docs(skills): add retrieval models skill#2305
Draft
oliverholworthy wants to merge 3 commits into
Draft
Conversation
Signed-off-by: Oliver Holworthy <1216955+oliverholworthy@users.noreply.github.com>
Signed-off-by: Oliver Holworthy <1216955+oliverholworthy@users.noreply.github.com>
Signed-off-by: Oliver Holworthy <1216955+oliverholworthy@users.noreply.github.com>
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 does this PR do ?
Adds a retrieval-models agent skill for NeMo AutoModel bi-encoder and cross-encoder work, including guidance for retrieval wrappers, bidirectional backbones, recipes, collator shape contracts, validation, and live skill evals.
Changelog
skills/retrieval-models/SKILL.mdwith retrieval model workflows, trigger boundaries, validation commands, and troubleshooting guidance.skills/retrieval-models/PITFALLS.mdfor common retrieval wrapper, metadata, and recipe shape issues.skills/retrieval-models/evals/evals.jsonfor astra live-agent evaluation coverage.Before your PR is "Ready for review"
Pre checks:
Additional Information
Validation run:
astra-skill-eval evaluate skills/retrieval-models --static --markdown-> A, 100/100, no issuesastra-skill-eval validate skills/retrieval-models-> all checks passedastra-skill-eval evaluate skills/retrieval-models --agent-eval -a codex --env-mode local --n-attempts 1 --skip-baseline --copy-repo --results-dir /tmp/astra-retrieval-models-eval-clean --markdown-> pass@1 3/4, accuracy 1.00Draft PR because the live eval still shows one implementation-heavy scenario below threshold and should get a reviewer pass before marking ready.