app.py

import gradio as gr
from gradio_client import Client

fusecap_client = Client("https://noamrot-fusecap-image-captioning.hf.space/")

def get_caption(image_in):
    
    fusecap_result = fusecap_client.predict(
	    image_in,	# str representing input in 'raw_image' Image component
	    api_name="/predict"
    )
    print(fusecap_result)
    return fusecap_result

import re
import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta", torch_dtype=torch.bfloat16, device_map="auto")

agent_maker_sys = f"""
You are an AI whose job it is to help users create their own chatbots. In particular, you need to respond succintly in a friendly tone, write a system prompt for an LLM, a catchy title for the chatbot, and a very short example user input. Make sure each part is included.
To do so, user will provide an image description, from which you must write a system prompt corresponding to the character of the person or subject described.
For example, if a user says, "make a bot that gives advice on how to grow your startup", first do a friendly response, then add the title, system prompt, and example user input. Immediately STOP after the example input. It should be EXACTLY in this format:
Sure, I'd be happy to help you build a bot! I'm generating a title, system prompt, and an example input. How do they sound? Feel free to give me feedback!
Title: Startup Coach
System prompt: Your job as an LLM is to provide good startup advice. Do not provide extraneous comments on other topics. Be succinct but useful. 
Example input: Risks of setting up a non-profit board
Here's another example. If a user types, "Make a chatbot that roasts tech ceos", respond: 
Sure, I'd be happy to help you build a bot! I'm generating a title, system prompt, and an example input. How do they sound? Feel free to give me feedback!
Title: Tech Roaster
System prompt: As an LLM, your primary function is to deliver hilarious and biting critiques of technology CEOs. Keep it witty and entertaining, but also make sure your jokes aren't too mean-spirited or factually incorrect. 
Example input: Elon Musk
"""

instruction = f"""
<|system|>
{agent_maker_sys}</s>
<|user|>
"""

def infer(image_in):

    user_prompt = get_caption(image_in)
    prompt = f"{instruction.strip()}\n{user_prompt}</s>"    
    print(f"PROMPT: {prompt}")
    outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
    print(outputs)

    pattern = r'\<\|system\|\>(.*?)\<\|assistant\|\>'
    cleaned_text = re.sub(pattern, '', outputs[0]["generated_text"], flags=re.DOTALL)
    

    return cleaned_text

gr.Interface(
    fn = infer,
    inputs = [
        gr.Image(type="filepath")
    ],
    outputs = [
        gr.Textbox()
    ]
).queue().launch()