t2g-sdk 1.0.0rc14

SDK for the T2G API

Lettria's Text-to-Graph SDK 🚀

Welcome to the official Python SDK for Lettria's Text-to-Graph (T2G) API! This SDK makes it easy to turn unstructured text into powerful knowledge graphs right from your Python applications. ✨

🌟 Features

• Asynchronous Client: High-performance, non-blocking API calls using asyncio and aiohttp.
• Simple Interface: Easy-to-use methods for file operations, ontology management, and graph building.
• Data Validation: Robust data modeling with pydantic.
• Neo4j Integration: Directly save your graph data to a Neo4j instance.
• Flexible Configuration: Configure via environment variables or directly in code.

📦 Installation

pip install t2g-sdk==1.0.0-rc.14

🚀 Quick Start

To use the SDK, you need an API key from Lettria. Get in touch with us at [e-mail] to get started.

Configuration

Create a .env file and add your credentials:

LETTRIA_API_KEY="YOUR_LETTRIA_API_KEY"

# Optional Neo4j credentials
NEO4J_URI="bolt://localhost:7687"
NEO4J_USER="neo4j"
NEO4J_PASSWORD="password"

The T2GClient will automatically load these variables.

Example: Build a Graph

This example shows how to build a graph from a text file.

import asyncio
from t2g_sdk import T2GClient

async def main():
    async with T2GClient() as client:
        try:
            await client.build_graph(
                file_path="path/to/your/document.txt",
            )
            print("🎉 Graph built successfully!")
        except Exception as e:
            print(f"An error occurred: {e}")

if __name__ == "__main__":
    asyncio.run(main())

📚 API Reference

client.build_graph

async def build_graph(
    file_path: str,
    ontology_path: Optional[str] = None,
    output_path: Optional[str] = None,
    save_to_neo4j: bool = False,
    refresh_graph: bool = False,
) -> Job:

Processes a file by uploading it, optionally with an ontology, running a job, and downloading the output.

Parameter	Type	Description	Default
file_path	str	The path to the file to process.
ontology_path	Optional[str]	The path to the ontology file to use.	None
output_path	Optional[str]	The path to save the output to. If not provided, a default path will be used.	None
save_to_neo4j	bool	Whether to save the output to Neo4j.	False
refresh_graph	bool	Whether to force a new job to be created (refresh the graph).	False

📂 Examples

For more detailed examples, check out the examples/ directory. Each example has its own README with instructions.

Simple Examples

• Build Graph: Build a knowledge graph from a text file.
• File Operations: Upload and manage files.
• Ontology Operations: Upload and manage ontologies.
• Delete Operations: Delete files and ontologies.

Advanced Example

• Simple Reporting: A complete workflow to index a PDF, build a graph, and generate a report.

🤝 Contributing

Contributions are welcome! Feel free to open an issue or submit a pull request.

📧 Contact

For support or questions, please reach out at [e-mail].

📄 License

This SDK is licensed under the MIT License.