3ec2059470
Issues resolved: - #68: pgvector Setup * Added pgvector vector index migration for knowledge_embeddings * Vector index uses HNSW algorithm with cosine distance * Optimized for 1536-dimension OpenAI embeddings - #69: Embedding Generation Pipeline * Created EmbeddingService with OpenAI integration * Automatic embedding generation on entry create/update * Batch processing endpoint for existing entries * Async generation to avoid blocking API responses * Content preparation with title weighting - #70: Semantic Search API * POST /api/knowledge/search/semantic - pure vector search * POST /api/knowledge/search/hybrid - RRF combined search * POST /api/knowledge/embeddings/batch - batch generation * Comprehensive test coverage * Full documentation in docs/SEMANTIC_SEARCH.md Technical details: - Uses OpenAI text-embedding-3-small model (1536 dims) - HNSW index for O(log n) similarity search - Reciprocal Rank Fusion for hybrid search - Graceful degradation when OpenAI not configured - Async embedding generation for performance Configuration: - Added OPENAI_API_KEY to .env.example - Optional feature - disabled if API key not set - Falls back to keyword search in hybrid mode
147 lines
4.5 KiB
Plaintext
147 lines
4.5 KiB
Plaintext
# ==============================================
|
|
# Mosaic Stack Environment Configuration
|
|
# ==============================================
|
|
# Copy this file to .env and customize for your environment
|
|
|
|
# ======================
|
|
# Application Ports
|
|
# ======================
|
|
API_PORT=3001
|
|
API_HOST=0.0.0.0
|
|
WEB_PORT=3000
|
|
|
|
# ======================
|
|
# Web Configuration
|
|
# ======================
|
|
NEXT_PUBLIC_API_URL=http://localhost:3001
|
|
|
|
# ======================
|
|
# PostgreSQL Database
|
|
# ======================
|
|
# SECURITY: Change POSTGRES_PASSWORD to a strong random password in production
|
|
DATABASE_URL=postgresql://mosaic:REPLACE_WITH_SECURE_PASSWORD@localhost:5432/mosaic
|
|
POSTGRES_USER=mosaic
|
|
POSTGRES_PASSWORD=REPLACE_WITH_SECURE_PASSWORD
|
|
POSTGRES_DB=mosaic
|
|
POSTGRES_PORT=5432
|
|
|
|
# PostgreSQL Performance Tuning (Optional)
|
|
POSTGRES_SHARED_BUFFERS=256MB
|
|
POSTGRES_EFFECTIVE_CACHE_SIZE=1GB
|
|
POSTGRES_MAX_CONNECTIONS=100
|
|
|
|
# ======================
|
|
# Valkey Cache (Redis-compatible)
|
|
# ======================
|
|
VALKEY_URL=redis://localhost:6379
|
|
VALKEY_PORT=6379
|
|
VALKEY_MAXMEMORY=256mb
|
|
|
|
# Knowledge Module Cache Configuration
|
|
# Set KNOWLEDGE_CACHE_ENABLED=false to disable caching (useful for development)
|
|
KNOWLEDGE_CACHE_ENABLED=true
|
|
# Cache TTL in seconds (default: 300 = 5 minutes)
|
|
KNOWLEDGE_CACHE_TTL=300
|
|
|
|
# ======================
|
|
# Authentication (Authentik OIDC)
|
|
# ======================
|
|
# Authentik Server URLs
|
|
OIDC_ISSUER=https://auth.example.com/application/o/mosaic-stack/
|
|
OIDC_CLIENT_ID=your-client-id-here
|
|
OIDC_CLIENT_SECRET=your-client-secret-here
|
|
OIDC_REDIRECT_URI=http://localhost:3001/auth/callback
|
|
|
|
# Authentik PostgreSQL Database
|
|
AUTHENTIK_POSTGRES_USER=authentik
|
|
AUTHENTIK_POSTGRES_PASSWORD=REPLACE_WITH_SECURE_PASSWORD
|
|
