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

chore(rag): enable NPU reranker by default

Browse Source
This commit is contained in:
William Valentin
2026-06-04 15:01:26 -07:00
parent 71f3c05587
commit 06cd49247a
3 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/swarm-infrastructure.html
+3 -3
View File
@@ -87,7 +87,7 @@
<g><rect x="965" y="385" width="210" height="80" rx="9" fill="#0f172a"/><rect x="965" y="385" width="210" height="80" rx="9" fill="rgba(8,51,68,.4)" stroke="#22d3ee" stroke-width="1.6"/><text x="1070" y="415" text-anchor="middle" class="title">Voice</text><text x="1070" y="436" text-anchor="middle" class="tiny">Kokoro + Whisper</text><text x="1070" y="454" text-anchor="middle" class="port">:18805 / :18816</text></g>
<g><rect x="965" y="555" width="210" height="80" rx="9" fill="#0f172a"/><rect x="965" y="555" width="210" height="80" rx="9" fill="rgba(76,29,149,.4)" stroke="#a78bfa" stroke-width="1.6"/><text x="1070" y="585" text-anchor="middle" class="title">Docker services</text><text x="1070" y="606" text-anchor="middle" class="tiny">agentmon.monitor=true</text><text x="1070" y="624" text-anchor="middle" class="port">swarm/service snapshots</text></g>
<g><rect x="965" y="665" width="210" height="80" rx="9" fill="#0f172a"/><rect x="965" y="665" width="210" height="80" rx="9" fill="rgba(120,53,15,.3)" stroke="#fbbf24" stroke-width="1.6"/><text x="1070" y="695" text-anchor="middle" class="title">OpenClaw VMs</text><text x="1070" y="716" text-anchor="middle" class="tiny">currently dormant</text><text x="1070" y="734" text-anchor="middle" class="port">openclaw.snapshot</text></g>
<g><rect x="965" y="775" width="210" height="75" rx="9" fill="#0f172a"/><rect x="965" y="775" width="210" height="75" rx="9" fill="rgba(76,29,149,.4)" stroke="#a78bfa" stroke-width="1.6"/><text x="1070" y="802" text-anchor="middle" class="title">Obsidian / RAG</text><text x="1070" y="821" text-anchor="middle" class="tiny">:18810 semantic search</text><text x="1070" y="840" text-anchor="middle" class="port">NPU embed; optional rerank</text></g>
<g><rect x="965" y="775" width="210" height="75" rx="9" fill="#0f172a"/><rect x="965" y="775" width="210" height="75" rx="9" fill="rgba(76,29,149,.4)" stroke="#a78bfa" stroke-width="1.6"/><text x="1070" y="802" text-anchor="middle" class="title">Obsidian / RAG</text><text x="1070" y="821" text-anchor="middle" class="tiny">:18810 semantic search</text><text x="1070" y="840" text-anchor="middle" class="port">NPU embed + rerank</text></g>
<g><rect x="965" y="870" width="210" height="80" rx="9" fill="#0f172a"/><rect x="965" y="870" width="210" height="80" rx="9" fill="rgba(244,63,94,.16)" stroke="#fb7185" stroke-width="1.6" stroke-dasharray="6,4"/><text x="1070" y="896" text-anchor="middle" class="title">NPU sidecars</text><text x="1070" y="917" text-anchor="middle" class="tiny">approved prototypes; not live</text><text x="1070" y="936" text-anchor="middle" class="port">:18818/:18819/:18820/:18829</text></g>
<!-- host local ai box -->
@@ -106,10 +106,10 @@
</div>
<div class="cards">
<div class="info"><h3>Monitoring model</h3><ul><li>• n8n direct probes critical ports</li><li>• agentmon aggregates Docker/OpenClaw snapshots</li><li>• n8n polls agentmon for stale/degraded state</li></ul></div>
<div class="info"><h3>Operational endpoints</h3><ul><li>• n8n: 127.0.0.1:18808</li><li>• agentmon query/UI: 8081 / 8082</li><li>• live NPU: RAG 18810, Whisper 18816, embeddings 18817</li><li>• optional disabled rerank hook: 18818</li><li>• prototypes not live-routed: 18819/18820/18829</li></ul></div>
<div class="info"><h3>Operational endpoints</h3><ul><li>• n8n: 127.0.0.1:18808</li><li>• agentmon query/UI: 8081 / 8082</li><li>• live NPU: RAG 18810, Whisper 18816, embeddings 18817</li><li>• live local reranker: 18818</li><li>• prototypes not live-routed: 18819/18820/18829</li></ul></div>
<div class="info"><h3>Source paths</h3><ul><li>• Swarm repo: ~/lab/swarm</li><li>• Agentmon repo: ~/lab/agentmon</li><li>• Workflows: swarm-common/n8n-workflows</li></ul></div>
</div>
<div class="footer">Generated as repo documentation. Open locally in a browser; no JavaScript, all SVG inline. Dashed red OpenVINO NPU sidecars are approved prototypes; only :18810 has a disabled-by-default request-time rerank hook to :18818, and no classifier/GenAI sidecar is live-routed.</div>
<div class="footer">Generated as repo documentation. Open locally in a browser; no JavaScript, all SVG inline. The :18818 reranker is live as a request-time second stage for :18810 semantic search with safe vector fallback; classifier/GenAI/doc-image sidecars remain prototypes/not live-routed.</div>
</div>
</body>
</html>
docs/swarm-infrastructure.md
+2 -2
View File
@@ -160,7 +160,7 @@ RAG/vector store:
- 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/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.
- Reranker path: `RAG_RERANK_ENABLED=true` for `:18810/semantic-search` after local bake testing. `/semantic-search` retrieves `RAG_RERANK_INITIAL_K` vector candidates, calls `RAG_RERANK_URL` (`http://127.0.0.1:18818/rerank`), 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
@@ -254,4 +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 `: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.
- 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 live as a local request-time second stage for `:18810/semantic-search`; it still falls back to vector order on timeout/error/non-positive NPU proof. Do not draw live Atlas/Hermes/classifier/GenAI arrows to prototypes until approval and implementation actually exist.
swarm-common/obsidian-reindex-endpoint.service
+4 -4
View File
@@ -11,13 +11,13 @@ Environment=PORT=18810
Environment=RAG_COLLECTION=obsidian_bge_npu
Environment=RAG_EMBED_MODEL=bge-base-en-v1.5-int8-ov
Environment=OLLAMA_BASE_URL=http://127.0.0.1:18817
# Optional request-time second-stage reranking. Disabled by default so :18810
# keeps working when the :18818 prototype is stopped or not yet approved live.
Environment=RAG_RERANK_ENABLED=false
# Request-time second-stage reranking. The :18810 handler keeps vector-order
# fallback on reranker timeout/error or missing positive NPU proof.
Environment=RAG_RERANK_ENABLED=true
Environment=RAG_RERANK_URL=http://127.0.0.1:18818/rerank
Environment=RAG_RERANK_INITIAL_K=20
Environment=RAG_RERANK_TOP_K=5
Environment=RAG_RERANK_TIMEOUT_MS=3000
Environment=RAG_RERANK_TIMEOUT_MS=1500
Environment=RAG_RERANK_REQUIRE_NPU_PROOF=true
[Install]