version: 2.6.0 # Final WP-15 Config: Smart Edges & Strict/Soft Chunking # ============================================================================== # 1. CHUNKING PROFILES # ============================================================================== chunking_profiles: # A. SHORT & FAST sliding_short: strategy: sliding_window enable_smart_edge_allocation: false target: 200 max: 350 overlap: [30, 50] # B. STANDARD & FAST sliding_standard: strategy: sliding_window enable_smart_edge_allocation: false target: 450 max: 650 overlap: [50, 100] # C. SMART FLOW (Text-Fluss) # Nutzt Sliding Window, aber mit LLM-Kanten-Analyse. sliding_smart_edges: strategy: sliding_window enable_smart_edge_allocation: true target: 400 max: 600 overlap: [50, 80] # D. SMART STRUCTURE (Soft Split) # Trennt bevorzugt an H2, fasst aber kleine Abschnitte zusammen ("Soft Mode"). structured_smart_edges: strategy: by_heading enable_smart_edge_allocation: true split_level: 2 strict_heading_split: false max: 600 target: 400 overlap: [50, 80] # E. SMART STRUCTURE STRICT (H2 Hard Split) # Trennt ZWINGEND an jeder H2. # Verhindert, dass "Vater" und "Partner" (Profile) oder Werte verschmelzen. structured_smart_edges_strict: strategy: by_heading enable_smart_edge_allocation: true split_level: 2 strict_heading_split: true # Hard Mode max: 600 target: 400 overlap: [50, 80] # F. SMART STRUCTURE DEEP (H3 Hard Split + Merge-Check) # Spezialfall für "Leitbild Prinzipien": # - Trennt H1, H2, H3 hart. # - Aber: Merged "leere" H2 (Tier 2) mit der folgenden H3 (MP1). structured_smart_edges_strict_L3: strategy: by_heading enable_smart_edge_allocation: true split_level: 3 strict_heading_split: true max: 600 target: 400 overlap: [50, 80] # ============================================================================== # 2. DEFAULTS # ============================================================================== defaults: retriever_weight: 1.0 chunking_profile: sliding_standard edge_defaults: [] # ============================================================================== # 3. TYPE DEFINITIONS # ============================================================================== types: # --- KERNTYPEN --- experience: chunking_profile: sliding_smart_edges retriever_weight: 0.90 edge_defaults: ["derived_from", "references"] detection_keywords: ["passiert", "erlebt", "gefühl", "situation", "reaktion"] schema: - "Situation (Was ist passiert?)" - "Meine Reaktion (Was habe ich getan?)" - "Ergebnis & Auswirkung" - "Reflexion & Learning (Was lerne ich daraus?)" project: chunking_profile: sliding_smart_edges retriever_weight: 0.97 edge_defaults: ["references", "depends_on"] detection_keywords: ["projekt", "vorhaben", "ziel ist", "planen", "starten"] schema: - "Mission & Zielsetzung" - "Aktueller Status & Blockaden" - "Nächste konkrete Schritte" decision: # Strict, damit jede Entscheidung atomar bleibt chunking_profile: structured_smart_edges_strict retriever_weight: 1.00 edge_defaults: ["caused_by", "references"] detection_keywords: ["entschieden", "wahl", "optionen", "alternativen", "adr"] schema: - "Kontext & Problemstellung" - "Betrachtete Optionen" - "Die Entscheidung" - "Begründung" # --- PERSÖNLICHKEIT & IDENTITÄT --- value: # Strict, damit Werte nicht verschwimmen chunking_profile: structured_smart_edges_strict retriever_weight: 1.00 edge_defaults: ["related_to"] detection_keywords: ["wert", "wichtig ist", "moral", "ethik"] schema: ["Definition", "Warum mir das wichtig ist", "Leitsätze"] principle: # L3 Strict für P3/P3a und Tier2/MP1 Logik chunking_profile: structured_smart_edges_strict_L3 retriever_weight: 0.95 edge_defaults: ["derived_from", "references"] detection_keywords: ["prinzip", "regel", "grundsatz", "leitlinie"] schema: ["Das Prinzip", "Anwendung & Beispiele"] belief: chunking_profile: sliding_short retriever_weight: 0.90 edge_defaults: ["related_to"] schema: ["Der Glaubenssatz", "Ursprung & Reflexion"] profile: # Strict: Jede Rolle (H2) muss ein eigener Chunk sein chunking_profile: structured_smart_edges_strict retriever_weight: 0.70 edge_defaults: ["references", "related_to"] schema: ["Rolle / Identität", "Fakten & Daten", "Historie"] # --- STRATEGIE & RISIKO --- goal: chunking_profile: sliding_smart_edges retriever_weight: 0.95 edge_defaults: ["depends_on", "related_to"] schema: ["Zielzustand", "Zeitrahmen & KPIs", "Motivation"] risk: chunking_profile: sliding_short retriever_weight: 0.85 edge_defaults: ["related_to", "blocks"] detection_keywords: ["risiko", "gefahr", "bedrohung"] schema: ["Beschreibung des Risikos", "Auswirkungen", "Gegenmaßnahmen"] # --- BASIS & WISSEN --- concept: chunking_profile: sliding_smart_edges retriever_weight: 0.60 edge_defaults: ["references", "related_to"] schema: ["Definition", "Kontext", "Verwandte Konzepte"] task: chunking_profile: sliding_short retriever_weight: 0.80 edge_defaults: ["depends_on", "part_of"] schema: ["Aufgabe", "Kontext", "Definition of Done"] journal: chunking_profile: sliding_standard retriever_weight: 0.80 edge_defaults: ["references", "related_to"] schema: ["Log-Eintrag", "Gedanken"] source: chunking_profile: sliding_standard retriever_weight: 0.50 edge_defaults: [] schema: ["Metadaten", "Zusammenfassung", "Zitate"] glossary: chunking_profile: sliding_short retriever_weight: 0.40 edge_defaults: ["related_to"] schema: ["Begriff", "Definition"] person: chunking_profile: sliding_standard retriever_weight: 0.50 edge_defaults: ["related_to"] schema: ["Rolle", "Beziehung", "Kontext"] event: chunking_profile: sliding_standard retriever_weight: 0.60 edge_defaults: ["related_to"] schema: ["Datum & Ort", "Teilnehmer", "Ergebnisse"] # --- FALLBACK --- default: chunking_profile: sliding_standard retriever_weight: 1.00 edge_defaults: ["references"] schema: ["Inhalt"]