Create an AI chatbot in 5 minutes with a huggable face and Gradio

Image by author

This short tutorial will build a simple chatbot using the Microsoft DialoGPT model, Hugging Face Space and Gradio intervention. Using similar techniques, you will be able to create and customize your own application in 5 minutes.

1. Go hf.co and create a free account. After that press your Display image in the upper right corner and select “New Space”.
2. Fill in the form with the app name, license, space hardware and visibility.

A picture from space

1. Click the “Create space” button to initialize the application.
2. You can clone the repository and install files from your local system or create and edit files on Hugging Face using a browser.

Image from AI ChatBot

Click on the “Files” tab. > + Add file > Create a new file.

Image from kingabzpro/AI-ChatBot

Create a Gradio interface. You can copy my code.

Image from app.py

I loaded the “microsoft/DialoGPT-large” tokenizer and model and created a `prediction’ function to get the response and generate the history.

from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr
import torch


title = "🤖AI ChatBot"
description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)"
examples = [["How are you?"]]


tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")


def predict(input, history=[]):
    # tokenize the new input sentence
    new_user_input_ids = tokenizer.encode(
        input + tokenizer.eos_token, return_tensors="pt"
    )

    # append the new user input tokens to the chat history
    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)

    # generate a response
    history = model.generate(
        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
    ).tolist()

    # convert the tokens to text, and then split the responses into lines
    response = tokenizer.decode(history[0]).split("<|endoftext|>")
    # print('decoded_response-->>'+str(response))
    response = [
        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
    ]  # convert to tuples of list
    # print('response-->>'+str(response))
    return response, history


gr.Interface(
    fn=predict,
    title=title,
    description=description,
    examples=examples,
    inputs=["text", "state"],
    outputs=["chatbot", "state"],
    theme="finlaymacklon/boxy_violet",
).launch()

Moreover, I have provided my application with a custom theme: boxy_violet. You can browse Gradio Theme Gallery to choose a theme according to your taste.

Now we need to create a `requirement.txt` file and add the required Python packages.

Image from requests.txt

After that, your application will start building and in a few minutes it will download the model and load the model conclusion.

The Gradio app looks amazing. We just need to create a `prediction’ function for all the different model architects to get the answers and keep the history.

Now you can chat and interact with the app on kingabzpro/AI-ChatBot or embed your app on your website using https://kingabzpro-ai-chatbot.hf.space.

Image from kingabzpro/AI-ChatBot

Are you still confused? Search hundreds of chatbot apps on Spaces to get inspired and learn how to model.

For example, if you have a mode that is perfectly set to “LLaMA-7B”. Search for model and scroll down to see different implementations of the model.

Image from decapoda-research/llama-7b-hf

In conclusion, this blog provides a quick and easy tutorial on how to create an AI chatbot using Hugging Face and Gradio in just 5 minutes. With step-by-step instructions and customizable options, anyone can easily create their own chatbot.

It was fun and I hope you learned something. Please share your Gradio demo in the comments section. If you’re looking for an even simpler solution, check out OpenChat: a free and easy platform to build custom chatbots in minutes.

Abid Ali Awan (@1abidaliawan) is a certified data scientist professional who enjoys building machine learning models. Currently, he focuses on content creation and writes technical blogs on machine learning and data science technologies. Abid holds a Master’s degree in Technology Management and a Bachelor’s degree in Telecommunications Engineering. His vision is to create an AI product using a graph neural network for students struggling with mental illness.