Creating Your Own GPT ChatGPT-Like Bot for Free in Python

In this article, we will explore how to quickly create your own ChatGPT-like chatbot for free using Python. Our approach involves leveraging the Hugging Face API and the Mistral-7B-Instruct-v0.1 open-source model. By following these steps, you'll be able to set up a functional chatbot within minutes.

Before we begin, make sure you have Python installed on your system. Additionally, you'll need to install the Hugging Face Transformers library, which can be done with the following command:

pip install huggingface_hub         

1. Hugging Face API Setup:First, sign up for a free account on the Hugging Face website (https://huggingface.co/). After registration, obtain your API key from your account settings.
2. Using the Mistral-7B-Instruct-v0.1 Model:We'll make use of the Mistral-7B-Instruct-v0.1 model, available on the Hugging Face Model Hub. You can load the model using the following Python code:

from huggingface_hub import InferenceClient

temperature=0.9 
max_new_tokens=512 
top_p=0.95 
repetition_penalty=1.0  
API_KEY='<HUGGING_API_KEY>'

headers = {"Authorization": F"Bearer {API_KEY}"}

def generate(prompt):

    if temperature < 1e-2:
        temperature = 1e-2  

    top_p = float(top_p)  

    generate_kwargs = dict(
        temperature=temperature, 
        max_new_tokens=max_new_tokens,
        top_p=top_p,  
        repetition_penalty=repetition_penalty,  
        do_sample=True,  
        seed=random.randint(0, 10**7),  
    )

    client = InferenceClient(API_URL, headers=headers)
    response = client.text_generation(prompt, **generate_kwargs)

    return response
        

Congratulations! You've successfully created a ChatGPT-like chatbot for free using the Hugging Face API and the Mistral-7B-Instruct-v0.1 model. Feel free to experiment with different input texts and explore the capabilities of your new chatbot. This serves as a quick and accessible way to implement powerful language models for various applications.