A FastAPI-based backend service for the LLM Visualizer React application.

This Python backend service provides API endpoints for processing and analyzing Large Language Model (LLM) related tasks, including:

• Tokenization of user prompts
• Embedding generation
• Data visualization support

• RESTful API endpoints using FastAPI
• Swagger UI documentation
• Token analysis
• Embedding generation
• Integration with LLM Visualizer frontend

1. Install dependencies:

pip install fastapi uvicorn transformers torch

1. Run the server:

uvicorn main:app --reload

The API documentation will be available at http://localhost:8000/docs

Detailed API documentation is available through the Swagger UI interface.

• Python 3.7+
• FastAPI
• Uvicorn
• Additional dependencies listed in requirements.txt