Skip to content
mlx.app

Chroma

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

When to use it

Use this when you want a zero-ops embedded vector store to pair with mlx-embeddings, with no separate service to run.

Alternatives in Embeddings & RAG

MLX Embeddings

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

txtai

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

LlamaIndex

The data framework most local RAG tutorials are built on.