dbpa 0.2.0

Database Personal Assistant - An AI-powered database management system with advanced text-to-SQL capabilities

Database Personal Assistant (DBPA)

DBPA is an advanced AI-powered database management system that provides natural language interface for database operations. It uses a modular, agent-based architecture to convert natural language queries into optimized SQL, analyze database schemas, and provide intelligent suggestions.

Features

• Natural Language to SQL: Convert human language queries into optimized SQL
• Schema Analysis: Intelligent database schema analysis and optimization
• Query Templates: Dynamic generation and management of query templates
• Multi-Agent Architecture: Specialized agents for different tasks
• Vector Store: Efficient semantic search for query examples
• Multilingual Support: Process queries in multiple languages
• Security-First: Built-in security best practices
• Modern UI: Streamlit-based user interface

Installation

pip install dbpa

For development:

pip install dbpa[dev]

Quick Start

from dbpa.txt2sql.agents.schema import SchemaAnalyzer
from dbpa.txt2sql.vector_store import VectorStore

# Initialize components
analyzer = SchemaAnalyzer()
store = VectorStore()

# Analyze database schema
schema_info = analyzer.analyze_schema(
    "postgresql://user:pass@localhost/db"
)

# Generate query templates
templates = analyzer.generate_templates(schema_info)

# Store templates
store.add_examples(templates)

# Convert natural language to SQL
query = "Find all active users who registered last month"
results = store.find_similar_queries(query)
sql = results[0].sql_query

Architecture

DBPA uses a multi-agent architecture with specialized components:

Core Agents

• SchemaAnalysisAgent: Database structure analysis
• DataManagementAgent: Vector store management
• QualityAssuranceAgent: Query optimization
• TranslationAgent: Multilingual support
• MonitoringAgent: Performance tracking
• SecurityAgent: Access control

Key Components

• Vector Store: Semantic search engine
• Template Generator: Query pattern management
• Schema Analyzer: Database structure analysis
• UI Components: Streamlit interface

Documentation

• API Reference
• User Guide
• Contributing
• Security

Security

DBPA implements several security measures:

• Query sanitization
• Input validation
• Access control
• Secure credential management
• Audit logging

See our Security Guide for details.

Testing

Run the test suite:

# Unit tests
pytest tests/unit

# Integration tests
robot tests/robot/tests

# Coverage report
pytest --cov=dbpa

Contributing

We welcome contributions! Please see our Contributing Guide for details.

1. Fork the repository
2. Create your feature branch
3. Make your changes
4. Run the test suite
5. Submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

• SQLAlchemy team for the amazing database toolkit
• Sentence Transformers for vector embeddings
• Streamlit for the UI framework
• PyPI for package hosting

Contact

• GitHub: achimdehnert/dbpa
• Issues: GitHub Issues

Roadmap

• Support for more database types
• Advanced query optimization
• Enhanced multilingual capabilities
• Real-time performance monitoring
• Extended security features