Go to file

Lars 4ff908823e Some checks failed Deploy mindnet to llm-node / deploy (push) Failing after 2s Details docker/embeddings.Dockerfile aktualisiert		2025-09-04 08:00:52 +02:00
.gitea/workflows	.gitea/workflows/deploy.yml aktualisiert	2025-09-03 12:30:04 +02:00
app	app/embed_server.py aktualisiert	2025-09-03 12:55:02 +02:00
docker	docker/embeddings.Dockerfile aktualisiert	2025-09-04 08:00:52 +02:00
docs	docs/chunking_strategy.md aktualisiert	2025-09-02 19:16:50 +02:00
schemas	schemas/note.schema.json aktualisiert	2025-09-03 07:40:37 +02:00
scripts	scripts/import_markdown.py aktualisiert	2025-09-03 07:58:57 +02:00
README.md	Dateien nach "/" hochladen	2025-09-02 10:20:51 +02:00
requirements.txt	Dateien nach "/" hochladen	2025-09-02 10:20:51 +02:00

README.md

mindnet API (bundle)

This bundle provides a minimal FastAPI app for embeddings and Qdrant upserts/queries plus a Markdown importer.

Quick start

python3 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt

# 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

# 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.