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.

V4-Pro reasons by default, so all you need to do is loop the conversation and append the right field to the history.

Diese Übung ist Teil des Kurses

<Kurs>Arbeiten mit DeepSeek in Python</Kurs>

Kurs ansehen

Übungsanweisungen

Loop over the user questions.
Send each user question, q, to the deepseek-ai/DeepSeek-V4-Pro model.
Append the assistant's final answer (the .content, not the reasoning) to messages so the conversation history stays lean.

Interaktive praktische Übung

Versuche dich an dieser Übung, indem du diesen Beispielcode vervollständigst.

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 — V4-Pro reasons by default
    response = client.chat.completions.create(
        model="deepseek-ai/____",
        messages=____,
        max_tokens=500
    )
    
    # Append only the final answer to the conversation history
    assistant_dict = {"role": "assistant", "content": response.choices[0].message.____}
    messages.append(assistant_dict)
    print("Assistant: ", response.choices[0].message.content, "\n")

Code bearbeiten und ausführen