit the release notes for a comprehensive overview of all new features and enhancements in Milvus 2.3.4.

Date published
Jan. 11, 2024

Author(s)
Yujian Tang

Language
English

Word count
1479

Hacker News points
None found.

Distributed systems are crucial for vector search applications, offering scalability, fault tolerance, enhanced performance, and global accessibility. Consistency is a key principle in distributed systems, ensuring that data remains accurate across all replicas. The fully distributed Milvus vector database offers Tunable Consistency through its unique architecture, allowing users to scale out data writing while maintaining consistency without additional tools. Consistency levels in Milvus include Eventual, Session, Bounded, and Strong. Eventual consistency ensures that data will eventually be consistent across all replicas, prioritizing speed over immediate data updates. Session consistency maintains up-to-date data within a single session, while Bounded Consistency forces instances and replicas to sync within a certain period. Strong consistency ensures immediate data availability but comes with increased latency. Understanding the levels of consistency is essential for building resilient, high-performing applications that utilize distributed systems.

Date published
Jan. 9, 2024

Author(s)
Robert Guo

Language
English

Word count
2284

Hacker News points
None found.

OpenAI's built-in retrieval feature has storage constraints, performance gaps, and cost concerns. The current pricing model of $0.2 per GB per day is expensive compared to traditional document services like Office 365 and Google Workspace. However, the server cost for serving vectors is only about $0.30 per day, which is a bargain compared to the pricing. The architecture of OpenAI Assistants' retrieval feature has limitations such as a maximum of 20 files per assistant, a cap of 512MB per file, and a hidden limitation of 2 million tokens per file. The current architecture may not scale well enough to support larger businesses with more extensive data requirements. To address these challenges and reduce costs, the service's architecture needs to be optimized. A refined vector database solution, hybrid disk/memory vector storage, streamlining disaster recovery by pooling system data, and multi-tenancy support for diverse user base are suggested improvements. Among popular vector databases, Milvus is considered the most mature open-source option with effective separation of system and query components, isolation of query components through Resource Group feature, hybrid memory/disk architecture, and application-level multi-tenancy facilitated by RBAC and Partition features. However, no single vector database solution can comprehensively address all challenges and meet every design requirement for imminent infrastructure development. The choice of vector databases should be tailored to specific requirements to effectively navigate the complexities of optimizing OpenAI Assistants' architecture.

Date published
Jan. 5, 2024

Author(s)
Cheney Zhang

Language
English

Word count
2134

Hacker News points
None found.

The OpenAI Assistants' retrieval feature has been a topic of discussion in the AI community, as it incorporates Retrieval Augmented Generation (RAG) capabilities for question-answering. A comparison between OpenAI's built-in RAG and a customized RAG using Milvus shows that while the former slightly outperforms in answer similarity, the latter performs better in context precision, faithfulness, answer relevancy, and correctness. The Milvus-powered Customized RAG system also has higher Ragas Scores than OpenAI's built-in RAG. This superior performance is attributed to factors such as effective utilization of external data, better document segmentation and data retrieval, and the ability for users to adjust parameters in the customized RAG pipeline.

Date published
Jan. 4, 2024

Author(s)
Steffi Li

Language
English

Word count
859

Hacker News points
1

The blog post discusses the disparities between benchmark results of Qdrant's vector database technology and VectorDB Bench, which uses Milvus. It highlights three reasons for these differences: outdated Milvus version used in testing, improper use of Milvus by only using Growing Segments, and benchmark-driven optimizations for Qdrant that may compromise operational flexibility in real-world scenarios. The post emphasizes the importance of trustworthy and comprehensive benchmarking for vector databases and suggests developers should access truthful and precise benchmarks or conduct their own tests against their data to make informed decisions when choosing a vector database.

Date published
Dec. 29, 2023

Author(s)
Cheney Zhang

Language
English

Word count
1700

Hacker News points
1

Optimizing Retrieval Augmented Generation (RAG) applications involves using methodologies, metrics, and evaluation tools to enhance their reliability. Three categories of metrics are used in RAG evaluations: those based on the ground truth, those without the ground truth, and those based on LLM responses. Ground truth metrics involve comparing RAG responses with established answers, while metrics without ground truth focus on evaluating the relevance between queries, context, and responses. Metrics based on LLM responses consider factors such as friendliness, harmfulness, and conciseness. Evaluation tools like Ragas, LlamaIndex, TruLens-Eval, and Phoenix can help assess RAG applications' performance and capabilities.

Date published
Dec. 27, 2023

Author(s)
Fendy Feng

Language
English

Word count
614

Hacker News points
None found.

Picdmo, an AI-powered photo management app, sought to improve its search performance and user experience. The team initially used Milvus, an open-source vector database, but found it labor-intensive and financially burdensome. They then integrated Zilliz Cloud, a fully managed Milvus service, into their infrastructure. This resulted in response times plummeting from 8 seconds to less than 1 second, even under extreme data loads. The adoption of Zilliz Cloud brought efficient search performance, substantial time and cost savings, and responsive support from the Zilliz team. As Picdmo evolves into a comprehensive multimedia application, its collaboration with Zilliz remains crucial for future features.

Date published
Dec. 26, 2023

Author(s)
Li Liu

Language
English

Word count
1363

Hacker News points
None found.

In the data-driven world, the exponential growth of unstructured data has led to the rise of vector databases. These powerful tools specialize in storing, indexing, and searching unstructured data through high-dimensional numerical representations known as vector embeddings. They are used for building recommender systems, chatbots, and applications for searching similar images, videos, and audio. When selecting a vector database, scalability, functionality, and performance are the top three most crucial metrics to consider. Scalability is essential for accommodating growing data demands effectively, while functionality includes both vector-oriented features like support for multiple index types and database-oriented features such as Change Data Capture (CDC) and multi-tenancy support. Performance is evaluated using benchmarking tools like ANN-Benchmark and VectorDBBench, which measure recall rate, QPS, latency, and other metrics. Various vector search technologies are available beyond vector databases, including vector search libraries, lightweight vector databases, vector search plugins, and purpose-built vector databases. Each type has its strengths and weaknesses, so the choice depends on specific business needs.

Date published
Dec. 25, 2023

Author(s)
Yujian Tang

Language
English

Word count
1506

Hacker News points
None found.

This post discusses database schemas, specifically focusing on vector databases and their dynamic schema feature. It explains that SQL databases have predefined schemas while NoSQL databases typically have a dynamic or schemaless schema. The Milvus vector database supports dynamic schema, allowing users to add data in JSON format without defining attributes when creating the database. The article covers how to use dynamic schema with the Milvus vector database and how the feature is implemented. It also discusses the pros and cons of dynamic schemas, such as ease of setup and flexibility but slower filtered search compared to fixed schemas.

Date published
Dec. 21, 2023

Author(s)
Fendy Feng

Language
English

Word count
913

Hacker News points
None found.

Trend Micro, a global leader in cybersecurity, has integrated Milvus, an open-source vector database, into their security infrastructure to enhance APK (Android application package) security. The company initially used MySQL for APK similarity search but faced scalability issues as the dataset grew. They then shifted focus to Faiss, which excelled in speed but lacked critical features required for a production environment. Milvus addressed these challenges with seamless integration with mainstream vector index libraries and simple, intuitive APIs. The implementation of Milvus has resulted in low query latency and high data import speed, significantly enhancing Trend Micro's ability to detect and neutralize harmful APKs.

Date published
Dec. 17, 2023

Author(s)
Christy Bergman

Language
English

Word count
1014

Hacker News points
None found.

The text discusses the use of vector databases like Milvus and Zilliz Cloud, which allow hybrid vector and scalar searches. It explains how metadata filtering can be used to perform more precise results that cater to specific needs by limiting search with certain conditions using boolean expressions on scalar fields or primary key field. The text also provides a step-by-step guide on how to create collections and pipelines in Zilliz Cloud, as well as searching via the web console or API calls.

Date published
Dec. 14, 2023

Author(s)
Fendy Feng

Language
English

Word count
659

Hacker News points
None found.