AUTHENTIK_POSTGRES_DB=authentik
|
|
|
|
# Authentik Configuration
|
|
# CRITICAL: Generate a random secret key with at least 50 characters
|
|
# Example: openssl rand -base64 50
|
|
AUTHENTIK_SECRET_KEY=REPLACE_WITH_RANDOM_SECRET_MINIMUM_50_CHARS
|
|
AUTHENTIK_ERROR_REPORTING=false
|
|
# SECURITY: Change bootstrap password immediately after first login
|
|
AUTHENTIK_BOOTSTRAP_PASSWORD=REPLACE_WITH_SECURE_PASSWORD
|
|
AUTHENTIK_BOOTSTRAP_EMAIL=admin@localhost
|
|
AUTHENTIK_COOKIE_DOMAIN=.localhost
|
|
|
|
# Authentik Ports
|
|
AUTHENTIK_PORT_HTTP=9000
|
|
AUTHENTIK_PORT_HTTPS=9443
|
|
|
|
# ======================
|
|
# JWT Configuration
|
|
# ======================
|
|
# CRITICAL: Generate a random secret key with at least 32 characters
|
|
# Example: openssl rand -base64 32
|
|
JWT_SECRET=REPLACE_WITH_RANDOM_SECRET_MINIMUM_32_CHARS
|
|
JWT_EXPIRATION=24h
|
|
|
|
# ======================
|
|
# Ollama (Optional AI Service)
|
|
# ======================
|
|
# Set OLLAMA_ENDPOINT to use local or remote Ollama
|
|
# For bundled Docker service: http://ollama:11434
|
|
# For external service: http://your-ollama-server:11434
|
|
OLLAMA_ENDPOINT=http://ollama:11434
|
|
OLLAMA_PORT=11434
|
|
|
|
# ======================
|
|
# OpenAI API (For Semantic Search)
|
|
# ======================
|
|
# OPTIONAL: Semantic search requires an OpenAI API key
|
|
# Get your API key from: https://platform.openai.com/api-keys
|
|
# If not configured, semantic search endpoints will return an error
|
|
# OPENAI_API_KEY=sk-...
|
|
|
|
# ======================
|
|
# Application Environment
|
|
# ======================
|
|
NODE_ENV=development
|
|
|
|
# ======================
|
|
# Docker Compose Profiles
|
|
# ======================
|
|
# Uncomment to enable optional services:
|
|
# COMPOSE_PROFILES=authentik,ollama # Enable both Authentik and Ollama
|
|
# COMPOSE_PROFILES=full # Enable all optional services
|
|
# COMPOSE_PROFILES=authentik # Enable only Authentik
|
|
# COMPOSE_PROFILES=ollama # Enable only Ollama
|
|
# COMPOSE_PROFILES=traefik-bundled # Enable bundled Traefik reverse proxy
|
|
|
|
# ======================
|
|
# Traefik Reverse Proxy
|
|
# ======================
|
|
# TRAEFIK_MODE options:
|
|
# - bundled: Use bundled Traefik (requires traefik-bundled profile)
|
|
# - upstream: Connect to external Traefik instance
|
|
# - none: Direct port exposure without reverse proxy (default)
|
|
TRAEFIK_MODE=none
|
|
|
|
# Domain configuration for Traefik routing
|
|
MOSAIC_API_DOMAIN=api.mosaic.local
|
|
MOSAIC_WEB_DOMAIN=mosaic.local
|
|
MOSAIC_AUTH_DOMAIN=auth.mosaic.local
|
|
|
|
# External Traefik network name (for upstream mode)
|
|
# Must match the network name of your existing Traefik instance
|
|
TRAEFIK_NETWORK=traefik-public
|
|
|
|
# TLS/SSL Configuration
|
|
TRAEFIK_TLS_ENABLED=true
|
|
# For Let's Encrypt (production):
|
|
TRAEFIK_ACME_EMAIL=admin@example.com
|
|
# For self-signed certificates (development), leave TRAEFIK_ACME_EMAIL empty
|
|
|
|
# Traefik Dashboard (bundled mode only)
|
|
TRAEFIK_DASHBOARD_ENABLED=true
|
|
TRAEFIK_DASHBOARD_PORT=8080
|
|
|
|
# ======================
|
|
# Logging & Debugging
|
|
# ======================
|
|
LOG_LEVEL=info
|
|
DEBUG=false
|