github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-03 03:59:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add template for Pinecone + Multi-Query (#12353)

Browse Source
This commit is contained in:
Lance Martin
2023-10-26 10:12:23 -07:00
committed by GitHub
parent c6a733802b
commit bc6f6e968e
12 changed files with 2531 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
templates/rag-pinecone-multi-query/README.md Normal file
View File

@@ -0,0 +1,16 @@
# RAG Pinecone multi query
This template performs RAG using Pinecone and OpenAI with the [multi-query retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/MultiQueryRetriever).
This will use an LLM to generate multiple queries from different perspectives for a given user input query.
For each query, it retrieves a set of relevant documents and takes the unique union across all queries for answer synthesis.
## Pinecone
This template uses Pinecone as a vectorstore and requires that `PINECONE_API_KEY`, `PINECONE_ENVIRONMENT`, and `PINECONE_INDEX` are set.
## LLM
Be sure that `OPENAI_API_KEY` is set in order to the OpenAI models.