Creating a reasoning chatbot for coding

Let's put everything together to build a reasoning chatbot for coding assistance!

You've been provided with two user messages: one to request Python code for a particular task, and a follow-up message requesting that it be written with a particular library.

Let's see how the reasoning model does!

This exercise is part of the course

Working with DeepSeek in Python

View Course

Exercise instructions

Loop over the user questions.
Send each user question, q, to the deepseek-ai/DeepSeek-R1 model.
Extract the response content to strip it of thinking tokens before appending it to messages.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

client = OpenAI(api_key="", base_url="https://api.together.xyz/v1")

messages = []
user_msgs = ["Write some Python code to generate a list of numbers from 1-10.", "Update the code to use the NumPy library."]

# Loop over the user questions
for q in ____:
    print("User: ", q)
    user_dict = {"role": "user", "content": q}
    messages.append(user_dict)
    
    # Create the API request
    response = client.chat.completions.create(
        model="deepseek-ai/____",
        messages=____,
        max_tokens=200
    )
    
    # Extract the response content to strip it of thinking tokens
    final_response = re.sub(r'[\s\S]*?<\/think>\s*', '', ____, re.DOTALL)
    assistant_dict = {"role": "assistant", "content": final_response.strip()}
    messages.append(assistant_dict)
    print("Assistant: ", response.choices[0].message.content, "\n")

Edit and Run Code