BIGO, the owner of short video platform Likee, has leveraged Milvus, an open-source vector database, to optimize its duplicate video removal process. With millions of daily uploads on Likee, the proliferation of duplicate videos posed a threat to content quality and user experience. Previously, BIGO used FAISS for similarity search but faced limitations in managing massive vectors. Milvus provided faster query responses and scalability, improving throughput and efficiency. The transformation involved converting new video frames into feature vectors and matching them against an extensive database of existing content using cutting-edge technologies like Kafka, deep learning models, and relational databases. BIGO plans to extend Milvus's capabilities for content moderation, restriction, and customized video services in the future.

Date published
Dec. 12, 2023

Author(s)
Cheney Zhang

Language
English

Word count
1531

Hacker News points
None found.

Prompt engineering techniques are being used to help large language models (LLMs) handle pronouns and other complex coreferences in retrieval augmented generation (RAG) systems. RAG combines the power of LLMs with a vector database acting as long-term memory, enhancing the accuracy of generated responses. One example is Akcio, an open source project that offers a robust question-answer system. However, implementing RAG systems introduces challenges, particularly in multi-turn conversations involving coreference resolution. Researchers are turning to LLMs like ChatGPT for coreference resolution tasks, but they occasionally produce direct answers instead of following the prompt instructions. A refined approach using few-shot prompts and Chain of Thought (CoT) methods has been developed to guide ChatGPT through coreference resolution, resulting in coherent responses.

Date published
Dec. 11, 2023

Author(s)
Yujian Tang

Language
English

Word count
1490

Hacker News points
3

This article discusses vector similarity search metrics and how they work. It covers three primary distance metrics: L2 or Euclidean distance, cosine similarity, and inner product. Additionally, it mentions other interesting vector similarity or distance metrics such as Hamming Distance and Jaccard Index. The article explains the concept of vectors in terms of orientation and magnitude, and how these metrics can be used to compare any data that can be vectorized. It also provides examples of when each metric should be used.

Date published
Dec. 7, 2023

Author(s)
Fendy Feng

Language
English

Word count
588

Hacker News points
None found.

In order to stay competitive in the e-commerce industry, Shopee ventured into short video services. However, they faced challenges handling vast amounts of unstructured data such as videos, images, audio, and text. Milvus emerged as a solution due to its ability to handle billions of vectors, scalability, and seamless integration with Shopee's internal ecosystem. The migration from Milvus 1.x to 2.x improved stability, scalability, and multi-replica capabilities, resulting in low-latency and high-availability retrieval services. With Milvus, Shopee has elevated its real-time search capabilities and streamlined offline data retrieval for copyright video matching and video deduplication processes.

Date published
Dec. 6, 2023

Author(s)
Steffi Li

Language
English

Word count
983

Hacker News points
2

Zilliz has introduced its new service, Zilliz Cloud Pipelines, which simplifies the process of creating and retrieving unstructured data as vectors. This solution is designed to empower developers in building high-quality semantic searches without requiring extensive customization or infrastructure adjustments. The platform consists of three specific pipelines: Ingestion, Search, and Deletion. Zilliz Cloud Pipelines currently focuses on semantic search in text documents but will be expanded to include image search, video copy detection, and multi-modal search capabilities in the future.

Date published
Dec. 4, 2023

Author(s)
Gourav Bais

Language
English

Word count
1594

Hacker News points
None found.

This article explains how to build a movie recommender system using the open source vector database, Milvus. The process involves setting up the environment, collecting and preprocessing data, connecting to Milvus, generating embeddings for movies, sending embeddings to Milvus, and finally recommending new movies using Milvus. By leveraging vector storage and similarity search, Milvus can help build an efficient and scalable movie recommendation system, enhancing user engagement and showcasing the role of advanced vector-based models in modern recommendation systems.

Date published
Nov. 29, 2023

Author(s)
Christy Bergman

Language
English

Word count
2068

Hacker News points
None found.

This blog post demonstrates how to build an open source chatbot using LangChain and Milvus in under 5 minutes. The process involves creating a retrieval augmented generation (RAG) stack with LangChain, which allows for answering questions about custom data while reducing hallucinations. The text is grounded on factual, custom data such as product documentation to ensure accuracy. The source code for the live chatbot is available on GitHub. The blog post also explains how to use Milvus, a high-performance vector database optimized for fast storage, indexing, and searching of embeddings or vectors. OpenAI's language models like GPT series are used in this process. Overall, the RAG retrieval and question-answering chatbot on custom documents is shown to be efficient and cost-effective as it allows free calls to data almost all the time for retrieval, evaluation, and development iterations, with only a paid call to OpenAI once for the final chat generation step.

Date published
Nov. 29, 2023

Author(s)
Fendy Feng

Language
English

Word count
609

Hacker News points
None found.

SmartNews, a leading news app, faced the challenge of optimizing ad recommendations for its highly engaged user base. The company turned to Milvus after researching solutions that could handle high-throughput and low-latency queries. Milvus's vector similarity search capabilities were instrumental in optimizing SmartNews's dynamic ad vector recall. Adopting Milvus led to more relevant ads, increasing click-through rates and driving up ad revenue. The company has upgraded its Milvus to 2.2.4 and is looking forward to leveraging new features for building even more real-time and reliable systems.

Date published
Nov. 27, 2023

Author(s)
Yujian Tang

Language
English

Word count
558

Hacker News points
3

The Open Source Advent is a project that aims to introduce participants to open-source software. For 25 days in December, one open-source project will be featured on social media along with a tutorial for quick start-up. Participants can earn points by starring the project's GitHub repo, creating repos using the project, and making posts tagging the company page. Extra points are awarded for writing a PR that gets merged or writing a blog about their experience. The top three scorers will receive swag packs from Zilliz and partners, as well as shoutouts on social media. Participants can join the Open Source Advent Discord Channel to submit their entries between December 26th, 2023, and January 2nd, 2024. Winners will be announced on January 8th, 2024.

Date published
Nov. 24, 2023

Author(s)
Christy Bergman

Language
English

Word count
595

Hacker News points
None found.

Milvus is an open-source vector database designed for building AI applications using unstructured data embeddings. It provides four SDKs, including Java, Python, React, and Ruby. The text outlines the steps to install and start a Milvus server, connect to it, create a collection with schema and index, insert data into the collection, and query the collection. Additionally, it mentions using LangChain and Milvus for building chatbots in an upcoming blog post. Resources are provided to get started with Milvus and Zilliz.

Date published
Nov. 22, 2023

Author(s)
Anya Sage

Language
English

Word count
1020

Hacker News points
None found.

Credal, an enterprise AI platform, aims to make Generative AI integration safer and more accessible for businesses. Their solution focuses on seamlessly integrating data from various sources while ensuring privacy and security. At the core of their offering is Milvus, an open-source vector database that enables efficient search, filtering, and data curation capabilities. Credal's architecture prioritizes high-quality data interpretations and effective communication with GenAI models. The platform offers observability and governance tools for administrators and IT teams, including features like PII redaction, audit logging, and data access controls. Milvus's scalability and robustness make it a game-changer for Credal, enabling them to deliver "Useful AI, made safe" to businesses worldwide.

Date published
Nov. 21, 2023

Author(s)
Steffi Li

Language
English

Word count
278

Hacker News points
None found.

Zilliz Cloud is now available on Microsoft Azure, expanding its presence across major cloud platforms including AWS and Google Cloud. This integration allows Azure-centric developers and enterprises to leverage the unique capabilities of Zilliz Cloud for vector database workloads. The move also signifies seamless access to Azure's cutting-edge AI services such as Semantic Kernel. Future enhancements include expansion into new Azure regions, availability on the Azure Marketplace, and continuous integration efforts to ensure data security and optimize application performance.

Date published
Nov. 21, 2023

Author(s)
Steffi Li

Language
English

Word count
460

Hacker News points
None found.

Zilliz Cloud has released the beta version of Milvus 2.3, introducing new features to enhance data management and querying processes for developers. The update includes Cosine similarity integration, Range Search feature, Upsert functionality, raw vector returns, JSON_CONTAINS filter, entity count, and more. Additionally, Zilliz Cloud has introduced enhanced enterprise features such as improved Role-Based Access Control (RBAC), expanded geographical options with the general availability of AWS EU Frankfurt region, and Self-Service Account and Organization Deletion feature. Furthermore, Zilliz Cloud is now available on Microsoft Azure in the azure-east-us region, completing its availability across major cloud platforms including AWS and Google Cloud. The company invites feedback from developers to shape the future of their vector database technology.

