app.py

import gradio as gr 
from text_generation import Client

hf_api_key = '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'

#FalcomLM-instruct endpoint on the text_generation library
#client = Client("https://api-inference.huggingface.co/models/tiiuae/falcon-40b-instruct", headers={"Authorization": f"Bearer {hf_api_key}"}, timeout=120)
#client = Client("https://wjmh73a2pphfr6ed.us-east-1.aws.endpoints.huggingface.cloud", headers={"Authorization": f"Bearer {hf_api_key}"}, timeout=120)
client = Client("https://api-inference.huggingface.co/models/tiiuae/falcon-7b-instruct", headers={"Authorization": f"Bearer {hf_api_key}"}, timeout=120)

def generate(input):
    output = client.generate(input,max_new_tokens=1024).generated_text
    return output

def respond(message, chat_history):
        #No LLM here, just respond with a random pre-made message
        '''bot_message = random.choice(["Tell me more about it", 
                                     "Cool, but I'm not interested", 
                                     "Hmmmm, ok then"]) '''
        bot_message = generate(message)

        chat_history.append((message, bot_message))
        return "", chat_history

with gr.Blocks() as demo:
    chatbot = gr.Chatbot() #just to fit the notebook
    msg = gr.Textbox(label="Prompt")
    btn = gr.Button("Submit")
    
    clear = gr.ClearButton(components=[msg, chatbot], value="Clear console")

    btn.click(respond, inputs=[msg, chatbot], outputs=[msg, chatbot])
    msg.submit(respond, inputs=[msg, chatbot], outputs=[msg, chatbot]) #Press enter to submit
demo.launch(height=240)