* feat: Implement multi-tenant architecture with tenant and knowledge base models - Added data models for tenants, knowledge bases, and related configurations. - Introduced role and permission management for users in the multi-tenant system. - Created a service layer for managing tenants and knowledge bases, including CRUD operations. - Developed a tenant-aware instance manager for LightRAG with caching and isolation features. - Added a migration script to transition existing workspace-based deployments to the new multi-tenant architecture. * chore: ignore lightrag/api/webui/assets/ directory * chore: stop tracking lightrag/api/webui/assets (ignore in .gitignore) * feat: Initialize LightRAG Multi-Tenant Stack with PostgreSQL - Added README.md for project overview, setup instructions, and architecture details. - Created docker-compose.yml to define services: PostgreSQL, Redis, LightRAG API, and Web UI. - Introduced env.example for environment variable configuration. - Implemented init-postgres.sql for PostgreSQL schema initialization with multi-tenant support. - Added reproduce_issue.py for testing default tenant access via API. * feat: Enhance TenantSelector and update related components for improved multi-tenant support * feat: Enhance testing capabilities and update documentation - Updated Makefile to include new test commands for various modes (compatibility, isolation, multi-tenant, security, coverage, and dry-run). - Modified API health check endpoint in Makefile to reflect new port configuration. - Updated QUICK_START.md and README.md to reflect changes in service URLs and ports. - Added environment variables for testing modes in env.example. - Introduced run_all_tests.sh script to automate testing across different modes. - Created conftest.py for pytest configuration, including database fixtures and mock services. - Implemented database helper functions for streamlined database operations in tests. - Added test collection hooks to skip tests based on the current MULTITENANT_MODE. * feat: Implement multi-tenant support with demo mode enabled by default - Added multi-tenant configuration to the environment and Docker setup. - Created pre-configured demo tenants (acme-corp and techstart) for testing. - Updated API endpoints to support tenant-specific data access. - Enhanced Makefile commands for better service management and database operations. - Introduced user-tenant membership system with role-based access control. - Added comprehensive documentation for multi-tenant setup and usage. - Fixed issues with document visibility in multi-tenant environments. - Implemented necessary database migrations for user memberships and legacy support. * feat(audit): Add final audit report for multi-tenant implementation - Documented overall assessment, architecture overview, test results, security findings, and recommendations. - Included detailed findings on critical security issues and architectural concerns. fix(security): Implement security fixes based on audit findings - Removed global RAG fallback and enforced strict tenant context. - Configured super-admin access and required user authentication for tenant access. - Cleared localStorage on logout and improved error handling in WebUI. chore(logs): Create task logs for audit and security fixes implementation - Documented actions, decisions, and next steps for both audit and security fixes. - Summarized test results and remaining recommendations. chore(scripts): Enhance development stack management scripts - Added scripts for cleaning, starting, and stopping the development stack. - Improved output messages and ensured graceful shutdown of services. feat(starter): Initialize PostgreSQL with AGE extension support - Created initialization scripts for PostgreSQL extensions including uuid-ossp, vector, and AGE. - Ensured successful installation and verification of extensions. * feat: Implement auto-select for first tenant and KB on initial load in WebUI - Removed WEBUI_INITIAL_STATE_FIX.md as the issue is resolved. - Added useTenantInitialization hook to automatically select the first available tenant and KB on app load. - Integrated the new hook into the Root component of the WebUI. - Updated RetrievalTesting component to ensure a KB is selected before allowing user interaction. - Created end-to-end tests for multi-tenant isolation and real service interactions. - Added scripts for starting, stopping, and cleaning the development stack. - Enhanced API and tenant routes to support tenant-specific pipeline status initialization. - Updated constants for backend URL to reflect the correct port. - Improved error handling and logging in various components. * feat: Add multi-tenant support with enhanced E2E testing scripts and client functionality * update client * Add integration and unit tests for multi-tenant API, models, security, and storage - Implement integration tests for tenant and knowledge base management endpoints in `test_tenant_api_routes.py`. - Create unit tests for tenant isolation, model