LLM Simple API Application

A FastAPI service to interact with Large Language Models (LLMs). It exposes endpoints to configure the target LLM (endpoint, model, API key) and to send prompts.

Setup

1. Create and activate a virtual environment:

python3 -m venv venv
source venv/bin/activate

2. Install dependencies:

pip install -r requirements.txt

Run

uvicorn main:app --reload

The server runs at http://localhost:8000.

Endpoints

• GET / — Welcome message
• GET /health — Health check
• POST /configure — Update endpoint, model, and api_key (all optional)
• POST /configure/endpoint — Update only endpoint
• POST /configure/model — Update only model
• POST /configure/key — Update only api_key
• GET /configure/get — Fetch current endpoint, model, and api_key
• POST /ask — Send a prompt to the configured LLM and get the response

Request Examples

Update endpoint/model/api_key:

curl -X POST http://localhost:8000/configure \
  -H "Content-Type: application/json" \
  -d '{"endpoint": "http://127.0.0.1:8011/v1/chat/completions", "model": "gpt-4.1", "api_key": "your-key"}'

Ask the LLM:

curl -X POST http://localhost:8000/ask \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Hello, how are you?"}'

Notes

• The configuration is stored in memory; restart resets values to defaults defined in main.py.
• Ensure your editor uses the project virtualenv to resolve imports and suppress linter warnings.