feat: add premise relevance to retrieval filtering#49
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add premise-oriented retrieval coverage to the generic HR retrieval-filtering examples in Python and TypeScript.
The examples now show two separate host-owned retrieval decisions:
The same query can now return different relevant documents when saved case context changes, while eligibility remains unchanged.
Why
Retrieval filtering previously demonstrated policy/access-control only.
This adds the remaining natural premise case for retrieval: persistent factual case context changing relevance within an already eligible document set.
The change keeps the access-control story intact and avoids using premise as disguised authorization:
use employee_hr_accessgrants eligibility to employee-facing documentsExample metadata
Checklist
Notes
Validation performed:
uv run --no-sync pytest python/tests/test_retrieval_filtering_example.py— passed,13 passedcd typescript/examples/retrieval_filtering/hr_policy_lookup && npm test— passed,13 passed, 0 failedcd typescript/examples/retrieval_filtering/hr_policy_lookup && npm run typecheck— passedcd typescript/examples/retrieval_filtering/hr_policy_lookup && npm run build— passed./scripts/validate_python.sh— passed,185 passed, 6 skipped./scripts/validate_typescript_fast.sh— passednpx --yes markdownlint-cli2 python/examples/retrieval_filtering/README.md python/examples/retrieval_filtering/hr_policy_lookup/README.md typescript/examples/retrieval_filtering/README.md typescript/examples/retrieval_filtering/hr_policy_lookup/README.md— passed,0 error(s)ChromaDB files were intentionally left unchanged.