Andrew Reece comments

Repositories
Issues
Comments

Results 2 comments of


                                            Andrew Reece

Pinecone.from_texts() added 'text' metadata field modifies data object passed in as argument AND errors if text size exceeds Pinecone metadata limit per vector

One other item to consider: Because [`ids_batch`](https://github.com/hwchase17/langchain/blob/adcad98bee03ac8486f328b4f316017a6ccfc808/langchain/vectorstores/pinecone.py#LL233C34-L233C46) assigns a random UUID, if the upsert fails then I'm not sure how to restart at the right spot (or how to ensure...

Pinecone.from_texts() added 'text' metadata field modifies data object passed in as argument AND errors if text size exceeds Pinecone metadata limit per vector

I used this filter, based on byte length, which helped prevent the API error. ``` byte_max = 30000 def utf8len(s): return len(s.encode('utf-8')) screened_docs = list() for i, doc in enumerate(loaded_docs):...