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 ✅"
1---2name: zeabur-rag-triage3description: List pending knowledge base maintenance items — open reports, unverified learned chunks, low-score queries, and negative feedback. Use when checking KB health, reviewing the maintenance queue, or starting a curation session. Triggers on "review queue", "what needs attention in the KB", "pending reports", "unverified chunks", "failed queries", "KB health check". Requires admin scope.4---56# RAG — Triage78Show what needs attention in the knowledge base. Returns 5 categories of pending items in a single call.910Base URL: `$ZEABUR_RAG_URL`11Auth: `Authorization: Bearer $RAG_API_KEY` — **admin scope required**1213## API1415```bash16curl -s "$ZEABUR_RAG_URL/api/admin/triage?days=14&similarity_threshold=0.4&limit=20" \17 -H "Authorization: Bearer $RAG_API_KEY"18```1920| Param | Default | Description |21|-------|---------|-------------|22| `days` | `14` | Time window for signals (reports and learned have no time window) |23| `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. |24| `limit` | `20` | Max items per category |2526## Response2728Returns JSON with 5 arrays + `counts` (true totals, not truncated) + `has_more` (boolean per category):2930- **`open_reports`** — reports with `status='open'`, no time window. Fields: `id`, `type`, `chunk_id`, `query`, `detail`, `created_at`.31- **`unverified_learned`** — learned chunks with `status='unverified'`, no time window. Fields: `id`, `title`, `tags`, `created_at`, `age_days`.32- **`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`.33- **`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`.34- **`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`.3536If a category query fails, its array is empty and a `<category>_error` field appears with the error message.3738## After triage3940- To drill into a specific chunk: use `zeabur-rag-inspect` with the chunk ID.41- To start the full curation loop: use `zeabur-rag-curate`.42- **Do not mutate anything directly from triage results.** Always inspect first, then decide on action.4344## When all categories are empty4546If every count is 0, the knowledge base has no pending maintenance. Report:47"The knowledge base has no pending items — looks healthy ✅"
zeabur