README.md

metadata

title: Claw
emoji: 🏢
colorFrom: gray
colorTo: yellow
sdk: docker
pinned: false
license: mit
short_description: Handle responses for claw

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Greet JSON Endpoint

The greet_json endpoint is located at the root of the application (path /).

How to Call

1. Via Browser

Navigate to the root URL in your browser:

• Hosted Space: devserenerocks-claw.hf.space
• Locally: http://localhost:7860/

2. Via cURL

• Hosted Space:

  curl https://devserenerocks-claw.hf.space/
  

• Locally:

  curl http://localhost:7860/
  

3. Via Python

• Hosted Space:

  import requests
  
  response = requests.get("https://devserenerocks-claw.hf.space/")
  print(response.json())
  

• Locally:

  import requests
  
  response = requests.get("http://localhost:7860/")
  print(response.json())
  

Expected Response

{
  "Hello": "World!"
}

Chat Endpoint

The chat endpoint is located at /chat and uses Hugging Face's InferenceClient (running nvidia/Llama-3.1-Nemotron-Nano-8B-v1) to get chat completions.

This endpoint requires the HF_TOKEN environment variable to be set with a valid Hugging Face Hub token.

How to Call

1. Via cURL

• Hosted Space:

  curl -X POST https://devserenerocks-claw.hf.space/chat \
    -H "Content-Type: application/json" \
    -d '{"message": "Hello, how are you?"}'
  

• Locally:

  curl -X POST http://localhost:7860/chat \
    -H "Content-Type: application/json" \
    -d '{"message": "Hello, how are you?"}'
  

2. Via Python

• Hosted Space:

  import requests
  
  payload = {"message": "Hello, how are you?"}
  response = requests.post("https://devserenerocks-claw.hf.space/chat", json=payload)
  print(response.json())
  

• Locally:

  import requests
  
  payload = {"message": "Hello, how are you?"}
  response = requests.post("http://localhost:7860/chat", json=payload)
  print(response.json())
  

Expected Response

{
  "response": "Hello! I am doing well, thank you. How can I help you today?"
}