Lars
0d61a9e191
All checks were successful
Deploy mindnet to llm-node / deploy (push) Successful in 3s
- Replaced 'sliding_smart_edges' with 'structured_smart_edges' for multiple types to improve data processing. - Added detection keywords for 'goal', 'concept', 'task', 'journal', 'source', 'glossary', 'person', and 'event' to enhance retrieval capabilities. - Adjusted retriever weights for consistency across types.
311 lines
9.6 KiB
YAML
311 lines
9.6 KiB
YAML
version: 2.7.0 # WP-14 Update: Dynamisierung der Ingestion-Pipeline
|
|
|
|
# ==============================================================================
|
|
# 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)
|
|
sliding_smart_edges:
|
|
strategy: sliding_window
|
|
enable_smart_edge_allocation: true
|
|
target: 400
|
|
max: 600
|
|
overlap: [50, 80]
|
|
|
|
# D. SMART STRUCTURE (Soft Split)
|
|
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)
|
|
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)
|
|
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
|
|
|
|
# ==============================================================================
|
|
# 3. INGESTION SETTINGS (WP-14 Dynamization)
|
|
# ==============================================================================
|
|
ingestion_settings:
|
|
ignore_statuses: ["system", "template", "archive", "hidden"]
|
|
default_note_type: "concept"
|
|
|
|
# ==============================================================================
|
|
# 4. SUMMARY & SCAN SETTINGS
|
|
# ==============================================================================
|
|
summary_settings:
|
|
max_summary_length: 500
|
|
pre_scan_depth: 600
|
|
|
|
# ==============================================================================
|
|
# 5. LLM SETTINGS
|
|
# ==============================================================================
|
|
llm_settings:
|
|
cleanup_patterns: ["<s>", "</s>", "[OUT]", "[/OUT]", "```json", "```"]
|
|
|
|
# ==============================================================================
|
|
# 6. TYPE DEFINITIONS
|
|
# ==============================================================================
|
|
|
|
types:
|
|
|
|
experience:
|
|
chunking_profile: structured_smart_edges
|
|
retriever_weight: 1.10
|
|
detection_keywords: ["erleben", "reagieren", "handeln", "prägen", "reflektieren"]
|
|
schema:
|
|
- "Situation (Was ist passiert?)"
|
|
- "Meine Reaktion (Was habe ich getan?)"
|
|
- "Ergebnis & Auswirkung"
|
|
- "Reflexion & Learning (Was lerne ich daraus?)"
|
|
|
|
insight:
|
|
chunking_profile: structured_smart_edges
|
|
retriever_weight: 1.20
|
|
detection_keywords: ["beobachten", "erkennen", "verstehen", "analysieren", "schlussfolgern"]
|
|
schema:
|
|
- "Beobachtung (Was sehe ich?)"
|
|
- "Interpretation (Was bedeutet das?)"
|
|
- "Bedürfnis (Was steckt dahinter?)"
|
|
- "Handlungsempfehlung"
|
|
|
|
project:
|
|
chunking_profile: structured_smart_edges
|
|
retriever_weight: 0.97
|
|
detection_keywords: ["umsetzen", "planen", "starten", "bauen", "abschließen"]
|
|
schema:
|
|
- "Mission & Zielsetzung"
|
|
- "Aktueller Status & Blockaden"
|
|
- "Nächste konkrete Schritte"
|
|
|
|
decision:
|
|
chunking_profile: structured_smart_edges_strict
|
|
retriever_weight: 1.00
|
|
detection_keywords: ["entscheiden", "wählen", "abwägen", "priorisieren", "festlegen"]
|
|
schema:
|
|
- "Kontext & Problemstellung"
|
|
- "Betrachtete Optionen"
|
|
- "Die Entscheidung"
|
|
- "Begründung"
|
|
|
|
value:
|
|
chunking_profile: structured_smart_edges_strict
|
|
retriever_weight: 1.00
|
|
detection_keywords: ["werten", "achten", "verpflichten", "bedeuten"]
|
|
schema:
|
|
- "Definition"
|
|
- "Warum mir das wichtig ist"
|
|
- "Leitsätze"
|
|
|
|
principle:
|
|
chunking_profile: structured_smart_edges_strict_L3
|
|
retriever_weight: 0.95
|
|
detection_keywords: ["leiten", "steuern", "ausrichten", "handhaben"]
|
|
schema:
|
|
- "Das Prinzip"
|
|
- "Anwendung & Beispiele"
|
|
|
|
trait:
|
|
chunking_profile: structured_smart_edges_strict
|
|
retriever_weight: 1.10
|
|
detection_keywords: ["begeistern", "können", "auszeichnen", "befähigen", "stärken"]
|
|
schema:
|
|
- "Eigenschaft / Talent"
|
|
- "Beispiele aus der Praxis"
|
|
- "Potenzial für die Zukunft"
|
|
|
|
obstacle:
|
|
chunking_profile: structured_smart_edges_strict
|
|
retriever_weight: 1.00
|
|
detection_keywords: ["blockieren", "fürchten", "vermeiden", "hindern", "zweifeln"]
|
|
schema:
|
|
- "Beschreibung der Hürde"
|
|
- "Ursprung / Auslöser"
|
|
- "Auswirkung auf Ziele"
|
|
- "Gegenstrategie"
|
