Find answers from the community

Updated 2 years ago

Vector index

That makes sense. If I use a vector db, would I still use LlamaIndex? I'm a bit confused on how that would work since LlamaIndex generates a JSON file for the index
L
1 comment
Yea for most vector indexes I think it ends up storing the documents in the vector dB

Then, you just connect back to it with llama index.

For example
index = GPTPineconeIndex([], pinecone_index=pinecone_index) will connect to an index you made with llama index

Llama index still handles querying the llm, chunking, etc. Can even make graphs that use vector dbs too
Add a reply
Sign up and join the conversation on Discord