[billybones]

Such an important problem!

I get the benefit over Pinecone (which wasn't built with LLMs, etc in mind)

How does this compare to Chroma? Feels like it has most of what you're talking about, and already has an open source product live.

https://www.trychroma.com/

[gk1]

> I get the benefit over Pinecone (which wasn't built with LLMs, etc in mind)

What do you mean?

Pinecone was specifically made to be used alongside LLMs and other embedding models. That’s how anyone uses Pinecone.

[jxodwyer1]

Chroma is awesome <3 - We have some overlap with them as we store the embeddings. But, we provide additional operations on top of the data, such as clustering/fine-tuning. We're also looking into open-sourcing some tools in the near future!

[swalsh]

Postgres has an extension as well (pgvector). I've been using it, great performance, great scaling options (though I'm not even close to testing the limits) and gives you the full flexibility of Postgres.

It's easy enough to define a docker compose file, and deploy it to my environments.

[sroussey]

That’s what I’m setting up now. What do you use to creat the embedding? OpenAI? Which model?

[abyesilyurt]

How does it scale with the number of rows?