will/swarm-master
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(rag): add optional NPU reranker fallback

Browse Source
This commit is contained in:
William Valentin
2026-06-04 14:50:41 -07:00
parent 06f235d26b
commit 71f3c05587
5 changed files with 303 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/swarm-infrastructure.md
+12 -5
View File
@@ -126,7 +126,7 @@ Host/user services:
- `ollama.service` — `:18807`, legacy/CPU embeddings API fallback
- `openvino-embeddings.service` — `:18817`, OpenVINO NPU embeddings API (`/v1/embeddings`, `/api/embed`, `/api/embeddings`)
- `docker-health-endpoint.service` — `:18809`, read-only container health for n8n
- `obsidian-reindex-endpoint.service` — `:18810`, Obsidian/RAG reindex trigger; default collection `obsidian_bge_npu` using OpenVINO NPU embeddings
- `obsidian-reindex-endpoint.service` — `:18810`, Obsidian/RAG reindex trigger and `/semantic-search`; default collection `obsidian_bge_npu` using OpenVINO NPU embeddings, with optional request-time `:18818` reranking disabled by default
- `url-content-extractor.service` — `:18812`, YouTube/PDF/web extraction
- `voice-memo-processor.service` — `:18813`, voice memo processing
- `rag-embedding-health.service` — `:18814`, RAG/embedding health wrapper
@@ -159,7 +159,8 @@ RAG/vector store:
- Reindex state/progress: active BGE/NPU state in `~/.hermes/data/rag-search/obsidian_bge_npu_index_state.json` and `obsidian_bge_npu_reindex_progress.json`; legacy Ollama state in `obsidian_index_state.json` remains for comparison/fallback.
- Active RAG query/reindex embedding backend: OpenVINO NPU embeddings service on `:18817`, currently `bge-base-en-v1.5-int8-ov`, collection `obsidian_bge_npu`.
- Legacy comparison/fallback collection: `obsidian`, built with Ollama on `:18807` using `nomic-embed-text`.
- Reindex endpoint: `POST :18810/reindex` for incremental updates, `POST :18810/reindex?full=true` for full semantic rebuilds, `GET :18810/semantic-health` to verify vectors plus a search smoke test.
- Reindex/search endpoint: `POST :18810/reindex` for incremental updates, `POST :18810/reindex?full=true` for full semantic rebuilds, `GET :18810/semantic-health` to verify vectors plus a search smoke test, and `POST :18810/semantic-search` for n8n/Hermes semantic context lookup.
- Optional reranker path: `RAG_RERANK_ENABLED=false` by default. When enabled, `/semantic-search` retrieves `RAG_RERANK_INITIAL_K` vector candidates, calls `RAG_RERANK_URL` (`http://127.0.0.1:18818/rerank` by default), returns reranked `RAG_RERANK_TOP_K`, requires positive `npu_busy_delta_us` by default (`RAG_RERANK_REQUIRE_NPU_PROOF=true`), and falls back to vector order with `rerank.error` metadata on timeout/error/non-positive NPU proof. Reranking is request-time only and must not mutate Chroma/vector collections.
## Monitoring model
@@ -214,6 +215,11 @@ cd /home/will/lab/swarm
make status
make local-ai-health
./scripts/npu-service-health.sh # read-only; includes sysfs busy-time proof for :18817
curl -fsS http://127.0.0.1:18810/semantic-health | jq '{status,state,search_ok,result_count}'
curl -fsS http://127.0.0.1:18810/semantic-search \
-H 'Content-Type: application/json' \
-d '{"query":"non-private semantic smoke","top_k":2}' \
| jq '{ok,index,top_k,search_k,rerank,result_count}'
curl -fsS http://127.0.0.1:18808/healthz
curl -fsS http://127.0.0.1:8081/healthz
curl -fsS 'http://127.0.0.1:8081/v1/events?event_type=swarm.snapshot&limit=1' | jq .
@@ -223,8 +229,9 @@ From inside `n8n-agent`:
```bash
docker exec n8n-agent /bin/sh -lc '
wget -qO- -T 5 http://172.19.0.1:8081/healthz
wget -qO- -T 5 "http://172.19.0.1:8081/v1/events?event_type=swarm.snapshot&limit=1" | head -c 500
wget -qO- -T 5 http://172.19.0.1:18810/healthz
wget -qO- -T 5 http://172.19.0.1:18814/healthz
wget -qO- -T 5 http://172.19.0.1:18817/healthz | head -c 500
'
```
@@ -247,4 +254,4 @@ jq '.[0] | {id,name,active,nodes:(.nodes|length)}' /tmp/agentmon-export.json
- From `n8n-agent`, use `127.0.0.1:5678` for n8n itself and `172.19.0.1:<host-port>` for host-published swarm services.
- Agentmon `/healthz` only proves the web/API process is alive; pair it with snapshot freshness to prove the monitoring pipeline is flowing.
- OpenClaw is intentionally dormant unless explicitly re-enabled; do not alert on VMs being shut off by default.
- OpenVINO NPU sidecars on `:18818`, `:18819`, `:18820`, and optional `:18829` are prototypes/not-live unless a later approved change installs and routes them. Do not draw live Atlas/Hermes/RAG arrows to them in diagrams until that approval and implementation actually exist.
- OpenVINO NPU sidecars on `:18819`, `:18820`, and optional `:18829` are prototypes/not-live unless a later approved change installs and routes them. The `:18818` reranker is also a prototype service, but `:18810/semantic-search` now has a disabled-by-default request-time rerank hook that falls back safely when `:18818` is unavailable. Do not draw live Atlas/Hermes/classifier/GenAI arrows to prototypes until approval and implementation actually exist.