Date published
Nov. 20, 2023

Author(s)
Steffi Li

Language
English

Word count
1348

Hacker News points
None found.

Zilliz has introduced Upsert, Kafka Connector, and Airbyte integration to enhance data flow efficiency in its vector database. Upsert simplifies the update process by inserting or updating data based on atomicity. The Kafka Connector enables real-time streaming of vector data from Confluent/Kafka into Milvus or Zilliz vector databases, enhancing capabilities for Generative AI and e-commerce recommendations. Airbyte Integration streamlines data transfer and processing in LLMs and vector databases, improving search functionality. These enhancements aim to improve search performance and streamline the entire data pipeline, making it more efficient and developer-friendly.

Date published
Nov. 20, 2023

Author(s)
Steffi Li

Language
English

Word count
544

Hacker News points
None found.

Milvus, the vector database system, has released versions 2.3.2 and 2.3.3 with significant improvements aimed at enhancing performance and user experience. The latest updates include support for array data types, complex delete expressions, integration of TiKV for metadata storage, FP16 vector type, and vector index MMAP. Other enhancements include a rolling upgrade experience, performance optimization, upgraded CDC (Change Data Capture), bulk insert of binlog data with partition keys, and the return of binary metric types such as SUBSTRUCTURE and SUPERSTRUCTURE. The developer community's contributions have been instrumental in shaping these updates, and feedback is welcome for future enhancements.

Date published
Nov. 16, 2023

Author(s)
Yujian Tang

Language
English

Word count
890

Hacker News points
None found.

LangChain, an open-source library for LLM orchestration, recently added the "Self Query" retriever. This feature allows users to query vector databases like Milvus using LangChain. The implementation of this self-query retriever is covered in lines 189 to 233 of the base.py file in the self-query folder. The only class method for the self-query base class is from_llm, which has eight specified parameters and one allowing keyword arguments (kwargs). Four required parameters are llm, vectorstore, document_contents, and metadata_field_info. Other optional parameters include structured_query_translator, chain_kwargs, enable_limit, and use_original_query. The self-query retriever implementation involves parsing the self-query parameters, creating an LLM chain, and returning a self-query retriever. This feature enables users to build simple retrieval augmented generation (RAG) applications using an LLM, vector database, and prompts to interface with the LLM.

Date published
Nov. 15, 2023

Author(s)
Emily Kurze

Language
English

Word count
400

Hacker News points
None found.

AWS re:Invent, one of the largest global cloud computing events, will take place in Las Vegas from November 27 to December 1, 2023. Zilliz invites attendees to visit their booth (#1339) and meet the team behind Milvus, a vector database solution. The event offers opportunities for innovative solution demos, problem-solving expertise, collaboration, community engagement, and swag. Attendees can also book private demos or meetings with Zilliz's experts to discuss specific projects or use cases. Additionally, users are invited to join the team for dinner to share project updates and feedback. Resources on vector databases are recommended for those interested in learning more before the event.

Date published
Nov. 15, 2023

Author(s)
Yujian Tang

Language
English

Word count
940

Hacker News points
None found.

In this tutorial, we learn how to ground our Retriever- Augmenter-Generator (RAG) results using LlamaIndex and citations. We start by setting up the necessary libraries and environment variables for our chatbot. Next, we define the parameters of our RAG chatbot, including the embedding model, vector database, and data abstractions. Finally, we implement citations via LlamaIndex's CitationQueryEngine module to ensure grounded results. This tutorial uses Zilliz Cloud as a fully managed and optimized version of Milvus for persisting data across multiple projects.

Date published
Nov. 13, 2023

Author(s)
Jael Gu

Language
English

Word count
1281

Hacker News points
None found.

OpenAI's built-in Retrieval feature in its Assistants API has some limitations, such as scalability constraints and lack of customization. These issues can be addressed by integrating a custom retriever powered by a vector database like Milvus or Zilliz Cloud. This approach allows developers to optimize and configure the retrieval process according to their specific needs, improving overall efficiency.

Date published
Nov. 9, 2023

Author(s)
Leon Cai

Language
English

Word count
1198

Hacker News points
None found.

Milvus, an open-source vector database, has introduced a new feature called Range Search to enhance its similarity search capabilities. This feature allows developers to specify a distance range for relevant vectors in their searches, addressing limitations of traditional KNN searches in recommendation systems where results can be either too similar or too diverse. The technical architecture and usage guide for Range Search are outlined, along with details on when to use it over Top-K search. The feature is not limited to recommendation engines but has broader applications in areas like content matching, anomaly detection, and NLP search tasks. It is now available for public preview on Zilliz Cloud.

Date published
Nov. 8, 2023

Author(s)
Yujian Tang

Language
English

Word count
203

Hacker News points
None found.

HackNC 2021, an annual hackathon event hosted by the University of North Carolina at Chapel Hill, saw over 1,300 registrations and 650 participating hackers. Zilliz, a data observability company, was represented during the event with a workshop and keynote speech. The winning project, "wellSpent," is an expense tracking app that provides users with a dynamic pie chart of their expenses, transaction lists, and various financial planning tools. Congratulations to the team behind wellSpent for their victory in the Best Use of Zilliz category.

Date published
Nov. 3, 2023

Author(s)
Christy Bergman

Language
English

Word count
1137

Hacker News points
None found.

CalHacks, a hackathon event held in San Francisco from October 27-29, featured over 1000 students from around the world participating in various projects. With $137,650 in prize money and sponsor awards, several innovative projects were awarded for their use of Milvus, an open-source vector database. The winning project, Second Search, utilized Milvus to search lecture videos by embedding video caption text into vectors and returning relevant sections based on user queries. Other notable projects included Jarvis, which described visual scenes to visually impaired users, an AI 911 agent that assessed emergency situations, and Mental Maps, a chatbot for mental well-being tracking.

Date published
Nov. 3, 2023

Author(s)
Fendy Feng

Language
English

Word count
966

Hacker News points
None found.

Confluent, a data streaming platform, has announced the availability of its Kafka Connector for open-source Milvus and Zilliz Cloud. This collaboration enables seamless real-time vector data streaming from Confluent to Milvus or Zilliz vector databases, significantly enhancing real-time Generative AI powered by large language models (LLMs) like OpenAI's GPT-4. The integration of Zilliz and Confluent allows for continuous flow of real-time Confluent vector streams converted from unstructured data to be ported to Milvus/Zilliz, empowering developers to build applications for various use cases such as real-time semantic search, image/video/audio similarity search and retrieval augmented generation. The integration opens up possibilities for various sectors and applications, including enhancing Generative AI with a real-time knowledge base and optimizing personalized recommendations for e-commerce platforms.

Date published
Nov. 2, 2023

Author(s)
Alexandr Guzhva

Language
English

Word count
404

Hacker News points
None found.

Alexandr Guzhva, an expert in performance optimization, joined Zilliz to outcompete its competitors and fully utilize his expertise. With over 15 years of experience in finance and two years at Meta, he has contributed significantly to the FAISS library and written more than 2 million lines of code. Zilliz's focus on advanced similarity search methods and integration with NVIDIA Raft attracted him to the company. His goal is to improve Zilliz products and contribute to Milvus OSS, potentially applying his knowledge of ANNS for time series prediction in the future.

Date published
Nov. 1, 2023

Author(s)
Anya Sage

Language
English

Word count
722

Hacker News points
None found.

Troop, a tech company revolutionizing shareholder activism and engagement, leverages machine learning and AI technologies to enable investors to participate in corporate governance. Using the Milvus vector database, Troop built a solution that empowers individuals for collective financial activism in major corporations. The integration of Milvus enabled scalability, efficient handling of massive datasets, separation of storage and compute, rapid scaling of nodes, data partitioning, and improved semantic search capabilities. This infrastructure supports retrieval augmented generation (RAG) to process large volumes of unstructured data and build intelligent shareholder voting recommendation engines.

Date published
Oct. 31, 2023

Author(s)
Josh Reini

Language
English

Word count
2154

Hacker News points
None found.

