A simple FastAPI application that provides a REST API for interacting with Cerebras LLM using LangChain.

• Single /chat endpoint for sending messages to Cerebras LLM
• Support for custom models and API keys
• Health check endpoints
• Async support for better performance

1. Install dependencies:

pip install -r requirements.txt

2. Set your Cerebras API key (optional if provided in requests):

export CEREBRAS_API_KEY="your-api-key-here"

python main.py

The server will start on http://localhost:8000

Send a message to the Cerebras LLM.

Request Body:

{
  "message": "Hello, how are you?",
  "model": "llama-3.1-8b-instruct",
  "api_key": "your-api-key" // optional if set as environment variable
}

Response:

{
  "response": "I'm doing well, thank you for asking!",
  "provider_info": {
    "provider": "cerebras",
    "model": "llama-3.1-8b-instruct",
    "api_key_available": true
  }
}

Health check endpoint.

Detailed health check endpoint.

Once the server is running, visit:

• Swagger UI: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc

curl -X POST "http://localhost:8000/chat" \
     -H "Content-Type: application/json" \
     -d '{
       "message": "What is the capital of France?",
       "model": "llama-3.1-8b-instruct"
     }'