124 lines
3.1 KiB
YAML
124 lines
3.1 KiB
YAML
version: 1.2 # Update für Smart Chunking Config
|
|
|
|
# --- CHUNKING DEFINITIONEN ---
|
|
# Hier definieren wir die technischen Strategien zentral.
|
|
chunking_profiles:
|
|
# Standard für Fließtexte (Sliding Window)
|
|
sliding_short:
|
|
strategy: sliding_window
|
|
target: 200
|
|
max: 350
|
|
overlap: [30, 50]
|
|
|
|
sliding_standard:
|
|
strategy: sliding_window
|
|
target: 400
|
|
max: 600
|
|
overlap: [50, 80]
|
|
|
|
sliding_large:
|
|
strategy: sliding_window
|
|
target: 500
|
|
max: 800
|
|
overlap: [60, 100]
|
|
|
|
# Smart Chunking für Strukturen (Harte Splits)
|
|
structured_strict:
|
|
strategy: by_heading
|
|
split_level: 2
|
|
max: 600 # Fallback Limit
|
|
target: 400 # Fallback Target bei Sub-Chunking
|
|
overlap: [50, 80] # Overlap bei Sub-Chunking
|
|
|
|
# NEU: LLM-basierte semantische Zerlegung (Chunker.py ruft semantic_analyzer.py)
|
|
semantic_llm:
|
|
strategy: semantic_llm
|
|
# Da das LLM die Längensteuerung übernimmt, dienen diese als Fallback/Empfehlung
|
|
target: 400
|
|
max: 800
|
|
|
|
defaults:
|
|
retriever_weight: 1.0
|
|
chunking_profile: sliding_standard # Fallback Profil
|
|
edge_defaults: []
|
|
|
|
types:
|
|
# --- WISSENSBAUSTEINE ---
|
|
concept:
|
|
chunking_profile: sliding_standard
|
|
retriever_weight: 0.60
|
|
edge_defaults: ["references", "related_to"]
|
|
|
|
source:
|
|
chunking_profile: sliding_standard
|
|
retriever_weight: 0.50
|
|
edge_defaults: []
|
|
|
|
glossary:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.40
|
|
edge_defaults: ["related_to"]
|
|
|
|
# --- IDENTITÄT & PERSÖNLICHKEIT ---
|
|
profile:
|
|
chunking_profile: structured_strict
|
|
retriever_weight: 0.70
|
|
edge_defaults: ["references", "related_to"]
|
|
|
|
value:
|
|
chunking_profile: structured_strict
|
|
retriever_weight: 1.00
|
|
edge_defaults: ["related_to"]
|
|
|
|
principle:
|
|
chunking_profile: structured_strict
|
|
retriever_weight: 0.95
|
|
edge_defaults: ["derived_from", "references"]
|
|
|
|
belief:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.90
|
|
edge_defaults: ["related_to"]
|
|
|
|
experience:
|
|
chunking_profile: sliding_standard
|
|
retriever_weight: 0.90
|
|
edge_defaults: ["derived_from", "references"]
|
|
|
|
# --- STRATEGIE & ENTSCHEIDUNG ---
|
|
goal:
|
|
chunking_profile: sliding_standard
|
|
retriever_weight: 0.95
|
|
edge_defaults: ["depends_on", "related_to"]
|
|
|
|
decision:
|
|
chunking_profile: structured_strict
|
|
retriever_weight: 1.00
|
|
edge_defaults: ["caused_by", "references"]
|
|
|
|
risk:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.85
|
|
edge_defaults: ["related_to", "blocks"]
|
|
|
|
milestone:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.70
|
|
edge_defaults: ["related_to", "part_of"]
|
|
|
|
# --- OPERATIV ---
|
|
project:
|
|
chunking_profile: sliding_large
|
|
retriever_weight: 0.97
|
|
edge_defaults: ["references", "depends_on"]
|
|
|
|
task:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.80
|
|
edge_defaults: ["depends_on", "part_of"]
|
|
|
|
journal:
|
|
# NEUE ZUWEISUNG: Journale profitieren am meisten von der semantischen Analyse
|
|
chunking_profile: semantic_llm
|
|
retriever_weight: 0.80
|
|
edge_defaults: ["references", "related_to"] |