Chroma
The shortest distance from pip install to a working retriever — which is why nearly every RAG tutorial starts here.
Prototypes, notebooks, and single-node applications under a few million vectors
Read more →
Vector databases, hybrid search engines and embedding storage layers.
The shortest distance from pip install to a working retriever — which is why nearly every RAG tutorial starts here.
Rust vector database with payload filtering — strong when metadata matters as much as similarity.
Distributed vector database built for billion-scale — the choice once one node stops being enough.
Vector database with built-in embedding modules — less glue code in your ingestion path.
Vectors inside the Postgres you already run — the right answer until it is not.
Published benchmark tables compare recall on public datasets, which is not your dataset, your filters, or your query distribution. Four operational questions decide it instead.