This article discusses the use of vector search technologies, such as Milvus and Zilliz Cloud, in building retrieval augmented generation (RAG) applications. RAGs are question-answering applications that allow large language models (LLMs) to access a verified knowledge base for context. The article highlights various configuration choices that can affect the quality of retrieval, including data selection, embedding model, index type, amount of context retrieved, and chunk size. It also introduces TruLens, an open-source library for evaluating and tracking the performance of LLM applications like RAGs. By using TruLens to evaluate different configurations and parameters, developers can identify failure modes and find the most performant combination for their specific use case.

Date published
Oct. 30, 2023

Author(s)
Yujian Tang

Language
English

Word count
1042

Hacker News points
None found.

This tutorial demonstrates how to build a retrieval augmented generation (RAG) type app using LangChain and Milvus. The process involves reviewing LangChain self-querying, working with Notion docs in LangChain, ingesting Notion documents, storing them in a vector database, and querying the documents. The tutorial uses LangChain for operational framework and Milvus as the similarity engine. It covers how to load and parse a Notion document into sections to query in a basic RAG architecture, with future tutorials exploring different chunking strategies, embeddings, splitting strategies, and evaluation methods.

Date published
Oct. 27, 2023

Author(s)
David Wang

Language
English

Word count
872

Hacker News points
None found.

Large Language Models (LLMs) are driving innovation in AI, with LLM-driven Agents at the forefront. These agents combine LLMs with planning, memory, and tool modules to make decisions and take actions autonomously. The AutoGPT project demonstrates their potential by generating tasks, prioritizing them, and executing them using external resources. However, challenges such as getting stuck in loops and prompt length constraints need to be addressed. Ongoing research is focused on improving LLMs' reasoning abilities, enhancing agent frameworks, and developing specialized agent applications for various scenarios.

Date published
Oct. 24, 2023

Author(s)
Yujian Tang

Language
English

Word count
1499

Hacker News points
None found.

This tutorial explores the impact of different chunking strategies on retrieval augmented generation applications using LangChain. Chunking is the process of dividing text into smaller parts, and the choice of strategy can significantly affect the output quality. The code for this post can be found in a GitHub repo on LLM experimentation. The tutorial covers setting up the environment, importing necessary tools, and creating a function that takes parameters for document ingestion and chunking experimentation. It then tests five different chunking strategies with varying lengths and overlaps. The results show that finding an ideal chunking size is challenging and depends on the desired output format. Future tutorials may cover testing overlaps and using other libraries to refine chunking strategies further.

Date published
Oct. 16, 2023

Author(s)
Jiang Chen

Language
English

Word count
835

Hacker News points
None found.

Over the past decade, the author has specialized in various aspects of data infrastructure, including access control, data privacy, NoSQL databases, and web-scale data indexing. In recent years, big data emerged as a significant innovation with technologies like MapReduce, distributed computing, and structured data storage leading the way. However, the AI era requires different technology stacks, especially with the growing popularity of Large Language Models. Embedding and vector stores are at the center of this stage, which is also the focus of Zilliz. The author's experience includes working on search indexing at Google, where they built ultra-flexible infrastructures to understand billions of images and videos on the public web. They believe that AI-native infrastructure holds the key to the future of business and are enthusiastic about democratizing this highly complex infrastructure for resource-limited startups. The author joined Zilliz due to its ambitious mission, exceptional team, and challenging work environment. At Zilliz, they build a suite of tooling and services that ease the information retrieval process on unstructured data, including Towhee, Akcio, and a vector database for efficient storage and search of vector embeddings.

Date published
Oct. 13, 2023

Author(s)
Yang Cen

Language
English

Word count
661

Hacker News points
None found.

Milvus introduces the MMap feature, which redefines how large data volumes are managed and promises cost efficiency without compromising functionality. MMap is a memory-mapped file technology that allows Milvus to map large files directly into system memory space, transforming them into contiguous memory blocks. This integration eliminates the need for explicit read or write operations, fundamentally changing how Milvus manages data. The feature benefits vector databases by enabling more efficient storage and access to large files or situations where users need to access files randomly. However, it may cause performance fluctuations as data volume grows. Enabling MMap in Milvus is straightforward, requiring a modification of the milvus.yaml file. Future updates will refine memory usage and provide more granular control over the feature.

Date published
Oct. 13, 2023

Author(s)
Steffi Li

Language
English

Word count
1239

Hacker News points
None found.

This blog compares two vector databases, Qdrant and Zilliz/Milvus. While both are purpose-built for vector data, they serve different market needs. Qdrant is designed for developers who prioritize modern technology and minimal infrastructure maintenance, while Zilliz/Milvus is engineered for extreme scale, high performance, and low latency. The benchmark results show that Zilliz Cloud outperforms Qdrant Cloud in terms of queries per second (QPS), queries per dollar (QP$), and latency. Furthermore, the feature comparison highlights differences in scalability, functionality, and purpose-built features between the two vector databases.

Date published
Oct. 12, 2023

Author(s)
Yujian Tang

Language
English

Word count
1338

Hacker News points
None found.

This tutorial demonstrates how to use LlamaIndex, an open-source data retrieval framework, to improve the performance of a chatbot built with Zilliz Cloud. The primary challenge addressed in this project is integrating an existing Milvus collection into LlamaIndex while handling differences in embedding vector dimensions and metadata field usage. By using LlamaIndex as a query engine, the chatbot's retrieval capabilities are significantly enhanced, providing more accurate and relevant responses to user queries.

Date published
Oct. 11, 2023

Author(s)
Zhen Ye

Language
English

Word count
1055

Hacker News points
None found.

Milvus, an open-source vector database, has introduced NATS messaging integration in its latest version 2.3. This feature enhances the handling of substantial data volumes and complex scenarios compared to its predecessor, RocksMQ. NATS is a distributed system connectivity technology implemented in Go that supports various communication modes like Request-Reply and Publish-Subscribe across systems. Milvus 2.3 offers a new control option, mq.type, which allows users to specify the type of MQ they want to use. To enable NATS, set mq.type=natsmq. The migration from RocksMQ to NATS is seamless and involves steps like stopping write operations, flushing data, modifying configurations, and verifying the migration through Milvus logs. Performance testing results show that NATS outperforms RocksMQ for larger data packets (> 64kb), offering much faster response times. In extensive testing with a 100 million vectors dataset, NATS showcased lower vector search and query latency compared to RocksMQ.

Date published
Oct. 10, 2023

Author(s)
Joe Reuter

Language
English

Word count
1909

Hacker News points
None found.

Milvus is an open-source vector database used to store, index, and efficiently search high-dimensional vector data. It's particularly useful in applications involving similarity searches across unstructured data, such as Generative Chat responses, product recommendations, and more. By using Airbyte, it's straightforward to transfer data from many different sources into Milvus, calculating vector embeddings of texts along the way. The power of embeddings is to be able to search for relevant pieces of information, even if similar concepts are phrased differently. This article demonstrates how to use Zilliz Cloud as a vector store, Airbyte to extract and load the data, OpenAI embedding API to calculate embeddings, and Streamlit to build a smart submission form showing relevant data.

Date published
Oct. 6, 2023

Author(s)
Christy Bergman

Language
English

Word count
1432

Hacker News points
None found.

Christy Bergman, a new Developer Advocate at Zilliz, shares her journey of discovering and choosing Milvus, the world's most popular open-source vector database. She explains how she explored various vector databases, including FAISS, Qdrant, Chroma, Weaviate, Pinecone, and finally settled on Milvus due to its user-friendly experience, speed in loading vectors and querying, and additional features. Christy also discusses her role at Zilliz and her plans for organizing events, writing blogs, improving documentation, and helping developers learn how to use Milvus.

Date published
Oct. 4, 2023

Author(s)
Burcin Bozkaya

Language
English

Word count
3087

Hacker News points
None found.

This blog post discusses the integration of NVIDIA Merlin, an open-source framework developed for training end-to-end models to make recommendations at any scale, with Milvus, an efficient vector database created by Zilliz. The integration is beneficial in the item retrieval stage with a highly efficient top-k vector embedding search. The post also highlights how Milvus complements Merlin in recommender systems workflows and provides benchmark results showing impressive speedups with GPU-accelerated Milvus that uses NVIDIA RAFT with the vector embeddings generated by Merlin Models.

Date published
Oct. 3, 2023

Author(s)
Yujian Tang

Language
English

Word count
1846

Hacker News points
None found.

