app.py

import streamlit as st
from langchain.prompts import PromptTemplate
from langchain.llms import CTransformers
import gradio as gr
## Function To get response from LLAma 2 model

def getLLamaresponse(input_text = "home decoration" ,no_words = 100,blog_style = "lifestyle"):

    ### LLama2 model
    llm=CTransformers(model='TheBloke/OpenHermes-2.5-Mistral-7B-GGUF',
                      model_type='llama',
                      config={'max_new_tokens':256,
                              'temperature':0.01})
    
    ## Prompt Template

    template="""
        Write a blog for {blog_style} job profile for a topic {input_text}
        within {no_words} words.
            """
    
    prompt=PromptTemplate(input_variables=["blog_style","input_text",'no_words'],
                          template=template)
    
    ## Generate the ressponse from the LLama 2 model
    response=llm(prompt.format(blog_style=blog_style,input_text=input_text,no_words=no_words))
    print(response)
    return response


with gr.Blocks() as demo:
    gr.Markdown("# AI Patient Chatbot")
    with gr.Group():
        with gr.Tab("Patient Chatbot"):
            chatbot = gr.Chatbot()
            message = gr.Textbox(label="Enter your message to Barry", placeholder="Type here...", lines=2)
            send_message = gr.Button("Submit")
            send_message.click(AIPatient, inputs=[message], outputs=[chatbot])
            save_chatlog = gr.Button("Save Chatlog")
            #send_message.click(SaveChatlog, inputs=[message], outputs=[chatbot])


            #message.submit(AIPatient, inputs=[message], outputs=[chatbot])

demo.launch(debug=True)