zeabur-rag-triage

RAG — Triage

Show what needs attention in the knowledge base. Returns 5 categories of pending items in a single call.

Base URL: $ZEABUR_RAG_URL Auth: Authorization: Bearer $RAG_API_KEY — admin scope required

API

curl -s "$ZEABUR_RAG_URL/api/admin/triage?days=14&similarity_threshold=0.4&limit=20" \
  -H "Authorization: Bearer $RAG_API_KEY"

Param	Default	Description
days	14	Time window for signals (reports and learned have no time window)
similarity_threshold	0.4	Queries with top_similarity below this are flagged. Note: in hybrid mode (RRF), scores are ~0–0.02 so the default 0.4 catches all hybrid queries. Adjust to ~0.005 for meaningful hybrid-mode filtering.
limit	20	Max items per category

Response

Returns JSON with 5 arrays + counts (true totals, not truncated) + has_more (boolean per category):

• open_reports — reports with status='open', no time window. Fields: id, type, chunk_id, query, detail, created_at.
• unverified_learned — learned chunks with status='unverified', no time window. Fields: id, title, tags, created_at, age_days.
• low_similarity_signals — queries where the top score fell below the threshold, within the time window, deduped by query text. The score is RRF in hybrid mode (~0–0.02) or cosine in semantic mode (0–1). Fields: id, query, top_similarity, top_chunk_ids, client, created_at.
• negative_feedback_signals — queries that got negative user feedback, within the time window. Fields: id, query, feedback_score, feedback_comment, top_chunk_ids, created_at.
• needs_frontmatter — chunks whose tags include "needs-frontmatter", meaning they were ingested from a source file that lacks proper frontmatter and got a temporary ID. Fields: id, title, tags, url, source, created_at.

If a category query fails, its array is empty and a <category>_error field appears with the error message.

After triage

• To drill into a specific chunk: use zeabur-rag-inspect with the chunk ID.
• To start the full curation loop: use zeabur-rag-curate.
• Do not mutate anything directly from triage results. Always inspect first, then decide on action.

When all categories are empty

If every count is 0, the knowledge base has no pending maintenance. Report: "The knowledge base has no pending items — looks healthy ✅"