Skip to content
mlx.app

txtai

An all-in-one embeddings database, from before 'RAG' was a word.

When to use it

Use this when you want vector search, filtering and pipelines in one embedded database instead of a separate vector server.

Alternatives in Embeddings & RAG

MLX Embeddings

Embedding models on MLX, so retrieval doesn't need PyTorch.

LlamaIndex

The data framework most local RAG tutorials are built on.

Chroma

The vector database that got embedded into every local RAG demo first.