• Prerequisites

• Open the below provided Colab link

  • https://colab.research.google.com/drive/1miK4Xbqv9lYkfe0z6jMh41fA_itulAA0?usp=sharing

• Copying Code to your Google Drive

  • On the top left corner of Google Colab Notebook you can find File, click on it.

    

  • Click on Save a Copy in Drive

    

  • If you are not logged in to your Google Account, please log into it.

  • Once you are successfully logged in a new Google Colab Notebook with the given code will be opened

• Click on the Run button to Install the Packages

  

• Click on the Run button to import the required things to build the application

  

• Get the OpenAI API Key and set it as environmental variable

  • Generate API Key

    • Go to https://platform.openai.com/account/api-keys
    • Create a new Secret Key
    • Copy the Secret Key for your use.

  • Replace your Open AI API Key with your own API Key

    

  • Click on the Run button

    

• Assigning the values for template, prompt, and memory

  • You can update the first line of the template provided

  • Click on the Run button

    

• Initializing LLM Chain using Open AI

  • Using ChatOpenAI we are creating an LLMChain

  • Click on the Run button

    

• Define a function to generate the response for the question you ask:

  • From the initialized llm_chain we will predict the response

    • Click on the Run button

      

• Create a ChatInterface using the Gradio

  • We are creating the ChatInterface from gradio and providing a function get_text_reponse and also examples

  • Check for other arguments here

  • Click on the Run button to create an interface

    

• Launch your ChatBot with Gradio APP

  • Click on the Run button to launch the App

  

• Now you can try asking questions in your ChatBot

• If you are getting any errors:

  • Keep print statements to identify the issue

  • To identify the error you are getting please add debug=True while launching the gradio app.

    if __name__ == "__main__":
        demo.launch(debug=True)
    

    def get_text_response(user_message,history):
        try:
          response = llm_chain.predict(user_message = user_message)
        except Exception as e:
          print("Error:", e)
          try:
            print("Error:", e.error.message)
            response = "Failed to reply: " + e.error.message
          except Exception as e:
            response = "Failed to reply"
        return response
    

Publish your code to Hugging face

• Login to Hugging Face from Google Colab

  • Create a Hugging Face token and Copy
    • Login to Hugging Face https://huggingface.co/
    • Open https://huggingface.co/settings/tokens
    • Click on New token
    • Add a name for the Token
    • Choose a Role for the Token whether to Read or Write
    • Choose to Write and click on Create
  • Click on the Run button to enter Hugging Face Token

  

  

  • Now paste the hugging Face token in the textbox provided

• Create HuggingFace API to push code from Google Colab

  • Click on the Run button to create API

    

• Adding Hugging Face Repo ID

  • Copy Hugging Face Repo ID by opening the Hugging Face Repo Created

    

  • Replace your Repo ID

    

  • Click on Run button to assign hugging Face Repo ID