Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add rag-pinecone-cohere-embed-rerank template #15216

Closed

Conversation

samuelpath
Copy link
Contributor

@samuelpath samuelpath commented Dec 27, 2023

  • Description: Following a private discussion with @rlancemartin and @SandraKublik, this PR adds a new template using:
    • Cohere Embed v3
    • Cohere Chat
    • Cohere Re-Rank

This template is very similar to the Rag Pinecone Rerank template which uses OpenAI's API instead for the embeddings and chat endpoints.

I have tested it locally and it works as expected.

If this PR gets merged, we may want to rename the Rag Pinecone Rerank template to specify that OpenAI is used for the embeddings and chat (for instance to something like: rag-pinecone-openai-embed-rerank).

  • Issue: N/A
  • Dependencies: No dependencies added for this change.
  • Twitter handle: @smlpth

@efriis efriis self-assigned this Dec 27, 2023
@dosubot dosubot bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Dec 27, 2023
Copy link

vercel bot commented Dec 27, 2023

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Ignored Deployment
Name Status Preview Comments Updated (UTC)
langchain ⬜️ Ignored (Inspect) Visit Preview Jan 26, 2024 8:54pm

@dosubot dosubot bot added Ɑ: embeddings Related to text embedding models module 🤖:enhancement A large net-new component, integration, or chain. Use sparingly. The largest features 🔌: pinecone Primarily related to Pinecone vector store integration labels Dec 27, 2023
@samuelpath samuelpath force-pushed the cohere-embed-template branch 10 times, most recently from 8d7015c to b946e5c Compare December 27, 2023 16:41
@samuelpath samuelpath changed the title Add rag-pineceone-cohere-embed-rerank template Add rag-pineceone-cohere-embed-rerank template Dec 27, 2023
@samuelpath samuelpath changed the title Add rag-pineceone-cohere-embed-rerank template Add rag-pinecone-cohere-embed-rerank template Dec 27, 2023
@samuelpath samuelpath force-pushed the cohere-embed-template branch from b946e5c to 50fe498 Compare January 2, 2024 12:35
@dosubot dosubot bot added size:M This PR changes 30-99 lines, ignoring generated files. and removed size:L This PR changes 100-499 lines, ignoring generated files. labels Jan 26, 2024
@samuelpath samuelpath force-pushed the cohere-embed-template branch from c0e4f2e to a2fe4d9 Compare January 26, 2024 20:53
@samuelpath samuelpath force-pushed the cohere-embed-template branch from a2fe4d9 to 90b0180 Compare January 26, 2024 20:54
@samuelpath
Copy link
Contributor Author

@efriis I took the same toggle switch approach here for this reranking template as I did for the RAG conversation template here.

cc @rlancemartin

@efriis
Copy link
Member

efriis commented Jan 28, 2024

Great! Same comment about using a configurable alternative instead of an environment var here. Happy to answer questions if you need! https://templates.langchain.com/?integration_name=pirate-speak-configurable

@hwchase17 hwchase17 closed this Jan 30, 2024
@baskaryan baskaryan reopened this Jan 30, 2024
@samuelpath samuelpath closed this Feb 23, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Ɑ: embeddings Related to text embedding models module 🤖:enhancement A large net-new component, integration, or chain. Use sparingly. The largest features 🔌: pinecone Primarily related to Pinecone vector store integration size:M This PR changes 30-99 lines, ignoring generated files. template
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants