[swyx]

congrats team!

what was the thinking behind choosing to support "Vector Database (powered by LangChain)" instead of directly supporting Pinecone Chroma et al directly as you do in the other destinations? when is direct integration the right approach vs when is it better to have an (possibly brittle, but faster time to market) integration of an integration?

[mtricot]

Great question :) We want to get to value as fast as possible. I am certain that at some point we will need to go deeper with those integrations and they will likely require to be separate destinations. It will also depend on how they differentiate from each others, we will need more granularity with configurations.

[zarazas]

I ak playing around with langchain the last days as well and when I checked right all langchain is really doing for you is giving you a guideline about recommended steps for a vector assisted LLM. In your example it actually just adds some text to the prompt like: "Answer the following question with the context provided here, If you dont find the right info dont make something up" sth. Along those lines

[mritchie712]

have you considered supporting pgvector? I'd imagine that'd be easier since you already have pg as a destination.

[mtricot]

On the roadmap! We want to get more clarity on how to fit the Embedding part in the ELT model. Once we figure it out we will add it to PG.

[rschwabco]

A version supporting Pinecone directly is coming soon!