__init__.py

• Pfad: /var/www/scripts/pipeline/__init__.py
• Namespace: pipeline
• Zeilen: 22 | Größe: 509 Bytes
• Geändert: 2025-12-23 22:57:42 | Gescannt: 2025-12-31 10:22:15

Code Hygiene Score: 100

• Dependencies: 100 (25%)
• LOC: 100 (20%)
• Methods: 100 (20%)
• Secrets: 100 (15%)
• Classes: 100 (10%)
• Magic Numbers: 100 (10%)

Keine Issues gefunden.

Code

"""
KI-System Document Pipeline

A Python-based document processing pipeline for:
- Text extraction from PDF, PPTX, DOCX, MD, TXT
- Semantic chunking with hierarchy preservation
- Embedding generation via Ollama (mxbai-embed-large)
- Vector storage in Qdrant
- Semantic analysis (entities, relations, taxonomy)

Usage:
    from pipeline import pipeline
    pipeline.main()

Or from command line:
    python -m pipeline scan
    python -m pipeline process
    python -m pipeline all
"""

__version__ = "1.0.0"