docs: clarify LostInTheMiddleRanker threshold units - #12092
Conversation
|
@MaskerFather is attempting to deploy a commit to the deepset Team on Vercel. A member of the Team first needs to authorize it. |
|
|
|
Hi @zcxGGmu, 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 |
|
Hi @zcxGGmu, just a friendly reminder: this PR is still in draft because the Contributor License Agreement (CLA) hasn't been signed yet. We'd love to review your contribution! Please sign the CLA via the link in the |
Related Issues
Proposed Changes:
LostInTheMiddleRanker.word_count_thresholdcounts whitespace-separated words, not tokenizer-aware tokens.How did you test it?
hatch run fmt-check haystack/components/rankers/lost_in_the_middle.pyhatch -e test run pytest test/components/rankers/test_lost_in_the_middle.pygit diff --checkNotes for the reviewer
No release note was added because this is a docs/docstring-only clarification with no behavior change.
This PR was generated with an AI assistant. I reviewed the changes and ran the relevant tests.
Checklist
fix:,feat:,build:,chore:,ci:,docs:,style:,refactor:,perf:,test:and added!in case the PR includes breaking changes.