add relevance feedback skill#60
Open
mrscoopers wants to merge 1 commit into
Open
Conversation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
✅ Deploy Preview for qdrant-skills ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Contributor
Author
|
Link checker fails because skill is not merged in, and I reference its URL fully from a parent skill doc, as in my experience, agents have troubles navigating downwards, seeing only relative path & having to figure out absolute URL themselves So I can fix the link checker thing, but I'd like to avoid it, to be honest:) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this PR does
Adds
qdrant-relevance-feedbackas a new leaf sub-skill undersearch-strategies/relevance-feedback/, at the same level ashybrid-search/. Updates the parentsearch-strategies/SKILL.mdto replace the inline RF content with a reference link and improve the section header and "Use when:" line.Type
Checklist
python3 scripts/validate_skills.pypasses — 2 warnings: line count (116, intentional — RF requires prerequisite calibration context) and em-dash (pre-existing style)Use whenwith 5+ trigger phrasesallowed-tools## What NOT to Dosectionsearch.qdrant.tech/md/documentation/— two exceptions:api.qdrant.tech/api-reference/search/query-points(RF API reference) andpypi.org/project/qdrant-relevance-feedback/(calibration library), both intentionalTest prompt
I have a context engineering workshop where I create a collection and populate it.
Currently, it uses a tool based on the retrieve_papers_based_on_query in search_engine_query.py,
which uses hybrid search + reranker, and as a dense search arm, it uses text-embedding-3-small, cut to 1024 dims.
I'd love to use text-embedding-3-large as the dense retriever instead for better quality,
but it's too expensive. Is there any cheaper alternative? Use Qdrant skills, recommend something to me.