Lars/mindnet
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 21 Wiki Activity
661 Commits 3 Branches 37 Tags 7.6 MiB
Python 98.9%
Shell 0.9%
Dockerfile 0.2%
V2.3.1-WP06
Go to file
Lars 86faf5b8f0
All checks were successful
Deploy mindnet to llm-node / deploy (push) Successful in 3s
Details
Merge pull request 'WP06' (#4) from WP06 into main 
feat(wp06): Release v2.3.1 - Decision Engine & Hybrid Intent Router

Abschluss von WP-06: Transformation des Chatbots zum strategischen Partner.

Hauptänderungen:
- Feature: Hybrid Intent Router implementiert (Fast Path: Keywords / Slow Path: LLM-Fallback).
- Feature: Strategic Retrieval (Injektion von [VALUE], [GOAL], [EXPERIENCE] basierend auf Intent).
- Feature: Multi-Persona Support (Berater, Empathischer Spiegel, Coder, Bibliothekar).
- Config: Late Binding Logik komplett in `config/decision_engine.yaml` ausgelagert.
- Tech: LLM-Service erweitert um konfigurierbaren Timeout (CPU-Inference Support) und Raw-Generation Mode.
- Docs: Vollständige Aktualisierung der Kern-Dokumentation (Architektur, Playbooks, Guides) auf v2.3.1.

Version Bump: 2.3.0 -> 2.3.1
2025-12-09 17:14:52 +01:00
.gitea/workflows .gitea/workflows/deploy.yml aktualisiert 2025-11-07 09:37:02 +01:00
.vscode Neue Dokumentationsdateien 2025-12-07 15:49:44 +01:00
app verbessertes Prompt, und chat-Router optimiert 2025-12-09 13:50:18 +01:00
config verbessertes Prompt, und chat-Router optimiert 2025-12-09 13:50:18 +01:00
docker docker/embeddings.Dockerfile aktualisiert 2025-09-04 08:00:52 +02:00
docs WP06 Dokumentation 2025-12-09 17:11:03 +01:00
Programmmanagement WP06 Dokumentation 2025-12-09 17:11:03 +01:00
schemas schemas/note.schema.json aktualisiert 2025-09-09 19:43:12 +02:00
scripts scripts/health_check_mindnet.py aktualisiert 2025-12-05 12:12:30 +01:00
tests neues Testscript 2025-12-09 15:14:38 +01:00
vault vault/leitbild/templates/obsidian_review_daily.md hinzugefügt 2025-11-01 15:08:47 +01:00
README.md test 2025-12-07 12:43:20 +01:00
requirements.txt OK 2025-12-07 16:20:16 +01:00

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.

Anmerkung: Diese Datei ist veraltet