RedisAI, an AI serving engine for Redis, is now generally available and designed to run where data lives, decreasing latency and increasing simplicity in various use cases such as transaction scoring, fraud detection, and recommendation engines personalization. It provides optimal performance when serving models due to its architecture that stores machine learning native data types in the memory space of the Redis server. RedisAI supports several integrated backends, including TensorFlow, Pytorch, and ONNXRuntime, and offers features like auto-batching support and the DAG command for increased efficiency during serving. Benchmarks reveal that RedisAI increases speed by up to 81x compared to other model serving platforms when the overall end-to-end time is not dominated by the inference itself.