Ship a real example knowledge doc (RAG + e2e) - #5
Merged
Merged
Conversation
The shipped knowledge base doc was a placeholder whose text led with "This is a sample document ... replace it with your own files." That boilerplate dominated RAG retrieval — a "which day is trash pickup" query surfaced the "replace me" intro instead of the actual schedule, and the e2e KNOWLEDGE test never got its answer. Replace it with real, clean household reference content (trash/recycling schedule, Wi-Fi, contacts, thermostat, mail) and no meta boilerplate, so retrieval returns the facts. Track this one example under data/knowledge/ via a .gitignore exception (user-dropped docs there stay ignored), so a fresh clone has a working, indexable knowledge base out of the box. Verified: reindexed live (1 doc, 2 chunks), "trash pickup" retrieval returns Tuesday, and test_knowledge_over_call passes end to end. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
The shipped knowledge base doc was a placeholder whose text led with "This is a sample document … replace it with your own files." That boilerplate dominated RAG retrieval — a "which day is trash pickup?" query surfaced the "replace me" intro instead of the actual schedule, and the e2e KNOWLEDGE test never got its answer.
data/knowledge/via a.gitignoreexception — user-dropped docs there stay ignored — so a fresh clone has a working, indexable knowledge base out of the box.Verified
Reindexed live (1 doc, 2 chunks); "trash pickup" retrieval returns Tuesday;
test_knowledge_over_callpasses end to end. This was the last non-guarded e2e failure.