LightRAG/docs/LOCAL_DEVELOPMENT.md
Raphael MANSUY fe9b8ec02a
tests: stabilize integration tests + skip external services; fix multi-tenant API behavior and idempotency (#4)
* 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
2025-12-04 16:04:21 +08:00

9.8 KiB

LightRAG Local Development Guide

This guide explains how to run LightRAG in hybrid development mode:

  • PostgreSQL + Redis run in Docker containers
  • API Server + WebUI run natively on your machine

This setup provides the best development experience with hot-reloading for the WebUI and easy debugging of the Python API.

🚀 Quick Start

# Start everything with one command
make dev

# Or use the script directly
./dev-start.sh

📋 Prerequisites

  • Docker - For PostgreSQL and Redis
  • Python 3.10+ - For the API server
  • Bun or npm - For the WebUI (Bun preferred for speed)
  • curl - For health checks

⚙️ Configuration

All configuration is read from the .env file at the project root.

Key Settings

# Database (Docker containers will use these)
POSTGRES_HOST=localhost
POSTGRES_PORT=15432
POSTGRES_USER=lightrag
POSTGRES_PASSWORD=lightrag123
POSTGRES_DATABASE=lightrag_multitenant

# Redis
REDIS_URI=redis://localhost:16379

# Authentication
AUTH_USER=admin
AUTH_PASS=admin123

# LLM Configuration (OpenAI example)
LLM_BINDING=openai
LLM_MODEL=gpt-4o-mini
LLM_BINDING_API_KEY=sk-your-key-here

# Embedding Configuration
EMBEDDING_BINDING=openai
EMBEDDING_MODEL=text-embedding-3-small
EMBEDDING_DIM=1536
EMBEDDING_BINDING_API_KEY=sk-your-key-here

📡 Service URLs

When the stack is running:

Service URL
WebUI http://localhost:5173
API Server http://localhost:9621
API Documentation http://localhost:9621/docs
Health Check http://localhost:9621/health

🔐 Login Credentials

Default development credentials (configurable in .env):

  • Username: admin
  • Password: admin123

🛠️ Available Commands

make dev              # Start everything
You can also auto-confirm killing any processes/containers occupying dev ports (dangerous in shared environments):

```bash
make dev CONFIRM_KILL=yes   # or
./dev-start.sh --yes

The script will then stop containers/processes using the dev ports before starting.

make dev-stop # Stop everything make dev-status # Check what's running make dev-logs # View all logs make dev-logs-api # View API logs only make dev-logs-webui # View WebUI logs only


### Database Only

If you want to run only the databases (e.g., for custom API development):

```bash
make db-only          # Start PostgreSQL + Redis
make db-stop          # Stop databases
make db-shell         # Connect to PostgreSQL CLI
make db-logs          # View database logs
make clean-db         # Delete all data (⚠️ destructive!)

Setup & Utilities

make install          # Install all dependencies
make test             # Run tests
make lint             # Run linters

📁 Files Created

File Purpose
dev-start.sh Main startup script
dev-stop.sh Graceful shutdown script
dev-status.sh Status check script
docker-compose.dev-db.yml Docker Compose for databases only
Makefile Convenient make commands

🔄 How It Works

  1. Docker Compose starts PostgreSQL (with AGE graph extension) and Redis
  2. Python runs the LightRAG API server natively
  3. Bun/npm runs the Vite dev server for the WebUI with hot-reload

This architecture means:

  • Database data persists in Docker volumes
  • API changes can be tested with a simple restart
  • WebUI changes are reflected immediately (hot-reload)

🐛 Troubleshooting

Port Already in Use

# Check what's using a port
lsof -i :9621
lsof -i :5173

# Kill the process
kill -9 <PID>

# Or let the scripts handle it
make dev-stop
make dev

Database Connection Issues

# Check if PostgreSQL is running
docker ps | grep postgres

# View PostgreSQL logs
docker logs lightrag-dev-postgres

# Connect directly
docker exec -it lightrag-dev-postgres psql -U lightrag -d lightrag_multitenant

WebUI Not Loading

# Check WebUI logs
tail -f /tmp/lightrag-dev-webui.log

# Reinstall dependencies
cd lightrag_webui && bun install

API Server Crashes

# Check API logs
tail -f /tmp/lightrag-dev-api.log

# Common issues:
# - Missing LLM_BINDING_API_KEY in .env
# - Database not ready yet (wait a few seconds)
# - Python dependencies missing (run: pip install -e .)

