Skip to content

community(you): Integrate You.com conversational APIs #23046

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

Merged
merged 15 commits into from
Jul 15, 2024

Conversation

christeefy
Copy link
Contributor

You.com is releasing two new conversational APIs — Smart and Research.

This PR:

  • integrates those APIs with Langchain, as an LLM
  • streaming is supported

If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.

Copy link

vercel bot commented Jun 17, 2024

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 Jun 24, 2024 3:13pm

@dosubot dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. 🤖:enhancement A large net-new component, integration, or chain. Use sparingly. The largest features labels Jun 17, 2024
@christeefy christeefy changed the title community(you): Integrate You.com's Smart and Research conversational APIs community(you): Integrate You.com conversational APIs Jun 17, 2024
Copy link
Contributor

@hwchase17 hwchase17 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

these are cool! i think you need to merge master before CI can run

Copy link
Contributor Author

@christeefy christeefy Jun 18, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Only adding unit tests for the .invoke method.

I do not know how to use the requests_mock library to mock a stream of bytes. I've attempted to use requests.post(..., content=content_callback) where content_callback returns a whole byte string but the BaseLLM.stream method raises an error. If I have force content_callback to return a generator of byte tokens, requests_mock instead raises an error expecting content_callback to return only one byte string.

@christeefy christeefy requested a review from hwchase17 June 18, 2024 20:37
@ccurme ccurme added the community Related to langchain-community label Jun 18, 2024
@rmcarthur
Copy link

Checking in from You.com. We are hoping to rapidly increase and improve APIs. Let me know if we can support in any way.

@rmcarthur
Copy link

@hwchase17 how do we get this merged?

@christeefy
Copy link
Contributor Author

@ccurme, since you previously reviewed a related #22622, could you help us to get this over the line?
Thank you very much in advance!

@ccurme ccurme self-assigned this Jul 15, 2024
@dosubot dosubot bot added the lgtm PR looks good. Use to confirm that a PR is ready for merging. label Jul 15, 2024
@ccurme ccurme merged commit 5171ffc into langchain-ai:master Jul 15, 2024
51 checks passed
@christeefy christeefy deleted the you/chat-apis branch July 16, 2024 12:44
@christeefy
Copy link
Contributor Author

Thanks @ccurme!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
community Related to langchain-community 🤖:enhancement A large net-new component, integration, or chain. Use sparingly. The largest features lgtm PR looks good. Use to confirm that a PR is ready for merging. size:L This PR changes 100-499 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants