I use postgres and it has pgvector - why should I consider using Chroma, Pinecone, or any other dedicated vector db for my llm-based application that needs to store embeddings information?
You can do everything with PostGres:<p>Full-text search, but there are better engines for it: Elastic, Meilisearch, etc. right?<p>You can also store JSON into Postgres, but you should better use MongoDB for NoSQL purposes, right?<p>The reason for this is: dedicated tools are always better, faster, and more feature-rich.<p>The ANN index IVF implemented in pgvector has very poor performance, with only around 50% recall. Is it something you are looking for?<p>Disclaimer: I'm a co-founder at Qdrant, an open-source vector database written in Rust. <a href="https://github.com/qdrant/qdrant">https://github.com/qdrant/qdrant</a><p>PS: Chroma isn't a database but а Python wrapper around ClickHouse DB.