Building a Chatbot with Qwen/QwQ-32B

Create a basic chatbot with Qwen/QwQ-32B in a few steps.

Prerequisites

• An API key from DeepRequest.io
• Python 3.6 or later
• Requests library (pip install requests)

Example Code

import requests
import json

api_key = "YOUR_API_KEY_HERE"
url = "https://api.deeprequest.io/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {api_key}"
}

def get_response(user_input, conversation_history=None):
    if conversation_history is None:
        conversation_history = []

    # Add user message to history
    conversation_history.append({"role": "user", "content": user_input})

    data = {
        "model": "qwq-32b",
        "messages": conversation_history,
        "max_tokens": 500,
        "temperature": 0.7
    }

    response = requests.post(url, headers=headers, json=data)
    response_data = response.json()

    assistant_message = response_data["choices"][0]["message"]["content"]

    # Add assistant response to history
    conversation_history.append({"role": "assistant", "content": assistant_message})

    return assistant_message, conversation_history

# Example usage
conversation = []
while True:
    user_input = input("You: ")
    if user_input.lower() in ["exit", "quit", "bye"]:
        break

    bot_response, conversation = get_response(user_input, conversation)
    print(f"Bot: {bot_response}")

How It Works

1. We send a request to the API with:

   • Model identifier: qwq-32b
   • Messages: An array of conversation messages with roles and content
   • Temperature: Controls randomness (0.7 is balanced)
   • Max tokens: Limits response length

2. The API returns a response we can display to the user

3. We maintain a conversation history to give the model context of previous exchanges

Next Steps

• Add a system message to set the chatbot’s personality
• Implement error handling for API calls
• Create a web interface with Flask or Streamlit