validation, and role permissions in `test_tenant_models.py`. - Add security tests to enforce role-based permissions and context validation in `test_tenant_security.py`. - Develop tests for tenant-aware storage operations and context isolation in `test_tenant_storage_phase3.py`. * feat(e2e): Implement OpenAI model support and database reset functionality * Add comprehensive test suite for gpt-5-nano compatibility - Introduced tests for parameter normalization, embeddings, and entity extraction. - Implemented direct API testing for gpt-5-nano. - Validated .env configuration loading and OpenAI API connectivity. - Analyzed reasoning token overhead with various token limits. - Documented test procedures and expected outcomes in README files. - Ensured all tests pass for production readiness. * kg(postgres_impl): ensure AGE extension is loaded in session and configure graph initialization * dev: add hybrid dev helper scripts, Makefile, docker-compose.dev-db and local development docs * feat(dev): add dev helper scripts and local development documentation for hybrid setup * feat(multi-tenant): add detailed specifications and logs for multi-tenant improvements, including UX, backend handling, and ingestion pipeline * feat(migration): add generated tenant/kb columns, indexes, triggers; drop unused tables; update schema and docs * test(backward-compat): adapt tests to new StorageNameSpace/TenantService APIs (use concrete dummy storages) * chore: multi-tenant and UX updates — docs, webui, storage, tenant service adjustments * tests: stabilize integration tests + skip external services; fix multi-tenant API behavior and idempotency - gpt5_nano_compatibility: add pytest-asyncio markers, skip when OPENAI key missing, prevent module-level asyncio.run collection, add conftest - Ollama tests: add server availability check and skip markers; avoid pytest collection warnings by renaming helper classes - Graph storage tests: rename interactive test functions to avoid pytest collection - Document & Tenant routes: support external_ids for idempotency; ensure HTTPExceptions are re-raised - LightRAG core: support external_ids in apipeline_enqueue_documents and idempotent logic - Tests updated to match API changes (tenant routes & document routes) - Add logs and scripts for inspection and audit
7.5 KiB
7.5 KiB
Quick Reference Guide - LightRAG Multi-Tenant Stack
🚀 First Time Setup (5 minutes)
# 1. Enter the starter directory
cd starter
# 2. Initialize environment
make setup
# 3. Edit .env with your API keys (if needed)
# nano .env
# 4. Start all services
make up
# 5. Initialize database (wait 30 seconds after 'make up')
make init-db
# 6. Verify everything is working
make api-health
# 7. Open in browser
# http://localhost:3000
📊 Monitoring & Debugging
# View all service logs in real-time
make logs
# View only API logs
make logs-api
# Check service status
make status
# Check API health
make api-health
# Connect to database
make db-shell
🗄️ Database Operations
# Create a backup
make db-backup
# Creates: ./backups/lightrag_backup_YYYYMMDD_HHMMSS.sql
# Restore from latest backup
make db-restore
# Connect to database shell
make db-shell
# Common commands:
# \dt - list all tables
# \di - list all indexes
# \d documents - show documents table structure
# SELECT count(*) FROM documents;
# SELECT distinct tenant_id FROM documents;
# \q - quit
# WARNING: Delete and reinitialize database
make db-reset
🔄 Service Management
# Start services
make up
# Stop services
make down
# Restart services
make restart
# See what's running
make ps
# Stop and remove everything (keep data)
make down
# Complete reset (WARNING: deletes all data!)
make reset
🧪 Testing Multi-Tenant Features
# Test with curl - Insert document for tenant "acme-corp"
curl -X POST http://localhost:9621/api/v1/insert \
-H "Content-Type: application/json" \
-H "X-Tenant-Id: acme-corp" \
-H "X-KB-Id: kb-prod" \
-d '{"document": "Sample document content"}'
# Test isolation - query as different tenant
curl "http://localhost:9621/api/v1/query" \
-H "X-Tenant-Id: acme-corp" \
-H "X-KB-Id: kb-prod" \
-G --data-urlencode "param=test"
# Check isolation
curl "http://localhost:9621/api/v1/query" \
-H "X-Tenant-Id: techstart" \
-H "X-KB-Id: kb-main" \
-G --data-urlencode "param=test"
# Run test suite
make test
# Run isolation tests
make test-isolation
🔧 Configuration Cheat Sheet
Change API Port
# In .env
API_PORT=9622
# Restart
make restart
Change WebUI Port
# In .env
WEBUI_PORT=3001
# Restart
make restart
Change Database Password
# In .env
POSTGRES_PASSWORD=your_new_password
# WARNING: Database must be reset if already initialized
make db-reset
make init-db
Use Different LLM (OpenAI)
# In .env
LLM_BINDING=openai
LLM_MODEL=gpt-4o
LLM_BINDING_API_KEY=sk-...
# Restart API
docker compose -p lightrag-multitenant restart lightrag-api
Use Different Embedding Model
# In .env
EMBEDDING_BINDING=openai
EMBEDDING_MODEL=text-embedding-3-large
EMBEDDING_DIM=3072
EMBEDDING_BINDING_HOST=https://api.openai.com/v1
EMBEDDING_BINDING_API_KEY=sk-...
