Metadata-Version: 2.4
Name: agentium
Version: 1.1.0
Summary: A comprehensive toolkit for AI agent development and workflow orchestration with Gemini AI integration
Home-page: https://github.com/RNSsanjay/Agentium-Python-Library
Author: Sanjay N
Author-email: 2005sanjaynrs@gmail.com
Keywords: ai,agents,langchain,langgraph,gemini,nlp,automation,workflow,google-ai
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Text Processing :: Linguistic
Classifier: Topic :: Communications
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: numpy>=1.21.0
Requires-Dist: pandas>=1.3.0
Requires-Dist: requests>=2.25.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: typing-extensions>=4.0.0
Requires-Dist: python-dotenv>=0.19.0
Requires-Dist: asyncio-throttle>=1.0.0
Requires-Dist: aiohttp>=3.8.0
Requires-Dist: openai>=1.0.0
Requires-Dist: anthropic>=0.3.0
Requires-Dist: google-generativeai>=0.3.0
Requires-Dist: tiktoken>=0.4.0
Requires-Dist: beautifulsoup4>=4.9.0
Requires-Dist: lxml>=4.6.0
Requires-Dist: PyYAML>=6.0
Requires-Dist: Jinja2>=3.0.0
Requires-Dist: redis>=4.0.0
Requires-Dist: sqlite3
Requires-Dist: logging
Requires-Dist: json5>=0.9.0
Requires-Dist: dateutil>=2.8.0
Requires-Dist: textstat>=0.7.0
Requires-Dist: scikit-learn>=1.0.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: pytest-cov>=4.0; extra == "dev"
Requires-Dist: black>=22.0; extra == "dev"
Requires-Dist: flake8>=5.0; extra == "dev"
Requires-Dist: mypy>=0.991; extra == "dev"
Provides-Extra: langchain
Requires-Dist: langchain>=0.1.0; extra == "langchain"
Requires-Dist: langchain-community>=0.0.10; extra == "langchain"
Provides-Extra: langgraph
Requires-Dist: langgraph>=0.0.20; extra == "langgraph"
Provides-Extra: ai
Requires-Dist: google-generativeai>=0.3.0; extra == "ai"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# Agentium - AI Agent Development Toolkit

[![PyPI version](https://badge.fury.io/py/agentium.svg)](https://badge.fury.io/py/agentium)
[![Python Support](https://img.shields.io/pypi/pyversions/agentium.svg)](https://pypi.org/project/agentium/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

A comprehensive Python library designed for AI agent development and workflow orchestration. Agentium provides a rich set of tools and utilities that seamlessly integrate with popular AI frameworks like LangChain, LangGraph, and now features built-in **Google Gemini API integration**.

## New Features

- **Google Gemini Integration** - Built-in support for Gemini Pro, Gemini 1.5 Pro, and Gemini 1.5 Flash
- **Model Selection** - Easy switching between different AI models
- **Enhanced AI Processing** - All core features now support AI-enhanced processing
- **Advanced Configuration** - Comprehensive model and processing configuration

## Features

- **Condense**: Intelligent content condensation and compression with AI enhancement
- **Optimizer**: Refine text, code, and workflows for better performance
- **Rearranger**: Organize and restructure content logically
- **Extractor**: Extract structured information from various data sources
- **Communicator**: Send messages and notifications across platforms
- **Translator**: Multi-language translation with AI-powered tone adaptation
- **Insight Generator**: Generate actionable insights from data using AI
- **Workflow Helper**: Orchestrate complex tasks and triggers
- **Template Manager**: Standardize outputs with customizable templates
- **Memory Helper**: Context storage and retrieval system
- **Custom Summarizer**: Create AI-enhanced summaries tailored to specific needs
- **Logger Utils**: Track and debug operations with detailed logging
- **Gemini Integration**: Native Google Gemini API support with model selection

## Installation

```bash
pip install agentium
```

### With AI Enhancement (Recommended):

```bash
# For full AI capabilities including Gemini
pip install agentium google-generativeai

# For LangChain integration
pip install agentium[langchain]

# For LangGraph integration
pip install agentium[langgraph]

# For development
pip install agentium[dev]
```

## API Key Setup

### Getting Your Google Gemini API Key

To use the AI-enhanced features, you need a Google Gemini API key:

1. **Visit Google AI Studio**
   - Go to https://makersuite.google.com/app/apikey
   - Sign in with your Google account

2. **Create API Key**
   - Click "Create API Key"
   - Choose "Create API key in new project" or select an existing project
   - Copy the generated API key and save it securely

3. **Set Up Your API Key** (Choose one method):

   **Method 1: Environment Variable (Recommended)**
   ```bash
   # Windows (Command Prompt)
   set GEMINI_API_KEY=your_api_key_here
   
   # Windows (PowerShell)
   $env:GEMINI_API_KEY="your_api_key_here"
   
   # Linux/Mac
   export GEMINI_API_KEY=your_api_key_here
   ```

   **Method 2: In Your Python Code**
   ```python
   from agentium.integrations.gemini import GeminiIntegration
   
   # Initialize with API key directly
   gemini = GeminiIntegration(api_key="your_api_key_here")
   ```

   **Method 3: Using .env File**
   ```bash
   # Create a .env file in your project root
   echo "GEMINI_API_KEY=your_api_key_here" > .env
   ```
   ```python
   import os
   from dotenv import load_dotenv
   
   load_dotenv()
   api_key = os.getenv('GEMINI_API_KEY')
   ```