Vector embeddings are crucial when working with semantic similarity. They represent input data as a series of numbers, allowing mathematical operations to be performed on the data instead of relying on qualitative comparisons. The appropriate vector embeddings must be obtained before use, as using an image model for text or vice versa may result in poor results. Vector embeddings are influential for many tasks, particularly semantic search. Vector embeddings are created by removing the last layer and taking the output from the second-to-last layer of a deep learning model (embedding models or a deep neural network). The dimensionality of a vector embedding is equivalent to the size of the second-to-last layer in the model. Common vector dimensionalities include 384, 768, 1,536, and 2,048. A single dimension in a vector embedding does not mean anything; however, when all dimensions are taken together, they provide the semantic meaning of the input data. The dimensions represent high-level, abstract attributes that depend on the training data and the model itself. Different models generate different embeddings based on their training data and architecture. To obtain proper vector embeddings, identify the type of data you wish to embed (images, text, audio, videos, or multimodal data) and use appropriate open-source embedding models from Hugging Face or PyTorch. For example, ResNet-50 is a popular image recognition model, while MiniLM-L6-v2 and MPNet-Base-V2 are text embedding models. Vector databases like Milvus and Zilliz Cloud are used to store, index, and search across massive datasets of unstructured data through vector embeddings. They employ the Approximate Nearest Neighbor (ANN) algorithm to calculate spatial distances between query vectors and stored vectors in the database.

Date published
Oct. 2, 2023

Author(s)
Wenhui Zhang

Language
English

Word count
1741

Hacker News points
None found.

Milvus is an open-source vector database designed for similarity search, offering robust storage, processing, and retrieval capabilities for billions of vector data with minimal latency. As of September 2023, it has garnered almost 23,000 stars on GitHub and is used by tens of thousands of users across various industries. The latest release introduces new features such as GPU support and MMap storage for increased performance and capacity. To facilitate the migration process from older versions of Milvus (1.x), FAISS, and Elasticsearch 7.0 and beyond to the latest Milvus 2.x versions, a data migration tool called Milvus Migration has been developed. This powerful tool is written in Go and supports multiple interaction modes, including command-line interface (CLI) using the Cobra framework, Restful API with built-in Swagger UI, and integration as a Go module in other tools. Milvus Migration simplifies the migration process through its robust feature set, which includes support for various data sources such as Milvus 1.x to Milvus 2.x, Elasticsearch 7.0 and beyond to Milvus 2.x, and FAISS to Milvus 2.x. It also supports multiple file formats like local files, Amazon S3, Object Storage Service (OSS), Google Cloud Platform (GCP), and flexible Elasticsearch integration for migrating dense_vector type vectors from Elasticsearch as well as other field types such as long, integer, short, boolean, keyword, text, and double. The migration process involves configuring a migration.yaml file with details about the data source, target, and other relevant settings. Users can then execute the migration job using either command-line or Restful API methods. Once completed, users can view the total number of successful rows migrated and perform other collection-related operations using Attu, an all-in-one vector database administration tool. Future plans for Milvus Migration include supporting migration from more data sources like Redis and MongoDB, adding resumable migration capabilities, simplifying migration commands by merging the dump and load processes into one, and expanding support to other mainstream data sources.

Date published
Sept. 29, 2023

Author(s)
Jaken Ma

Language
English

Word count
803

Hacker News points
None found.

Milvus 2.3 introduces GPU support, unlocking a 10x increase in throughput and significant reductions in latency. This strategic innovation is aimed at enhancing vector searching capabilities, particularly with the rise of Large Language Models (LLMs) like GPT-3. The integration of Milvus and NVIDIA GPUs allows for efficient searching through massive datasets and expands the AI landscape. To get started with the Milvus GPU version, users need to install CUDA drivers, configure Milvus GPU settings, build Milvus locally, and run it in standalone mode or using a provided docker-compose file.

Date published
Sept. 28, 2023

Author(s)
Yujian Tang

Language
English

Word count
1206

Hacker News points
None found.

LangChain, known for orchestrating interactions with large language models (LLMs), has introduced self-querying capabilities. This tutorial demonstrates how to perform self-querying on Milvus, the world's most popular vector database. The process involves setting up LangChain and Milvus, obtaining necessary data, informing the model about expected data format, and finally, performing self-querying. Self-querying allows an LLM to query itself using the underlying vector store, creating a simple retrieval augmented generation (RAG) app in the CVP framework.

Date published
Sept. 27, 2023

Author(s)
Yujian Tang

Language
English

Word count
1119

Hacker News points
None found.

Unstructured data, which makes up 80% of global data, is becoming increasingly prevalent. Vector embeddings are numerical representations used to work with unstructured data such as text, images, audio, and videos. They can be extracted from trained machine-learning models and have high dimensionality to store complex data. Vector embeddings are the de facto way to work with unstructured data, allowing for comparisons between data points. When generating embedding vectors, factors like vector size, training data quality, and quantity should be considered. Vector embeddings can be used to debug training data by detecting errors through clustering, finding samples not present in the training data, identifying hallucinations, and fixing errors in retrieval augmented generation (RAG). Additionally, they can be indexed, stored, and queried using vector databases like Milvus or Zilliz Cloud. The power of vector embeddings is evident from their wide range of use cases, making them a valuable tool for working with unstructured data in machine learning applications.

Date published
Sept. 26, 2023

Author(s)
Steffi Li

Language
English

Word count
976

Hacker News points
None found.

Zilliz Cloud has integrated with Confluent Cloud, allowing users of both platforms to access real-time data streams across their entire business for building AI applications. The integration enables the ingestion, parsing, and processing of real-time data into Zilliz Cloud using Confluent's Kafka producer and consumer APIs. This collaboration opens new avenues for leveraging Generative Artificial Intelligence (GenAI) in real-time scenarios, such as personalized responses and content generation platforms. The integration also enhances traditional AI use cases like recommender systems and anomaly detection. With easy access to data streams from across their entire business, Zilliz users can now create a real-time knowledge base, build governed, secured, and trusted AI applications, and experiment, scale, and innovate faster.

Date published
Sept. 25, 2023

Author(s)
Patrick Xu

Language
English

Word count
803

Hacker News points
None found.

Milvus 2.3 has been released with significant updates, including the transformative upgrade of Knowhere 2.0. Key features of Knowhere 2.0 include support for GPU indexes, Cosine similarity, ScaNN index, ARM architecture, range search, optimized filter queries, code structure and compilation enhancements, MMap support, and retrieval of original vectors. These improvements aim to elevate Milvus's performance and user experience in vector databases.

Date published
Sept. 21, 2023

Author(s)
Steffi Li

Language
English

Word count
1234

Hacker News points
None found.

This blog compares two vector databases, Weaviate and Zilliz/Milvus. While both are designed to manage vector data, they serve different needs. Weaviate is a strong choice for developers seeking quick and straightforward implementation, while Zilliz/Milvus excels in handling large-scale, high-performance, low-latency applications. The benchmark results show that Zilliz Cloud outperforms Weaviate Cloud in terms of queries per second (QPS), queries per dollar (QP$), and latency. Furthermore, a feature comparison reveals differences in scalability, functionality, and purpose-built features between the two vector databases.

Date published
Sept. 20, 2023

Author(s)
Yujian Tang

Language
English

Word count
2347

Hacker News points
1

In the first part of the Chat Towards Data Science blog series, we guide you through building a chatbot using your dataset as the knowledge backbone. We employ web scraping techniques to collect data for our knowledge base and store it in Zilliz Cloud, a fully managed vector database service built on Milvus. The tutorial covers creating a chatbot for the Towards Data Science publication, demonstrating how to prompt the user for a query, vectorize the query, and query the vector database. However, we discovered that while the results are semantically similar, they are not exactly what we desire. In the next part of this blog series, we will explore using LlamaIndex to route queries and see if we can achieve better results.

Date published
Sept. 15, 2023

Author(s)
Siddhant Varma

Language
English

Word count
2072

Hacker News points
None found.

This guide explores the use of Pgvector, an extension of PostgreSQL that allows developers to store and query vector data. It covers setting up Pgvector, integrating it with PostgreSQL, using it for similarity searches, understanding its indexes and limitations, and comparing it with dedicated vector databases like Milvus and Zilliz. The article also discusses the advantages of using dedicated vector databases over traditional relational databases and provides benchmarking results to help developers choose the best solution for their projects.

