Find answers from the community

Updated 2 years ago

Hey oguntadej 8125 thanks for flagging

Hey @oguntadej , thanks for flagging this. We're working on making the UX better - in the meantime try defining a pinecone vector store object: https://github.com/jerryjliu/gpt_index/blob/main/gpt_index/vector_stores/pinecone.py, and then passing this is as a vector store argument when you initialize GPTPineconeIndex e.g. index = GPTPineconeIndex(documents, ..., vector_store=vector_store)

7 comments

ooguntadej

@jerryjliu0 that gives another error about GPTPineconeIndex requiring pinecone_index(even though I passed an instance of Pinecone index to the vector store):

    raise ValueError("pinecone_index is required.")
ValueError: pinecone_index is required.

jjerryjliu0

i see....you can also try importing the base GPTVectorStoreIndex class (from gpt_index.indices.vector_store.base import GPTVectorStoreIndex) and initializing it with the above

jjerryjliu0

sorry for the hassle

jjerryjliu0

with the pinecone index class you can try GPTPineconeIndex(documents, ..., vector_store=vector_store, pinecone_index=pinecone_index) where pinecone_index is your Pinecone index. it's a bit hacky atm

ooguntadej

Appreciate the help... 🙏 . Let me know how I can help out with the documentation

jjerryjliu0

@oguntadej of course, sorry the pinecone index is in a bit of a weird state atm. will keep you updated when we have an update!

ooguntadej

No worries.

Add a reply