🔧 Advanced: Manual Start

If you prefer to run services manually:

# 1. Start databases
docker compose -f docker-compose.dev-db.yml up -d

# 2. Start API server (in one terminal)
python -m lightrag.api.lightrag_server --host 0.0.0.0 --port 9621

# 3. Start WebUI (in another terminal)
cd lightrag_webui
VITE_API_BASE_URL=http://localhost:9621 bun run dev

📊 Architecture Diagram

┌─────────────────────────────────────────────────────────────────┐
│                        Your Machine                              │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  ┌─────────────────┐        ┌─────────────────────────────────┐ │
│  │   WebUI (Vite)  │◄──────►│      LightRAG API Server       │ │
│  │   localhost:5173│        │      localhost:9621            │ │
│  │   (Native)      │        │      (Native Python)           │ │
│  └─────────────────┘        └──────────────┬──────────────────┘ │
│                                            │                     │
│  ┌─────────────────────────────────────────┴───────────────────┐ │
│  │                     Docker                                   │ │
│  │  ┌─────────────────────┐    ┌─────────────────────┐         │ │
│  │  │    PostgreSQL       │    │       Redis         │         │ │
│  │  │    localhost:15432  │    │    localhost:16379  │         │ │
│  │  │    + AGE Graph Ext  │    │                     │         │ │
│  │  └─────────────────────┘    └─────────────────────┘         │ │
│  └─────────────────────────────────────────────────────────────┘ │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

🆚 Comparison with Other Setups

Feature make dev (Hybrid) starter/make up (Full Docker) scripts/start-dev-stack.sh
Databases Docker Docker Docker
API Server Native Docker Native
WebUI Native Docker Native
Hot Reload Yes No Yes
Uses root .env Yes Uses starter/.env Hardcoded
Easy debugging Yes Harder Yes

🔀 Multi-Tenant Development & Testing

LightRAG supports multi-tenant operation with workspace isolation. Here's how to test the multi-tenant features:

Running Multi-Tenant Tests

# Run the isolation test suite
./e2e/run_isolation_test.sh

# Run specific multi-tenant tests
python -m pytest tests/test_idempotency.py -v
python -m pytest e2e/test_multitenant_isolation.py -v

Testing Tenant State Management

The WebUI includes state management features for multi-tenant UX:

  1. URL State Sync: Navigate to documents with URL parameters:

    http://localhost:5173/documents#page=2&filter=processed
    
  2. Session Persistence: Tenant selection persists in session storage

    • Switch between tenants without losing document page state
    • "Last selected" hint shows on tenant selection page
  3. Cross-Tab Sync: Changes propagate across browser tabs via storage events

Testing Idempotent Document Ingestion

# Test with curl - first insertion
curl -X POST "http://localhost:9621/documents/text" \
  -H "Content-Type: application/json" \
  -H "X-Tenant-ID: test-tenant" \
  -H "X-KB-ID: kb-1" \
  -H "Authorization: Bearer your-token" \
  -d '{
    "text": "Document content here",
    "external_id": "doc-unique-id-123"
  }'

# Second insertion with same external_id returns existing document (no duplicate)
curl -X POST "http://localhost:9621/documents/text" \
  -H "Content-Type: application/json" \
  -H "X-Tenant-ID: test-tenant" \
  -H "X-KB-ID: kb-1" \
  -H "Authorization: Bearer your-token" \
  -d '{
    "text": "Different content - will be ignored",
    "external_id": "doc-unique-id-123"
  }'

Multi-Tenant Architecture

See Multi-Tenant UX Documentation for:

  • State management architecture
  • URL synchronization patterns
  • Idempotency implementation details
  • API examples

📝 Notes

  • Log files are stored in /tmp/lightrag-dev-*.log
  • PID files are stored in /tmp/lightrag-dev-*.pid
  • Database data is persisted in Docker volumes (lightrag_dev_postgres_data, lightrag_dev_redis_data)