Date published
Sept. 13, 2023

Author(s)
Towhee team

Language
English

Word count
2113

Hacker News points
2

Meta AI has released its open-source large language model (LLM), Llama 2, which is available for free use in commercial applications. It comes in three sizes and supports context lengths of up to 4096 tokens. Llama Chat, the fine-tuned model of Llama 2, has been trained on over 1 million human annotations and is specifically tailored for conversational AI scenarios. The performance of Llama 2 in answering questions was compared with that of ChatGPT, showing that both models excel at answering questions based on real-world knowledge. However, Llama 2 faces challenges maintaining answer quality when confronted with complex text formatting. Llama 2 stands out by not requiring high-end GPUs and can operate smoothly on desktop-level GPUs, especially after undergoing low-bit quantization.

Date published
Sept. 10, 2023

Author(s)
Owen jiao

Language
English

Word count
688

Hacker News points
None found.

Milvus 2.3, the latest version of the pioneering vector database, offers numerous enhancements and new features that make it an excellent choice for users looking to build applications ranging from recommendation systems and chatbots to artificial general intelligence (AGI) and retrieval augmented generation (RAG). The updated version balances performance, cost, and scalability while providing multiple deployment options. It also empowers developers with simplicity by enhancing its API and supporting data integration with other products. Furthermore, Milvus 2.3 ensures stability and second-level availability through improved system reliability features. Future updates will introduce additional cutting-edge features to enhance the user experience further.

Date published
Sept. 5, 2023

Author(s)
Chris Churilo

Language
English

Word count
1221

Hacker News points
None found.

This blog compares Elastic Cloud and Zilliz Cloud, two vector database cloud services. It delves into benchmarks to offer a performance perspective and performs an in-depth feature analysis of both platforms. The results show that Zilliz outperforms Elastic Cloud in terms of QPS, queries per dollar (QP$), and latency. Additionally, the blog highlights the features of each platform, such as scalability, multi-tenancy, data isolation, API support, and user interface/administrative console. It also provides a migration tutorial for moving from Elasticsearch to Zilliz Cloud.

Date published
Aug. 30, 2023

Author(s)
Steffi Li

Language
English

Word count
364

Hacker News points
None found.

Milvus 2.3.0 has been released, featuring numerous enhancements and improvements. Key features include computational upgrades with GPU & ARM64 support, search & indexing enhancements such as range search and ScaNN index integration, data pipeline tools like iterator in Pymilvus and upsert operation, and system optimizations for better operability, load balancing, and query performance. The release also includes bug fixes and updates to existing tools like Birdwatcher and Attu. Developers are encouraged to integrate these updates and provide feedback.

Date published
Aug. 28, 2023

Author(s)
Fendy Feng

Language
English

Word count
1461

Hacker News points
None found.

The article discusses the challenges faced by developers while building applications based on large language models (LLMs) such as high costs of API calls and poor performance due to response latency. It introduces GPTCache, an open-source semantic cache designed to improve efficiency and speed of GPT-based applications. GPTCache stores LLM responses in the cache, allowing users to retrieve previously requested answers without calling the LLM again. The article explains how GPTCache works, its benefits including drastic cost reduction, faster response times, improved scalability, and better availability. It also provides an example of OSS Chat, an AI chatbot that utilizes GPTCache and the CVP stack for more accurate results.

Date published
Aug. 21, 2023

Author(s)
Yujian Tang

Language
English

Word count
2436

Hacker News points
None found.

This article discusses the differences between vector embeddings generated by different neural networks and how to evaluate them in Jupyter Notebook. Vector embeddings are numerical representations of unstructured data, such as images, videos, audio, text, and molecular images. They are generated by running input data through a pre-trained neural network and taking the output of the second-to-last layer. The article provides an example of comparing vector embeddings from three different multilingual models based on MiniLM from Hugging Face using L2 distance metric and an inverted file index as the vector index. It also demonstrates how to compare vector embeddings directly in a Jupyter Notebook with Milvus Lite, a lightweight version of Milvus.

Date published
Aug. 18, 2023

Author(s)
Eric Goebelbecker

Language
English

Word count
2364

Hacker News points
None found.

