ontology

2026-05-13 19:57:34 +09:00
parent 2e9204243d
commit 9e88f4c7ad
4310 changed files with 48538 additions and 905279 deletions
--- a/ontology_platform/vendored/ontocast/.env.example
+++ b/ontology_platform/vendored/ontocast/.env.example
@@ -0,0 +1,98 @@
+# ===========================================
+# OntoCast Environment Configuration
+# Copy this file to .env and update with your values
+# ===========================================
+
+# Domain Configuration
+# Used for URI generation in the knowledge graph
+CURRENT_DOMAIN=https://example.com
+
+# Server Configuration
+PORT=8999
+RECURSION_LIMIT=1000
+ESTIMATED_CHUNKS=30
+MAX_VISITS=3
+
+# LLM Configuration
+# Choose your LLM provider and configure accordingly
+
+# OpenAI Configuration (Default)
+# Available providers: openai, ollama
+LLM_PROVIDER=openai
+# Available OpenAI models: gpt-4o, gpt-4o-mini etc
+LLM_MODEL_NAME=gpt-4o-mini
+LLM_TEMPERATURE=0.0
+LLM_API_KEY=your_openai_api_key_here
+
+# Ollama Configuration (Alternative)
+# LLM_PROVIDER=ollama
+# Available Ollama models: qwen2.5, qwen2.5:72b, llama3.1, llama3.1:70b
+# LLM_MODEL_NAME=llama3.1
+# LLM_BASE_URL=http://localhost:11434
+# LLM_TEMPERATURE=0.0
+
+# Chunking Configuration
+ CHUNK_BREAKPOINT_THRESHOLD_TYPE=percentile
+ CHUNK_BREAKPOINT_THRESHOLD_AMOUNT=95.0
+ CHUNK_BUFFER_SIZE=5
+ CHUNK_MIN_SIZE=2000
+ CHUNK_MAX_SIZE=20000
+
+# Triple Store Configuration
+# Fuseki is preferred over Neo4j when both are configured
+# If no triple store is configured, OntoCast will use filesystem storage
+
+# Fuseki Configuration (Recommended)
+FUSEKI_URI=http://localhost:3030/test
+FUSEKI_AUTH=admin/admin
+FUSEKI_DATASET=dataset_name
+# FUSEKI_ONTOLOGIES_DATASET=ontologies  # Defaults to "ontologies" from constants
+
+# Neo4j Configuration (Alternative)
+NEO4J_URI=bolt://localhost:7687
+NEO4J_AUTH=neo4j/test
+NEO4J_PORT=7476
+NEO4J_BOLT_PORT=7689
+
+# Path Configuration
+ONTOCAST_WORKING_DIRECTORY=/path/to/working/directory
+ONTOCAST_ONTOLOGY_DIRECTORY=/path/to/ontology/files
+ONTOCAST_CACHE_DIR=/path/to/cache/directory
+
+# EmbeddingBasedAggregator controls
+AGG_EMBEDDING_MODEL=paraphrase-multilingual-MiniLM-L12-v2
+AGG_SIMILARITY_THRESHOLD=0.80
+
+# Optional: Web grounding for ontology render/critic (DuckDuckGo)
+WEB_SEARCH_ENABLED=false
+WEB_SEARCH_PROVIDER=duckduckgo
+WEB_SEARCH_TOP_K=3
+WEB_SEARCH_TIMEOUT_SECONDS=8.0
+WEB_SEARCH_MAX_SNIPPET_CHARS=400
+WEB_SEARCH_MAX_TOTAL_CHARS=1800
+WEB_SEARCH_ONTOLOGY_RENDER_ENABLED=true
+WEB_SEARCH_ONTOLOGY_CRITIC_ENABLED=true
+WEB_SEARCH_FACTS_RENDER_ENABLED=false
+WEB_SEARCH_FACTS_CRITIC_ENABLED=false
+WEB_SEARCH_PLANNER_ENABLED=true
+WEB_SEARCH_PLANNER_MAX_QUERIES=3
+WEB_SEARCH_PLANNER_MIN_QUERY_CHARS=12
+WEB_SEARCH_PLANNER_MIN_CONFIDENCE=0.35
+WEB_SEARCH_REUSE_EVIDENCE_ACROSS_ATTEMPT=true
+WEB_SEARCH_MIN_SNIPPET_CHARS=40
+WEB_SEARCH_ALLOWED_DOMAINS=
+WEB_SEARCH_BLOCKED_DOMAINS=
+WEB_SEARCH_REGION=wt-wt
+WEB_SEARCH_SAFESEARCH=moderate
+
+# Additional Configuration
+# Set to true to clean triple store on startup
+CLEAN=false
+# Set to true to skip ontology critique
+RENDER_MODE=ontology
+#RENDER_MODE=facts
+#RENDER_MODE=ontology_and_facts
+# Maximum number of triples allowed in ontology graph (set to empty for unlimited)
+ONTOLOGY_MAX_TRIPLES=10000
+# Set logging level (debug, info, warning, error)
+LOGGING_LEVEL=info