feat: RAG pipeline analytics#3
Merged
Merged
Conversation
Add /v1/llm/rag endpoint with DuckDB queries over rag.* metadata on retrieval spans. Dashboard gets a RAG tab with stat cards (total retrievals, avg relevance, context utilization), source table with latency percentiles, and relevance distribution. Trace detail view shows RAG metadata inline on retrieval spans. - Migration 021: span_type index for efficient retrieval span filtering - 3 DuckDB SQL queries: overview, hourly metrics, relevance summary - Uses json_extract with quoted key notation for dot-containing keys - 3 new integration tests + E2E seed data and spec updates
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
GET /v1/llm/ragendpoint for RAG pipeline analytics over retrieval span metadata (rag.*convention)span_typeindex for efficient retrieval span filteringTest plan
cargo test --features llm-tracing— 153 tests pass (48 LLM tracing including 3 new RAG tests)rag.*metadata, verify/v1/llm/ragreturns populated response