In this tutorial, we will create an intelligent chatbot using Milvus and Towhee. We will use the following components to build our chatbot: 1. Milvus: An open-source vector database for efficient similarity search and AI applications. 2. Towhee: A Python library that provides a set of pre-built machine learning models and tools for processing unstructured data. 3. OpenAI API: A service that allows developers to access powerful language generation models like GPT-3.5. 4. Gradio: An open-source Python library for creating interactive demos of machine learning models. First, we need to install the required packages: ```bash pip install milvus pymilvus towhee gradio ``` Next, let's define some variables and answer the prompt for the API key. Run this code to do so: ```python import os import getpass MILVUS_URI = 'http://localhost:19530' [MILVUS_HOST, MILVUS_PORT] = MILVUS_URI.split('://')[1].split(':') DROP_EXIST = True EMBED_MODEL = 'all-mpnet-base-v2' COLLECTION_NAME = 'chatbot_demo' DIM = 768 OPENAI_API_KEY = getpass.getpass('Enter your OpenAI API key: ') if os.path.exists('./sqlite.db'): os.remove('./sqlite.db') ``` Sample pipeline Now, let's download some data and store it in Milvus. But before you do that, let's look at a sample pipeline for downloading and processing unstructured data. You'll use the Towhee documentation pages for this example. You can try different sites to see how the code processes different data sets. This code uses Towhee pipelines: - input - begins a new pipeline with the source passed into it - map - uses ops.text_loader() to retrieve the URL and map it to 'doc' - flat_map - uses ops.text_splitter() to process the document into "chunks" for storage - output - closes and prepares the pipeline for use Pass this pipeline to DataCollection to see how it works: ```python from towhee import pipe, ops, DataCollection pipe_load = ( pipe.input('source') .map('source', 'doc', ops.text_loader()) .flat_map('doc', 'doc_chunks', ops.text_splitter(chunk_size=300)) .output('source', 'doc_chunks') ) DataCollection(pipe_load('https://towhee.io')).show() ``` Here's the output from show(): The pipeline created five chunks from the document. Sample embedding pipeline The pipeline retrieved the data and created chunks. You need to create embeddings, too. Let's take a look at another sample pipeline: This one uses map() to run ops.sentence_embedding.sbert() on each chunk. In this example, we're passing in a single block of text. ```python from towhee import pipe, ops, DataCollection pipe_embed = ( pipe.input('doc_chunk') .map('doc_chunk', 'vec', ops.sentence_embedding.sbert(model_name=EMBED_MODEL)) .map('vec', 'vec', ops.np_normalize()) .output('doc_chunk', 'vec') ) text = '''SOTA Models We provide 700+ pre-trained embedding models spanning 5 fields (CV, NLP, Multimodal, Audio, Medical), 15 tasks, and 140+ model architectures. These include BERT, CLIP, ViT, SwinTransformer, data2vec, etc. ''' DataCollection(pipe_embed(text)).show() ``` Run this code to see how the pipeline processes the single text block: Prepare Milvus Now, you need a collection to hold the data. This function defines create_collection(), which uses MILVUS_HOST and MILVUS_PORT to connect to Milvus, drop any existing collections with the specified name, and create a new one with this schema: - id - an integer identifier - embedding - a vector of floats for the embeddings - text - the corresponding text for the embeddings ```python from pymilvus import ( connections, utility, Collection, CollectionSchema, FieldSchema, DataType ) def create_collection(collection_name): connections.connect(host=MILVUS_HOST, port=MILVUS_PORT) has_collection = utility.has_collection(collection_name) if has_collection: collection = Collection(collection_name) if DROP_EXIST: collection.drop() else: return collection # Create collection fields = [ FieldSchema(name='id', dtype=DataType.INT64, is_primary=True, auto_id=True), FieldSchema(name='embedding', dtype=DataType.FLOAT_VECTOR, dim=DIM), FieldSchema(name='text', dtype=DataType.VARCHAR, max_length=500) ] schema = CollectionSchema( fields=fields, description="Towhee demo", enable_dynamic_field=True ) collection = Collection(name=collection_name, schema=schema) index_params = { 'metric_type': 'IP', 'index_type': 'IVF_FLAT', 'params': {'nlist': 1024} } collection.create_index( field_name='embedding', index_params=index_params ) return collection ``` Insert pipeline It's time to process your input text and insert it into Milvus. Let's start with a pipeline that collapses what you learned above: This function: - Creates the new collection - Retrieves the data - Splits it into chunks - Creates embeddings using EMBED_MODEL - Insert the text and embeddings into Milvus ```python from towhee import pipe, ops, DataCollection load_data = ( pipe.input('collection_name', 'source') .map('collection_name', 'collection', create_collection) .map('source', 'doc', ops.text_loader()) .flat_map('doc', 'doc_chunk', ops.text_splitter(chunk_size=300)) .map('doc_chunk', 'vec', ops.sentence_embedding.sbert(model_name=EMBED_MODEL)) .map('vec', 'vec', ops.np_normalize()) .map(('collection_name', 'vec', 'doc_chunk'), 'mr', ops.ann_insert.osschat_milvus(host=MILVUS_HOST, port=MILVUS_PORT)) .output('mr') ) ``` Here it is in action: ```python project_name = 'towhee_demo' data_source = 'https://en.wikipedia.org/wiki/Frodo_Baggins' mr = load_data(COLLECTION_NAME, data_source) print('Doc chunks inserted:', len(mr.to_list())) ``` The model does a good job of pulling three closely matched nodes: Search knowledge base Now, with the embeddings and text stored in Milvus, you can search it: This function creates a query pipeline. The most important step is this one: ops.ann_search.osschat_milvus(host=MILVUS_HOST, port=MILVUS_PORT, **{'metric_type': 'IP', 'limit': 3, 'output_fields': ['text']})) The osschat_milvus searches the embeddings for matches to the submitted text. Here is the whole pipeline: ```python from towhee import pipe, ops, DataCollection pipe_search = ( pipe.input('collection_name', 'query') .map('query', 'query_vec', ops.sentence_embedding.sbert(model_name=EMBED_MODEL)) .map('query_vec', 'query_vec', ops.np_normalize()) .map(('collection_name', 'query_vec'), 'search_res', ops.ann_search.osschat_milvus(host=MILVUS_HOST, port=MILVUS_PORT, **{'metric_type': 'IP', 'limit': 3, 'output_fields': ['text']})) .flat_map('search_res', ('id', 'score', 'text'), lambda x: (x[0], x[1], x[2])) .output('query', 'text', 'score') ) ``` Try it: ```python query = 'Who is Frodo Baggins?' DataCollection(pipe_search(project_name, query)).show() ``` The model does a good job of pulling three closely matched nodes: Add an LLM Now, it’s time to add a large language model (LLM) so users can hold a conversation with the chatbot. We’ll use ChatGPT and the OpenAI API for this example. Chat history In order to get better results from the LLM, you need to store chat history and present it with queries. You’ll use SQLite for this step: Here's a function for retrieving the history: ```python from towhee import pipe, ops, DataCollection pipe_get_history = ( pipe.input('collection_name', 'session') .map(('collection_name', 'session'), 'history', ops.chat_message_histories.sql(method='get')) .output('collection_name', 'session', 'history') ) ``` Here's the one to store it: ```python from towhee import pipe, ops, DataCollection pipe_add_history = ( pipe.input('collection_name', 'session', 'question', 'answer') .map(('collection_name', 'session', 'question', 'answer'), 'history', ops.chat_message_histories.sql(method='add')) .output('history') ) ``` LLM query pipeline Now, we need a pipeline to submit queries to ChatGPT: This pipeline: - searches Milvus using the user's query - collects the current chat history - submits the query, Milvus search, and chat history to ChatGPT - Appends the ChatGPT result to the chat history - Returns the result to the caller ```python from towhee import pipe, ops, DataCollection chat = ( pipe.input('collection_name', 'query', 'session') .map('query', 'query_vec', ops.sentence_embedding.sbert(model_name=EMBED_MODEL)) .map('query_vec', 'query_vec', ops.np_normalize()) .map(('collection_name', 'query_vec'), 'search_res', ops.ann_search.osschat_milvus(host=MILVUS_HOST, port=MILVUS_PORT, **{'metric_type': 'IP', 'limit': 3, 'output_fields': ['text']})) .map('search_res', 'knowledge', lambda y: [x[2] for x in y]) .map(('collection_name', 'session'), 'history', ops.chat_message_histories.sql(method='get')) .map(('query', 'knowledge', 'history'), 'messages', ops.prompt.question_answer()) .map('messages', 'answer', ops.LLM.OpenAI(api_key=OPENAI_API_KEY, model_name='gpt-3.5-turbo', temperature=0.8)) .map(('collection_name', 'session', 'query', 'answer'), 'new_history', ops.chat_message_histories.sql(method='add')) .output('query', 'history', 'answer') ) ``` Let's test this pipeline before connecting it to a GUI: ```python new_query = 'Where did Frodo take the ring?' DataCollection(chat(COLLECTION_NAME, new_query, session_id)).show() ``` The pipeline works. Let's put together a Gradio interface. Gradio GUI First, you need functions to create a session identifier and to respond to queries from the interface: These functions create a session ID using a UUID, and accept a session and query for the query pipeline: ```python import uuid import io def create_session_id(): uid = str(uuid.uuid4()) suid = ''.join(uid.split('-')) return 'sess_' + suid def respond(session, query): res = chat(COLLECTION_NAME, query, session).get_dict() answer = res['answer'] response = res['history'] response.append((query, answer)) return response ``` Next, the Gradio interface uses these functions to build a chatbot: It uses the Blocks API to create a ChatBot interface. The Send Message button uses the respond function to send requests to ChatGPT: ```python import gradio as gr with gr.Blocks() as demo: session_id = gr.State(create_session_id) with gr.Row(): with gr.Column(scale=2): gr.Markdown('''## Chat''') conversation = gr.Chatbot(label='conversation').style(height=300) question = gr.Textbox(label='question', value=None) send_btn = gr.Button('Send Message') send_btn.click( fn=respond, inputs=[ session_id, question ], outputs=conversation, ) demo.launch(server_name='127.0.0.1', server_port=8902) ``` Here it is: Now, you have an intelligent chatbot! Summary In this post, we created Towhee pipelines to ingest unstructured data, process it for embeddings, and store those embeddings in Milvus. Then, we created a query pipeline for the chat function and connected the chatbot with an LLM. Finally, we got an intelligent chatbot. This tutorial demonstrates how easy it is to build applications with Milvus. Milvus brings numerous advantages when integrated into applications, especially those relying on machine learning and artificial intelligence. It offers highly efficient, scalable, and reliable vector similarity search and analytics capabilities critical in applications like chatbots, recommendation systems, and image or text recognition.

Date published
Aug. 17, 2023

Author(s)
Steffi Li

Language
English

Word count
1272

Hacker News points
None found.

The release of GPT-3.5 and GPT-4 has revolutionized how users interact with data and applications, providing more natural and intuitive communication interfaces. However, implementing LLMs like ChatGPT in applications presents challenges such as lack of private data access, hallucination, outdated information, high costs, slow performance, and immutable pre-training data. Zilliz Cloud and GPTCache are innovative solutions that address these issues by improving accuracy, timeliness, cost-efficiency, and performance. The CVP Stack (ChatGPT/LLMs + a vector database + prompt-as-code) offers a robust framework for building LLM applications. OSS Chat is an example of a successful AI chatbot built with the CVP stack using Akcio and Zilliz Cloud. To learn more about these technologies, join the upcoming webinar on September 7.

Date published
Aug. 11, 2023

Author(s)
Yujian Tang

Language
English

Word count
2528

Hacker News points
1

In this tutorial, we extended our first celebrity-style project by using Milvus' new dynamic schema, filtering out certain segmentation IDs, and keeping track of the bounding boxes of our matches. We also sorted our search results to return the top three results based on the number of matches. Milvus' new dynamic schema allows us to add extra fields when we upload data using a dictionary format, changing the way we were initially batch-uploading a list of lists. It also facilitated adding crop coordinates without changing the schema. As a new preprocessing step, we filtered out certain IDs that aren't clothing-related based on the model card in Hugging Face. We filter these IDs out in the get_masks function. Fun fact, the obj_ids object in that function is actually a tensor. We also kept track of the bounding boxes. We moved the embedding step to the image cropping function and returned the embeddings with the bounding boxes and segmentation IDs. Then, we saved these embeddings into Milvus using a dynamic schema. At query time, we aggregated all the returned images by the number of bounding boxes they contained, allowing us to find the closest matching celebrity image via different articles of clothing. Now it's up to you. You can take my suggestions and make something else out of it, such as a fashion recommender system, a better style comparison system for you and your friends, or a generative fashion AI app.

