logo

Documentation

SQL Connectors

SQL Connectors provide powerful integration capabilities for various SQL databases, enabling seamless data access, querying, and manipulation. These connectors support multiple SQL database engines including PostgreSQL, MySQL, SQLite, and Microsoft SQL Server, making them versatile tools for your RAG applications.

1.1 SQL Query

SQL Query Configuration

SQL Query Connector Interface

Description

The SQL Query connector enables direct execution of SQL queries against your database. This connector provides fine-grained control over data retrieval and manipulation, supporting complex queries, joins, aggregations, and data transformations while maintaining security and performance optimization features.

Useful Links

Use Cases

  • Executing complex SQL queries for data analysis
  • Performing real-time data aggregation and reporting
  • Implementing custom data filtering and search operations
  • Building dynamic dashboards with live data
  • Integration with business intelligence tools

Inputs

  • Database URL: Connection string for the database (required)

    Example: postgresql://user:password@localhost:5432/mydb

  • Query: SQL query to execute (required)

    Example: SELECT * FROM users WHERE created_at > '2023-01-01'

  • Include Columns: Specify columns to include (optional)

    Example: ["id", "name", "email", "created_at"]

  • Add Error: Error handling configuration (optional)

    Example: throw_errors = true, log_errors = true

  • Passthrough: Direct query passthrough options (optional)

    Example: prepare = true, timeout = 30

Outputs

The connector returns query results in JSON format with execution metadata.

Example Output:

{
  "status": "success",
  "execution_time": "0.123 seconds",
  "rows_affected": 150,
  "results": [
    {
      "id": 1,
      "name": "John Doe",
      "email": "john.doe@example.com",
      "created_at": "2023-01-15T10:30:00Z"
    },
    {
      "id": 2,
      "name": "Jane Smith",
      "email": "jane.smith@example.com",
      "created_at": "2023-02-20T15:45:00Z"
    }
  ],
  "metadata": {
    "columns": [
      {"name": "id", "type": "integer"},
      {"name": "name", "type": "varchar"},
      {"name": "email", "type": "varchar"},
      {"name": "created_at", "type": "timestamp"}
    ],
    "query_plan": "Seq Scan on users"
  }
}

Implementation Notes

  • Use parameterized queries to prevent SQL injection
  • Implement proper error handling and logging
  • Consider query performance and optimization
  • Set appropriate timeout values for long-running queries
  • Use connection pooling for better resource management

1.2 SQL Database

Description

The SQL Database connector provides a high-level interface for managing database connections and operations. This connector handles connection pooling, transaction management, and database-specific optimizations, making it ideal for applications requiring persistent database access.

Useful Links

Use Cases

  • Managing persistent database connections
  • Handling transaction-based operations
  • Implementing connection pooling strategies
  • Supporting multiple database engines
  • Building scalable database applications

Inputs

  • URI: Database connection URI (required)

    Example: mysql://user:pass@localhost:3306/dbname

  • Connection Pool Size: Maximum number of connections (optional)

    Example: 10

  • SSL Configuration: SSL/TLS settings (optional)

    Example: mode = verify-full, ca = path/to/ca.crt

Outputs

The connector returns connection status and pool information.

Example Output:

{
  "status": "connected",
  "connection_id": "conn_12345",
  "pool_status": {
    "total_connections": 5,
    "active_connections": 2,
    "idle_connections": 3,
    "waiting_requests": 0
  },
  "database_info": {
    "engine": "PostgreSQL",
    "version": "14.5",
    "current_schema": "public",
    "server_encoding": "UTF8"
  },
  "ssl_info": {
    "ssl_in_use": true,
    "ssl_version": "TLSv1.3"
  }
}

Implementation Notes

  • Configure appropriate connection pool settings
  • Implement proper connection cleanup
  • Use SSL/TLS for secure connections
  • Monitor connection pool health
  • Handle connection timeouts and retries

Important Security Notes:

  • Use environment variables for sensitive connection details
  • Implement proper access control and user authentication
  • Regularly update database credentials
  • Monitor and audit database access patterns
  • Keep database drivers and client libraries up to date