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

feat(rag): switch Obsidian endpoint to NPU embeddings

Browse Source
This commit is contained in:
William Valentin
2026-06-03 20:04:43 -07:00
parent bcc652e5aa
commit 1a674e854e
3 changed files with 43 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/swarm-infrastructure.md
+4 -4
View File
@@ -125,7 +125,7 @@ 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
- `obsidian-reindex-endpoint.service` — `:18810`, Obsidian/RAG reindex trigger; default collection `obsidian_bge_npu` using OpenVINO NPU embeddings
- `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
@@ -144,9 +144,9 @@ Local REST API:
RAG/vector store:
- ChromaDB path: `~/.hermes/data/rag-search/chroma/`
- Reindex state/progress: `~/.hermes/data/rag-search/obsidian_index_state.json` and `obsidian_reindex_progress.json`
- RAG query/reindex embedding backend: still Ollama on `:18807` with `nomic-embed-text` until a deliberate full Chroma rebuild/migration is run.
- RAG/embedding health probe backend: OpenVINO NPU embeddings service on `:18817`, currently `bge-base-en-v1.5-int8-ov`.
- 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.
## Monitoring model