You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/templates/rag-pinecone-rerank
Bagatur 2424fff3f1
notebook fmt (#12498)
8 months ago
..
rag_pinecone_rerank Format Templates (#12396) 8 months ago
tests Cohere re-rank template (#12378) 8 months ago
LICENSE Cohere re-rank template (#12378) 8 months ago
README.md Cohere re-rank template (#12378) 8 months ago
poetry.lock Cohere re-rank template (#12378) 8 months ago
pyproject.toml Minor updates to ReRank template (#12388) 8 months ago
rag_pinecone_rerank.ipynb notebook fmt (#12498) 8 months ago

README.md

RAG Pinecone Cohere Re-rank

This template performs RAG using Pinecone and OpenAI, with Cohere to perform re-ranking on returned documents.

Re-ranking provides a way to rank retrieved documents using specified filters or criteria.

Pinecone

This connects to a hosted Pinecone vectorstore.

Be sure that you have set a few env variables in chain.py:

  • PINECONE_API_KEY
  • PINECONE_ENV
  • index_name

LLM

Be sure that OPENAI_API_KEY is set in order to the OpenAI models.

Cohere

Be sure that COHERE_API_KEY is set in order to the ReRank endpoint.