Find answers from the community

s
F
Y
a
P
Updated 2 years ago

Pinecone error

@Logan M is the latest version have any issue on direct pinecone query. Getting doc id error. Everything was working fine.
L
i
4 comments
What's the error/code you are running? Should be working fine, but some functions/attributes might have changed
after change from gpt_index to llama_index, getting following error
doc_id = match.metadata["doc_id"]
KeyError: 'doc_id'
we are using own embedding model with 2000 tokens and calling it as "id"
@Logan M
I think I still need more context πŸ˜… where is match coming from here?

The embedding model shouldn't matter much here.

You can also reference the latest pinecone example here
https://github.com/jerryjliu/llama_index/blob/main/examples/vector_indices/PineconeIndexDemo.ipynb
Add a reply
Sign up and join the conversation on Discord