Any reason why I cannot configure my own embedding function/method for a workspace? (instead of openAI embeddings)

Mintplex-Labs / vector-admin

The universal tool suite for vector database management. Manage Pinecone, Chroma, Qdrant, Weaviate and more vector databases with ease.

https://vectoradmin.com/

MIT License

1.01k stars 173 forks source link

Any reason why I cannot configure my own embedding function/method for a workspace? (instead of openAI embeddings) #137

Open vpinigin opened 2 months ago

vpinigin commented 2 months ago

What would you like to see?

I was wondering why I cannot use another embeding method for uploading docs? Why the only way of doing that is using OpenAI embedding models only?

timothycarambat commented 2 months ago

This is because we have not improved VectorAdmin since deciding to build out AnythingLLM. This of course should be allowed but for our first iteration of VA, we just kept the implementation very simple.

Being that embedding models and even db's with built-in embedders are quite popular and common now, this needs to be built out more to suit that use-case.