|
|
|
belief:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.90
|
|
detection_keywords: ["glauben", "meinen", "annehmen", "überzeugen"]
|
|
schema:
|
|
- "Der Glaubenssatz"
|
|
- "Ursprung & Reflexion"
|
|
|
|
profile:
|
|
chunking_profile: structured_smart_edges_strict
|
|
retriever_weight: 0.70
|
|
detection_keywords: ["verkörpern", "verantworten", "agieren", "repräsentieren"]
|
|
schema:
|
|
- "Rolle / Identität"
|
|
- "Fakten & Daten"
|
|
- "Historie"
|
|
|
|
idea:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.70
|
|
detection_keywords: ["einfall", "gedanke", "potenzial", "möglichkeit"]
|
|
schema:
|
|
- "Der Kerngedanke"
|
|
- "Potenzial & Auswirkung"
|
|
- "Nächste Schritte"
|
|
|
|
skill:
|
|
chunking_profile: sliding_smart_edges
|
|
retriever_weight: 0.90
|
|
detection_keywords: ["lernen", "beherrschen", "üben", "fertigkeit", "kompetenz"]
|
|
schema:
|
|
- "Definition der Fähigkeit"
|
|
- "Aktueller Stand & Lernpfad"
|
|
- "Evidenz (Proof of Work)"
|
|
|
|
habit:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.85
|
|
detection_keywords: ["gewohnheit", "routine", "automatismus", "immer wenn"]
|
|
schema:
|
|
- "Auslöser (Trigger)"
|
|
- "Routine (Handlung)"
|
|
- "Belohnung (Reward)"
|
|
- "Strategie"
|
|
|
|
need:
|
|
chunking_profile: structured_smart_edges
|
|
retriever_weight: 1.05
|
|
detection_keywords: ["bedürfnis", "brauchen", "mangel", "erfüllung"]
|
|
schema:
|
|
- "Das Bedürfnis"
|
|
- "Zustand (Mangel vs. Erfüllung)"
|
|
- "Bezug zu Werten"
|
|
|
|
motivation:
|
|
chunking_profile: structured_smart_edges
|
|
retriever_weight: 0.95
|
|
detection_keywords: ["motivation", "antrieb", "warum", "energie"]
|
|
schema:
|
|
- "Der Antrieb"
|
|
- "Zielbezug"
|
|
- "Energiequelle"
|
|
|
|
bias:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.80
|
|
detection_keywords: ["denkfehler", "verzerrung", "vorurteil", "falle"]
|
|
schema: ["Beschreibung der Verzerrung", "Typische Situationen", "Gegenstrategie"]
|
|
|
|
state:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.60
|
|
detection_keywords: ["stimmung", "energie", "gefühl", "verfassung"]
|
|
schema: ["Aktueller Zustand", "Auslöser", "Auswirkung auf den Tag"]
|
|
|
|
boundary:
|
|
chunking_profile: structured_smart_edges
|
|
retriever_weight: 0.90
|
|
detection_keywords: ["grenze", "nein sagen", "limit", "schutz"]
|
|
schema: ["Die Grenze", "Warum sie wichtig ist", "Konsequenz bei Verletzung"]
|
|
|
|
goal:
|
|
chunking_profile: structured_smart_edges
|
|
retriever_weight: 0.95
|
|
detection_keywords: ["ziel", "zielzustand", "kpi", "zeitrahmen", "deadline", "meilenstein"]
|
|
schema: ["Zielzustand", "Zeitrahmen & KPIs", "Motivation"]
|
|
|
|
risk:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.85
|
|
detection_keywords: ["risiko", "gefahr", "bedrohung"]
|
|
schema: ["Beschreibung des Risikos", "Auswirkungen", "Gegenmaßnahmen"]
|
|
|
|
concept:
|
|
chunking_profile: structured_smart_edges
|
|
retriever_weight: 0.6
|
|
detection_keywords: ["definition", "konzept", "begriff", "modell", "rahmen", "theorie"]
|
|
schema: ["Definition", "Kontext", "Verwandte Konzepte"]
|
|
|
|
task:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.8
|
|
detection_keywords: ["aufgabe", "todo", "next_action", "erledigen", "definition_of_done", "checkliste"]
|
|
schema: ["Aufgabe", "Kontext", "Definition of Done"]
|
|
|
|
journal:
|
|
chunking_profile: sliding_standard
|
|
retriever_weight: 0.8
|
|
detection_keywords: ["journal", "tagebuch", "log", "eintrag", "reflexion", "heute"]
|
|
schema: ["Log-Eintrag", "Gedanken"]
|
|
|
|
source:
|
|
chunking_profile: sliding_standard
|
|
retriever_weight: 0.5
|
|
detection_keywords: ["quelle", "paper", "buch", "artikel", "link", "zitat", "studie"]
|
|
schema: ["Metadaten", "Zusammenfassung", "Zitate"]
|
|
|
|
glossary:
|
|
chunking_profile: sliding_short
|
|
retriever_weight: 0.4
|
|
detection_keywords: ["glossar", "begriff", "definition", "terminologie"]
|
|
schema: ["Begriff", "Definition"]
|
|
|
|
person:
|
|
chunking_profile: sliding_standard
|
|
retriever_weight: 0.5
|
|
detection_keywords: ["person", "mensch", "kontakt", "name", "beziehung", "stakeholder"]
|
|
schema: ["Profile", "Beziehung", "Kontext"]
|
|
|
|
event:
|
|
chunking_profile: sliding_standard
|
|
retriever_weight: 0.6
|
|
detection_keywords: ["ereignis", "termin", "datum", "ort", "teilnehmer", "meeting"]
|
|
schema: ["Datum & Ort", "Teilnehmer", "Ergebnisse"]
|
|
|
|
default:
|
|
chunking_profile: sliding_standard
|
|
retriever_weight: 1.0
|
|
detection_keywords: []
|
|
schema: ["Inhalt"]
|