stella-ops.org/git.stella-ops.org
1
0
Fork 0
Code Issues Pull Requests Actions 3 Releases Wiki Activity

Repair live unified search corpus runtime

Browse Source
This commit is contained in:
master
2026-03-09 19:44:16 +02:00
parent bf937c9395
commit 00bf2fa99a
12 changed files with 175 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/operations/unified-search-operations.md
View File

@@ -6,6 +6,8 @@ Runbook for AdvisoryAI unified search setup, operations, troubleshooting, perfor
## Setup
1. Configure `AdvisoryAI:KnowledgeSearch:ConnectionString`.
2. Configure `AdvisoryAI:UnifiedSearch` options.
3. For live compose/runtime, set `AdvisoryAI:KnowledgeSearch:FindingsAdapterBaseUrl`, `...:VexAdapterBaseUrl`, and `...:PolicyAdapterBaseUrl` together so findings, VEX, and policy ingest from live services instead of partial fallback snapshots.
4. Ensure the published AdvisoryAI image carries the repo-shaped local corpus under `/app`, including `src/AdvisoryAI/StellaOps.AdvisoryAI/UnifiedSearch/Snapshots/{findings,vex,policy,graph,opsmemory,timeline,scanner}.snapshot.json`.
3. Ensure model artifact path exists when `VectorEncoderType=onnx`:
- default: `models/all-MiniLM-L6-v2.onnx`
4. Rebuild indexes in order when verifying live search quality:
@@ -109,6 +111,7 @@ Example:
- Verify `UnifiedSearch.Enabled` and tenant flag `Enabled`.
- Run index rebuild and check chunk count.
- If suggestions also fail, verify both rebuild steps were run in order and re-check with a known live query such as `database connectivity`.
- If only findings answer lanes work while VEX/policy/graph/OpsMemory remain corpus-unready, verify the published snapshot files exist under `/app/src/AdvisoryAI/StellaOps.AdvisoryAI/UnifiedSearch/Snapshots/` and confirm the VEX/policy adapter base URLs are configured in runtime env.
### Symptom: poor semantic recall
- Verify `VectorEncoderType` and active encoder diagnostics.