# Restart API
docker compose -p lightrag-multitenant restart lightrag-api
📱 Access Points
| Service | URL | Purpose |
|---|---|---|
| WebUI | http://localhost:3000 |
Upload documents, visualize graph, query |
| API | http://localhost:9621 |
RESTful API access |
| API Health | http://localhost:9621/health |
Check API status |
| PostgreSQL | localhost:5432 |
Database (use make db-shell) |
| Redis | localhost:6379 |
Cache (internal) |
🐛 Troubleshooting Quick Fixes
"Port already in use"
# Find process using port 9621
lsof -i :9621
# Kill it
kill -9 <PID>
# Or change port in .env and restart
"Database is not ready"
# Wait longer and try again
sleep 30
make init-db
# Or check logs
make logs-db
"API not responding"
# Restart API
docker compose -p lightrag-multitenant restart lightrag-api
# Check logs
make logs-api
# Check health
make api-health
"Can't connect to database"
# Check database is running
make status
# Try connecting directly
make db-shell
# Reinitialize if needed
make db-reset
make init-db
"WebUI won't load"
# Check if it's running
make status
# View logs
make logs-webui
# Rebuild if needed
docker compose -p lightrag-multitenant down
docker compose -p lightrag-multitenant build --no-cache lightrag-webui
make up
📋 Sample Tenants & KBs
Default data created by make init-db:
Tenant: acme-corp
├── kb-prod (Production knowledge base)
└── kb-dev (Development knowledge base)
Tenant: techstart
├── kb-main (Main knowledge base)
└── kb-backup (Backup knowledge base)
🔐 Multi-Tenant Isolation
How to Create Document for Specific Tenant
import requests
headers = {
"X-Tenant-Id": "acme-corp",
"X-KB-Id": "kb-prod",
"Content-Type": "application/json"
}
response = requests.post(
"http://localhost:9621/api/v1/insert",
headers=headers,
json={"document": "Your document content"}
)
How to Verify Isolation
# Insert for tenant "acme-corp"
curl -X POST http://localhost:9621/api/v1/insert \
-H "X-Tenant-Id: acme-corp" \
-H "X-KB-Id: kb-prod" \
-d '{"document": "acme-corp only"}'
# Query as "acme-corp" - should return data
curl "http://localhost:9621/api/v1/query" \
-H "X-Tenant-Id: acme-corp" \
-H "X-KB-Id: kb-prod" \
-G --data-urlencode "param=acme"
# Query as "techstart" - should NOT return data
curl "http://localhost:9621/api/v1/query" \
-H "X-Tenant-Id: techstart" \
-H "X-KB-Id: kb-main" \
-G --data-urlencode "param=acme"
# Result: Empty or different data
💾 Backup & Restore Workflow
# Before making major changes
make db-backup
# Creates: ./backups/lightrag_backup_20251120_143022.sql
# Do your work...
# If something goes wrong
make db-restore
# Or manually restore specific backup
psql -U lightrag -d lightrag_multitenant < ./backups/lightrag_backup_20251120_143022.sql
🚨 Common Error Messages
| Error | Cause | Solution |
|---|---|---|
| "Connection refused" | Services not running | make up |
| "Database does not exist" | Database not initialized | make init-db |
| "Port already in use" | Port conflict | Change port in .env |
| "Health check failed" | Service taking too long to start | Wait 30-60 seconds |
| "Permission denied" | Database permissions | make db-reset && make init-db |
| "Tenant not found" | Wrong tenant name | Check with make db-shell |
📚 Full Help
make help
Shows all available commands with descriptions.
🔗 Useful Links
- LightRAG Docs: https://github.com/HKUDS/LightRAG
- Docker Docs: https://docs.docker.com/
- PostgreSQL Docs: https://www.postgresql.org/docs/
- pgvector Docs: https://github.com/pgvector/pgvector
✅ Health Check Verification
# API Health
curl http://localhost:9621/health
# Database Connection
make db-shell
# SELECT count(*) FROM tenants;
# \q
# Redis Connection
docker compose -p lightrag-multitenant exec redis redis-cli -a redis_secure_password ping
🎯 Next Steps
- ✅ Setup Complete - Services are running
- 📤 Upload Documents - Use WebUI at http://localhost:3000
- 🔍 Create Queries - Ask questions about your documents
- 📊 Visualize KB - View knowledge graph in WebUI
- 🚀 Go to Production - Configure security, backups, monitoring
Version: 1.0
Last Updated: November 20, 2025
Status: Production Ready