Dateien nach "/" hochladen

README.md

@@ -1,32 +1,35 @@
-# mindnet — Lokales Wissensnetz (Obsidian → Qdrant → LLM) 
 
-**Ziel:** Markdown-Notizen (z. B. aus Obsidian) als Chunks mit Embeddings in **Qdrant** speichern, Notiz-Metadaten separat pflegen und Links/Beziehungen explizit abbilden.  
-**Präfix:** `mindnet_…` (keine Kollision mit bestehenden Trainer-Collections).
+# mindnet API (bundle)
 
-## Collections (Qdrant)
+This bundle provides a minimal FastAPI app for embeddings and Qdrant upserts/queries plus a Markdown importer.
 
-- **mindnet_chunks**  
-  Semantische Suche (RAG) über Text-Chunks (Vektor: 384, Distance: Cosine).  
-  **Payload (Auszug):** `note_id`, `chunk_id`, `title`, `path`, `tags[]`, `Typ`, `Rolle[]`, `Status`, `heading`, `text`, `links[]`.
-
-- **mindnet_notes**  
-  1 Punkt pro Notiz (optional Titel-Embedding). Metadaten/Facettierung.
-
-- **mindnet_edges**  
-  Explizite Kanten (A → B) als Payload-Punkte (Dummy-Vektor `size=1`).  
-  **Payload:** `src_note_id`, `dst_note_id`, `src_chunk_id`, `dst_chunk_id`, `link_text`, `relation`.
-
-## Schnellstart
+## Quick start
 
 ```bash
-python3 -m venv .venv
-source .venv/bin/activate
+python3 -m venv .venv && source .venv/bin/activate
 pip install -r requirements.txt
 
-# Qdrant-URL per ENV (optional), sonst Default:
-# export QDRANT_URL=http://127.0.0.1:6333
+# Environment (adjust as needed)
+export QDRANT_URL=http://127.0.0.1:6333
+export MINDNET_PREFIX=mindnet
+export MINDNET_MODEL=sentence-transformers/all-MiniLM-L6-v2
 
-python scripts/setup_collections.py \
-  --prefix mindnet \
-  --dim 384 \
-  --distance Cosine
+# Run API
+uvicorn app.main:app --host 0.0.0.0 --port 8001 --workers 1
+
+# (optional) Ensure collections exist (or use setup_mindnet_collections.py you already have)
+# python3 scripts/setup_mindnet_collections.py --qdrant-url $QDRANT_URL --prefix $MINDNET_PREFIX --dim 384 --distance Cosine
+
+# Import some notes
+python3 scripts/import_markdown.py --vault /path/to/Obsidian
+```
+
+## Endpoints
+
+- `POST /embed` → `{ "texts": [...] }` → 384-d vectors
+- `POST /qdrant/upsert_note`
+- `POST /qdrant/upsert_chunk`
+- `POST /qdrant/upsert_edge`
+- `POST /qdrant/query` → semantic search over chunks with optional filters
+
+See `scripts/quick_test.sh` for a runnable example.

requirements.txt

@@ -0,0 +1,9 @@
+
+fastapi
+uvicorn[standard]
+qdrant-client
+sentence-transformers
+torch
+python-frontmatter
+tqdm
+requests