ignis-lfx 0.1.0

IGNIS LFX - Langflow Executor for advanced flow execution and component management

IGNIS LFX - Langflow Executor

IGNIS LFX is a powerful Python package that provides execution capabilities for Langflow flows with advanced component management, memory handling, and flow execution features.

Features

• 🚀 Flow Execution: Execute Langflow flows programmatically with full control
• 💾 Memory Management: Built-in session-based memory management for conversational flows
• 🔧 Component System: Access and utilize extensive component library for flow building
• 📊 MCP Integration: Model Context Protocol support for advanced integrations
• 🛡️ Type Safety: Full type hints for better IDE support and development experience
• ⚡ FastAPI Integration: Ready-to-use FastAPI integration for web services
• 🔌 Multi-LLM Support: Support for OpenAI, Ollama, IBM LangChain, and more

Installation

Install ignis_lfx from PyPI:

pip install ignis_lfx

Or with optional dependencies:

# Development tools and testing
pip install ignis_lfx[dev]

# Documentation tools
pip install ignis_lfx[docs]

# All optional dependencies
pip install ignis_lfx[dev,docs]

Quick Start

Basic Flow Execution

from ignis_lfx import execute_flow

# Load and execute a flow
result = execute_flow(
    flow_name="my_flow.json",
    input_data={"question": "What is Python?"}
)

print(result)

FastAPI Integration

from fastapi import FastAPI
from ignis_lfx import execute_flow

app = FastAPI()

@app.post("/execute")
async def run_flow(input_data: dict):
    result = await execute_flow(
        flow_name="assistant.json",
        input_data=input_data
    )
    return {"result": result}

Memory-Based Chat

from ignis_lfx.memory import SessionMemory

# Initialize session memory
memory = SessionMemory(session_id="user_123")

# Store conversation history
memory.save("user", "Hello, how are you?")
memory.save("assistant", "I'm doing great! How can I help?")

# Load conversation history
history = memory.load("user_123")

Configuration

Environment Variables

# LFX Configuration
LANGFLOW_DEV=false
LFX_API_KEY=your_api_key_here
LFX_BASE_URL=http://localhost:7860

# LLM Configuration
OPENAI_API_KEY=sk-...
OLLAMA_BASE_URL=http://localhost:11434

Configuration File (ignis_lfx_config.json)

{
  "LFX_URL": "http://localhost:7860",
  "LFX_API_KEY": "your-api-key",
  "DEFAULT_FLOW": "default.json",
  "MEMORY_TYPE": "session",
  "DEBUG": false
}

Project Structure

ignis_lfx/
├── __init__.py           # Package initialization
├── core/                 # Core functionality
│   ├── flow.py          # Flow execution engine
│   ├── executor.py      # Flow executor
│   └── schema.py        # Data schemas
├── components/          # Component library
│   ├── __init__.py
│   └── base.py          # Base component class
├── memory/              # Memory management
│   ├── __init__.py
│   ├── base.py          # Base memory class
│   └── session.py       # Session memory implementation
├── integrations/        # External integrations
│   ├── fastapi.py       # FastAPI integration
│   ├── mcp.py           # MCP protocol support
│   └── llm.py           # LLM provider support
├── cli/                 # Command-line interface
│   ├── __init__.py
│   └── commands.py      # CLI commands
└── utils/               # Utility functions
    ├── __init__.py
    ├── logger.py        # Logging configuration
    └── validators.py    # Input validation

Dependencies

Core Dependencies

• fastapi (≥0.128.0) - Web framework
• pydantic (≥2.0.0) - Data validation
• langchain-core (≥0.3.0) - LangChain core library
• orjson (≥3.10.0) - Fast JSON serialization

LLM Provider Support

• langchain-openai - OpenAI API support
• langchain-ollama - Ollama local LLM support
• langchain-ibm - IBM LangChain support

CLI & HTTP

• typer (≥0.12.0) - CLI framework
• httpx (≥0.25.0) - Async HTTP client

Advanced Usage

Custom Memory Backend

from ignis_lfx.memory import BaseMemory

class CustomMemory(BaseMemory):
    def save(self, session_id: str, role: str, content: str) -> None:
        # Implement custom save logic
        pass
    
    def load(self, session_id: str) -> list:
        # Implement custom load logic
        pass

# Use custom memory
from ignis_lfx import execute_flow
result = execute_flow(
    flow_name="my_flow.json",
    memory_backend=CustomMemory()
)

Component Development

from ignis_lfx.components import BaseComponent
from pydantic import Field

class MyCustomComponent(BaseComponent):
    name: str = "MyComponent"
    description: str = "A custom component"
    
    input_param: str = Field(..., description="Input parameter")
    
    def run(self, **kwargs) -> dict:
        # Implement component logic
        return {"result": f"Processed: {self.input_param}"}

Contributing

We welcome contributions! Please follow these steps:

1. Fork the repository at Infogain-GenAI/ignis-lfx
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Commit changes: git commit -m 'Add amazing feature'
4. Push to branch: git push origin feature/amazing-feature
5. Open a Pull Request

Development Setup

# Clone repository
git clone https://github.com/Infogain-GenAI/ignis-lfx.git
cd ignis-lfx

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install in development mode
pip install -e ".[dev]"

# Run tests
pytest

# Format code
black .

# Lint code
ruff check . --fix

Testing

# Run all tests
pytest

# Run tests with coverage
pytest --cov=ignis_lfx --cov-report=html

# Run specific test file
pytest tests/test_execution.py

# Run tests matching pattern
pytest -k "memory" -v

Troubleshooting

Common Issues

Issue: ImportError: cannot import name 'execute_flow'

• Solution: Ensure ignis_lfx is properly installed: pip install --upgrade ignis_lfx

Issue: Connection refused to LFX server

• Solution: Verify LFX server is running and LFX_URL is correctly configured

Issue: API Key authentication failed

• Solution: Check your API key in the configuration file or environment variable

Documentation

For detailed documentation, examples, and API reference, visit:

• GitHub Wiki
• API Documentation

License

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

Support

• 📧 Email: [e-mail]
• 🐛 Issue Tracker: GitHub Issues
• 💬 Discussions: GitHub Discussions

Changelog

Version 0.1.0 (Initial Release)

• Initial release of ignis_lfx
• Core flow execution engine
• Memory management system
• FastAPI integration
• MCP protocol support
• Comprehensive documentation

Acknowledgments

Built by the Infogain GenAI team using the Langflow framework.

---

Made with ❤️ by Infogain