Date published
Aug. 8, 2023

Author(s)
Yujian Tang

Language
English

Word count
2587

Hacker News points
None found.

The article discusses the use of AI in fashion, specifically focusing on a project called "Fashion AI" that utilizes a fine-tuned model to segment clothing in images. It explains how the project involves cropping out each labeled article and resizing the images to the same size before storing the embeddings generated from those images in Milvus, an open-source vector database. The article also provides detailed steps on how to generate image segmentation for fashion items, add your image data to Milvus, and find out which celebrity your dress is most like using this technology.

Date published
Aug. 7, 2023

Author(s)
Steffi Li

Language
English

Word count
338

Hacker News points
None found.

Zilliz Cloud has expanded its services to AWS and GCP Singapore regions, following the positive response from users since its launch in April 2023. This expansion aims to meet increasing demand and provide greater flexibility for customers by offering more deployment options. As a result, Zilliz Cloud is now the first fully managed vector database available on AWS in the APAC region. The company invites users to explore new possibilities with this expansion and offers free trials of its Starter Plan and Standard plan with up to $200 worth of credits.

Date published
Aug. 4, 2023

Author(s)
Yujian Tang

Language
English

Word count
1209

Hacker News points
2

This tutorial explains how to implement retrieval augmented generation (RAG) with citations using LlamaIndex and Milvus. RAG is a technique used in large language model (LLM) applications to supplement their knowledge, addressing the lack of up-to-date or domain-specific information. The process involves using a vector database like Milvus to inject knowledge into an app. Citations and attributions are crucial for determining trustworthy answers as more data is added. LlamaIndex and Milvus can be used together to create a citation query engine, allowing users to retrieve information with citations or attributions. The tutorial demonstrates this process using Python libraries and provides code examples for scraping data from Wikipedia, setting up the vector store in LlamaIndex, and querying the engine with citations.

Date published
Aug. 3, 2023

Author(s)
Fendy Feng

Language
English

Word count
1135

Hacker News points
None found.

The emergence of ChatGPT has signaled the start of a new era in artificial intelligence (AI), with vector databases becoming an essential infrastructure. Vector databases store and retrieve unstructured data such as images, audio, videos, and text through high dimensional values called embeddings. They are frequently used for similarity searches using the Approximate Nearest Neighbor (ANN) algorithm. Specialized vector databases like Milvus and Zilliz Cloud offer many user-friendly features and are a more optimal solution for unstructured data storage and retrieval compared to vector search libraries. Vector databases are becoming vital infrastructure for AI-related tech stacks, such as LLM augmentation, recommender systems, image/audio/video/text similarity searches, anomaly detection, question-answering systems, and molecular similarity searches. To choose the most suitable vector database for your project, VectorDBBench is an open-source benchmarking tool that evaluates various vector database systems regarding QPS, latency, capacity, and other metrics.

Date published
Aug. 1, 2023

Author(s)
James Luan

Language
English

Word count
1037

Hacker News points
None found.

Zilliz Cloud, a fully-managed vector database, aims to minimize users' costs for building AI applications. The latest release of Zilliz Cloud offers new features such as partition key, dynamic schema, and JSON support, making it more accessible and affordable for developers. By minimizing development, hardware, and maintenance costs, Zilliz Cloud enables traditional companies and startups to create innovative AI applications. Future updates will introduce unstructured data processing pipelines, support for complex aggregation functions, and global expansion of services.

Date published
July 28, 2023

Author(s)
Eric Goebelbecker

Language
English

Word count
1833

Hacker News points
None found.

Milvus is an open-source database designed for vector search, offering robust scalability for various loads. It's ideal for machine learning deployments and includes best-of-class tooling like the JavaScript client. In this tutorial, we'll guide you through setting up a development environment with Milvus Lite and the Milvus node.js SDK(Client). We'll cover connecting to a server, creating databases and collections, inserting data, performing queries and searches, and more. With these tools, working with vector data in JavaScript using Milvus becomes simple and efficient.

Date published
July 27, 2023

Author(s)
Fendy Feng

Language
English

Word count
1340

Hacker News points
None found.

Vector databases, crucial infrastructure for AI applications and large language models (LLMs), have gained widespread attention from a broader user base. Unlike traditional relational or NoSQL databases that store structured data, vector databases are purpose-built to store and manage unstructured data in numeric representations called embeddings. They enable similarity searches using the approximate nearest neighbor (ANN) algorithm, making them valuable for various use cases such as recommender systems, anomaly detection, and question-and-answer systems. The democratization of vector databases is essential to make progress in AI technology. However, only some developers have equal access due to barriers like proprietary technology, complex architecture and deployment, high costs, and poor user experience. To improve vector database democratization, it's crucial to evangelize knowledge, expertise, and technologies; open the source code to all developers; provide fully managed vector database services; offer free cloud options for individual developers and small teams; and prioritize a great user experience that meets users' needs. Choosing the right vector database for your project can be challenging due to the many available options. VectorDBBench, an open-source benchmarking tool, thoroughly evaluates and compares different vector database systems based on critical metrics such as queries per second (QPS), latency, throughput, and capacity.

Date published
July 26, 2023

Author(s)
Yujian Tang

Language
English

Word count
706

Hacker News points
None found.

Yujian Tang, a developer advocate at Zilliz, has an extensive background in computer science, statistics, and neuroscience. He previously worked as a software engineer at Amazon and researched machine learning. Tang chose to join Zilliz due to their focus on vector databases and the company's commitment to open-source ethos. As a developer advocate, he works with cutting-edge AI technologies and hosts meetups and conferences. He encourages others interested in DevRel roles to consider joining Zilliz.

Date published
July 25, 2023

Author(s)
Eric Goebelbecker

Language
English

Word count
1752

Hacker News points
None found.

Zilliz Cloud is a comprehensive vector database service that accelerates AI and analytics applications at scale. It's built on Milvus, an open-source vector database capable of handling billions of vector embeddings. The use cases for Milvus and Zilliz Cloud are broad and varied, including powering recommendation systems and building AI models in healthcare. The Zilliz REST API provides methods for managing clusters, collections, and vector data, allowing users to create, list, describe, drop, insert, delete, query, and search collections.

Date published
July 19, 2023

Author(s)
Li Liu

Language
English

Word count
978

Hacker News points
None found.

Zilliz recently launched an updated version of its cloud platform, introducing new features such as a free tier, dynamic schema and partition keys, and more affordable pricing plans. The latest update has significantly improved performance, making it twice as fast as the previous version and three to ten times faster than other vector databases like Milvus. Zilliz Cloud's speed is attributed to its robust vector indexing engine, optimized code structure, and AutoIndex feature for stable recall rates.

Date published
July 18, 2023

Author(s)
Frank Liu

Language
English

Word count
928

Hacker News points
None found.

The text discusses the importance of machine learning models and their corresponding embeddings, which are high-dimensional vectors that provide an abstract way to represent input data in the model. It explains how embeddings have been used in various applications such as image recognition and semantic search. The author shares their personal journey working with embeddings and vector search, highlighting their experiences at Yahoo and a startup they founded. They also discuss Zilliz's mission to build an affordable and scalable vector search solution for the enterprise AI infrastructure market. The text ends by inviting readers to join Zilliz in its efforts to democratize enterprise AI infrastructure.

Date published
July 14, 2023

Author(s)
Steffi Li

Language
English

Word count
291

Hacker News points
None found.

Milvus has released versions 2.2.10 and 2.2.11, which include enhancements to improve functionality and user experience. Updates have been made based on community feedback, with a focus on performance and security improvements. The latest versions introduce the 'FlushAll' function and Database API for RBAC capabilities, optimize disk usage for RocksMq by enabling zstd compression, and replace CGO payload writer with Go payload writer to reduce memory usage. Additionally, several bug fixes and performance enhancements have been made in these releases.

Date published
July 12, 2023

Author(s)
Yujian Tang