AI-powered database assistant that helps users interact with PostgreSQL databases using natural language.
# Setup
cp app.env.example app.env
# Edit app.env with SERVER_PORT
# Run
make run# Get available models
curl http://localhost:8080/v1/models
# Chat with agent (requires API key header)
curl -X POST http://localhost:8080/v1/agent/chat \
-H "Content-Type: application/json" \
-H "X-Gemini-Api-Key: your-api-key" \
-d '{
"message": "Show me all users with their orders",
"connection_string": "postgres://user:pass@localhost:5432/mydb"
}'| Doc | Description |
|---|---|
| API | REST endpoints, authentication, examples |
| Architecture | System design, DDD layers, request flow |
| Agent | LLM agent, tools, prompt engineering |
| Security | API key handling, connection string protection |
| Development | Setup, building, contributing |
- Go 1.21+ with Google ADK
- Gemini LLM (API key via request header)
- PostgreSQL support
- Domain-Driven Design architecture
| Command | Description |
|---|---|
make run |
Run the server |
make build |
Build binary |
make test |
Run tests |
make tidy |
Install dependencies |