Embeddings DB recommendations I ve heard of pinecone chroma

Question

Embeddings DB recommendations I ve heard of pinecone chroma vectors directly in PG Does anyone have experience with these that can recommend one or another

Don Alvarez · Answer

Pinecone seems to be most people s default That said given the amount of resources Microsoft and Azure is throwing at AI and the centrality of Cosmos DB to Azure generally I m personally watching this announcement from about 2 weeks ago pretty closely <https devblogs microsoft com cosmosdb introducing vector search in azure cosmos db for mongodb vcore >

Vishwanath Seshagiri · Answer

If you don t mind managing your vector store I ve found weviate to be the best

Vishwanath Seshagiri · Answer

I would also recommend looking into pg vector and redis vector <https redis com solutions use cases vector database >

Han · Answer

just use redis

Han · Answer

depending on the size of your data if its only tens of million vectors just use chroma duckdb or cozo

Nicholas Charriere · Answer

< Han> for low size how would you compare redis and pg

Deepanshu · Answer

< Nicholas Charriere> have used qdrant in production its quite better on Ram footprint etc

Nicholas Charriere · Answer

Nice better than what Any comparison points

Deepanshu · Answer

Sure if you can share more about your use case and what is more important like performance speed recall precision etc can surely help direct you to those benchmarks etc

Deepanshu · Answer

If you want something local Qdrant and Weaviate have much better performance

Deepanshu · Answer

You can find more info here about difference benchmarks for choosing right Vector DB <https github com erikbern ann benchmarks>

Han · Answer

For small foot prints just use Chroma or Cozo They sit in memory dont need to do anything fancy And move to Redis if you need it in production so you can separate the scaling

Han · Answer

There s not much reason to use Pinecone Weaviate etc since that would require you to make a trip over the Internet PGVector has its use cases but its meh

Han · Answer

Also depending on use case you do need to sometimes worry about ingestion speed or upsert speed

Andrew Cote · Answer

contrarian take

Han · Answer

I dont see why that s contrarian numpy is usually the best choice if you just need something in memory then sqlite cozo or duckdb chroma

Han · Answer

Both embeddings layer and attention layers in the transformer model architecture are both doing vectorized retrieval