Embeddings DB recommendations? I've heard of pinec...
# 06-technical-discussionn
Nicholas Charriere
06/08/2023, 3:52 PMEmbeddings DB recommendations? I've heard of pinecone, chroma, vectors directly in PG. Does anyone have experience with these that can recommend one or another?
d
Don Alvarez
06/08/2023, 4:08 PMPinecone 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/
👀 2
v
Vishwanath Seshagiri
06/08/2023, 4:14 PMIf you don't mind managing your vector store, I've found weviate to be the best!
Vishwanath Seshagiri
06/08/2023, 4:15 PMI would also recommend looking into pg-vector and redis-vector (https://redis.com/solutions/use-cases/vector-database/)
🙏 1
h
Han
06/08/2023, 4:38 PMjust use redis
Han
06/08/2023, 4:38 PMdepending on the size of your data, if its only tens of million vectors, just use chroma/duckdb or cozo
👍 1
n
Nicholas Charriere
06/08/2023, 4:39 PM@Han for low size, how would you compare redis and pg ?
d
Deepanshu
06/08/2023, 4:41 PM@Nicholas Charriere have used qdrant in production, its quite better on Ram footprint etc
👀 1
n
Nicholas Charriere
06/08/2023, 4:41 PMNice, better than what? Any comparison points?
d
Deepanshu
06/08/2023, 4:45 PMSure, 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
06/08/2023, 4:47 PMIf you want something local, Qdrant and Weaviate have much better performance.
Deepanshu
06/08/2023, 4:48 PMYou can find more info here about difference benchmarks for choosing right Vector DB
https://github.com/erikbern/ann-benchmarks
🙌 2
h
Han
06/08/2023, 6:39 PMFor 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
06/08/2023, 6:40 PMThere'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
06/08/2023, 6:42 PMAlso, depending on use case, you do need to sometimes worry about ingestion speed or upsert speed.
a
Andrew Cote
06/09/2023, 5:50 PMcontrarian take:
👍 1
h
Han
06/09/2023, 5:59 PMI 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
06/09/2023, 6:01 PMBoth embeddings layer and attention layers in the transformer model architecture are both doing vectorized retrieval.
4 Views