feat: add Context.dev integration - #3871
Conversation
|
Hi @aadithyanr, thanks a lot for contributing a new integration! 🙏 This PR looks like it adds a new integration ( Every integration we merge is maintained, tested nightly, and released by us, so before reviewing the code Then reference the issue in this PR's description (for example, by adding |
|
Hi @aadithyanr, thanks a lot for your contribution! 🙏 We noticed that the Contributor License Agreement (CLA) check ( To get your PR reviewed, please sign the CLA via the link in the |
|
Thanks for signing the CLA, @aadithyanr! 🎉 This PR is now ready for review again and the reviewer has been re-assigned. |
Related Issues
Proposed Changes
Adds
context-dev-haystack, an official Context.dev integration with three Haystack components:ContextWebSearchfor relevance-ranked live web searchContextFetcherfor fetching known URLs as Markdown DocumentsContextCrawlerfor bounded website crawlingAll components support sync and async execution, environment-backed secrets, Haystack serialization, retry handling, custom API parameters, and the production Context.dev API.
How did you test it?
hatch run fmt-checkhatch run test:types— 5 source files passedhatch run test:unit— 25 passedhatch run test:integration— 6 live production API tests passed across sync and async search, fetch, and crawlhaystack-ai==2.24.1andhttpx==0.27.0hatch build— sdist and wheel built successfullyNotes for the reviewer
scripts/create_new_integration.py.context-dev-haystackbecause the unrelated Context.ai project already ownscontext-haystackon PyPI.maxPagesthroughcrawl_params.ContextWebSearchrequests 10 whentop_kis lower and returns only the requested number.Checklist