7689409950
- Complete Mem0 OSS integration with hybrid datastore - PostgreSQL + pgvector for vector storage - Neo4j 5.18 for graph relationships - Google Gemini embeddings integration - Comprehensive monitoring with correlation IDs - Real-time statistics and performance tracking - Production-grade observability features - Clean repository with no exposed secrets
39 lines
No EOL
1.5 KiB
Text
39 lines
No EOL
1.5 KiB
Text
# API Configuration - UPDATE THESE WITH YOUR VALUES
|
|
OPENAI_API_KEY=sk-your-openai-api-key-here
|
|
OPENAI_COMPAT_API_KEY=sk-your-openai-compatible-api-key-here
|
|
OPENAI_BASE_URL=https://your-openai-compatible-endpoint.com/v1
|
|
EMBEDDER_API_KEY=AIzaSy-your-google-gemini-api-key-here
|
|
|
|
# Database Configuration
|
|
POSTGRES_DB=mem0_db
|
|
POSTGRES_USER=mem0_user
|
|
POSTGRES_PASSWORD=mem0_password
|
|
POSTGRES_HOST=postgres
|
|
POSTGRES_PORT=5432
|
|
|
|
# Neo4j Configuration
|
|
NEO4J_AUTH=neo4j/mem0_neo4j_password
|
|
NEO4J_URI=bolt://neo4j:7687
|
|
NEO4J_USERNAME=neo4j
|
|
NEO4J_PASSWORD=mem0_neo4j_password
|
|
|
|
# Application Configuration
|
|
BACKEND_PORT=8000
|
|
FRONTEND_PORT=3000
|
|
LOG_LEVEL=INFO
|
|
CORS_ORIGINS=http://localhost:3000
|
|
|
|
# Model Configuration - Intelligent Routing
|
|
# These models are automatically selected based on task complexity
|
|
DEFAULT_MODEL=claude-sonnet-4 # General purpose model
|
|
EXTRACTION_MODEL=claude-sonnet-4 # Memory extraction and processing
|
|
FAST_MODEL=o4-mini # Simple/quick responses
|
|
ANALYTICAL_MODEL=gemini-2.5-pro # Analysis and comparison tasks
|
|
REASONING_MODEL=claude-sonnet-4 # Complex reasoning tasks
|
|
EXPERT_MODEL=o3 # Expert-level comprehensive analysis
|
|
|
|
# IMPORTANT NOTES:
|
|
# - Ensure all models are available on your OpenAI-compatible endpoint
|
|
# - Verify model availability: curl -H "Authorization: Bearer $API_KEY" $BASE_URL/v1/models
|
|
# - Neo4j must be version 5.18+ for vector.similarity.cosine() function
|
|
# - Ollama must be running locally with nomic-embed-text:latest model |