### Important Security Notes

- **Never commit API keys to version control**
- **Use environment variables in production**
- **Keep your API keys secure and private**
- **Monitor your API usage in Google Cloud Console**

## Quick Start

```python
from agentium import Agentium
from agentium.integrations.gemini import GeminiIntegration

# Initialize with Gemini AI enhancement
agentium = Agentium()
gemini = GeminiIntegration(api_key="your-gemini-api-key")

# Basic text processing
condensed_text = agentium.condenser.condense("Your long text here...")
optimized_text = agentium.optimizer.optimize(condensed_text)

# AI-enhanced processing
enhanced_summary = gemini.enhance_condenser(
    text="Complex document content",
    style="executive-summary"
)

# Workflow orchestration
workflow_result = agentium.workflow_helper.process_workflow({
    "input": "Data to process",
    "steps": ["condense", "optimize", "extract"],
    "ai_enhanced": True
})

print(f"Processed result: {workflow_result}")
```

## Configuration with Gemini

```python
from agentium.integrations.gemini import GeminiIntegration, GeminiConfig

# Configure Gemini integration
config = GeminiConfig(
    model_name="gemini-1.5-pro",
    temperature=0.7,
    max_tokens=1000
)

gemini = GeminiIntegration(
    api_key="your-api-key",
    config=config
)

# Use with any Agentium feature
enhanced_insights = gemini.enhance_insights(
    data="Your data here",
    context="Financial analysis",
    insight_type="trend_analysis"
)
```

## Sample Projects

The `sample_projects/` directory contains 5 comprehensive examples demonstrating all Agentium features:

### 1. Content Processing Pipeline (`content_pipeline.py`)
Advanced document processing system with AI-enhanced content analysis, multi-format support, and intelligent workflow orchestration.

**Features Demonstrated:**
- Content condensation and optimization
- Multi-language translation with tone adaptation  
- Template-based report generation
- Memory management and context storage
- Gemini AI enhancement for superior content quality

```python
# Example usage
pipeline = ContentProcessingPipeline()
result = pipeline.process_document("document.pdf", output_format="executive-summary")
```

### 2. Multilingual News Analyzer (`news_analyzer.py`)
Real-time news analysis system with sentiment analysis, trend detection, and multi-language support.

**Features Demonstrated:**
- Real-time content extraction and processing
- Advanced insight generation with trend analysis
- Multi-language translation and sentiment analysis
- Workflow orchestration for news processing
- AI-enhanced content understanding

```python
# Example usage
analyzer = NewsAnalyzer()
analysis = analyzer.analyze_news_feed("https://news-feed-url", languages=["en", "es", "fr"])
```

### 3. Data Intelligence Dashboard (`data_dashboard.py`)
Comprehensive data analysis and visualization system with AI-powered insights.

**Features Demonstrated:**
- Advanced data extraction and processing
- AI-enhanced insight generation
- Real-time data visualization
- Memory-based context management
- Intelligent report generation

```python
# Example usage
dashboard = DataIntelligenceDashboard()
insights = dashboard.generate_intelligence_report("sales_data.csv")
```

### 4. Automated Report Generator (`report_generator.py`)
Professional report generation system with AI-enhanced content creation and multi-format output.

**Features Demonstrated:**
- Template-based report generation
- AI-enhanced content optimization
- Multi-format output (PDF, HTML, Markdown)
- Workflow automation for report creation
- Memory management for report templates

```python
# Example usage
generator = AutomatedReportGenerator()
report = generator.generate_comprehensive_report("project_data", "quarterly-report")
```

### 5. Smart Communication Hub (`communication_hub.py`)
Intelligent communication orchestration system with multi-channel messaging and workflow automation.

**Features Demonstrated:**
- Multi-channel communication management
- Workflow-based message orchestration
- AI-enhanced content optimization for different channels
- Memory management for communication history
- Intelligent message routing and optimization

```python
# Example usage
hub = SmartCommunicationHub()
result = hub.process_and_distribute_message(
    "Important announcement",
    channels=["email", "slack", "teams"],
    ai_enhanced=True
)
```

## Streamlit Demo

Try the interactive demo to explore all Agentium features:

```bash
# Install Streamlit
pip install streamlit plotly pandas

# Run the demo
streamlit run sample_projects/agentium_streamlit_demo.py
```

The demo includes:
- Interactive feature testing
- Real-time processing examples
- AI model selection interface
- Processing history and export capabilities
- Comprehensive feature demonstrations

## Framework Integration

### LangChain Integration

```python
from agentium.integrations.langchain import AgentiumTool
from langchain.agents import initialize_agent

# Create Agentium tools for LangChain
tools = AgentiumTool.create_all_tools()
agent = initialize_agent(tools, llm, agent_type="zero-shot-react-description")
```

### LangGraph Integration

```python
from agentium.integrations.langgraph import AgentiumNode
from langgraph import Graph

# Add Agentium nodes to LangGraph
graph = Graph()
graph.add_node("condenser", AgentiumNode.condenser_node)
graph.add_node("optimizer", AgentiumNode.optimizer_node)
```

## Documentation

For detailed documentation and examples, visit [our documentation site](https://agentium.readthedocs.io).

## Contributing

We welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

## Support

If you encounter any issues or have questions, please [open an issue](https://github.com/RNSsanjay/Agentium-Python-Library/issues) on GitHub.
