app.py

from transformers import AutoConfig, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM, MistralForCausalLM
import torch
import gradio as gr
import random
from textwrap import wrap
import spaces

def wrap_text(text, width=90):
    lines = text.split('\n')
    wrapped_lines = [textwrap.fill(line, width=width) for line in lines]
    wrapped_text = '\n'.join(wrapped_lines)
    return wrapped_text

@spaces.GPU
def multimodal_prompt(user_input, system_prompt="You are an expert medical analyst:"):
    # Combine user input and system prompt
    formatted_input = f"<s> [INST] {example_instruction} [/INST] {example_answer}</s> [INST] {system_prompt} [/INST]"

    # Encode the input text
    encodeds = tokenizer(formatted_input, return_tensors="pt", add_special_tokens=False)
    model_inputs = encodeds.to(device)

    # Generate a response using the model
    output = model.generate(
        **model_inputs,
        max_length=max_length,
        use_cache=True,
        early_stopping=True,
        bos_token_id=model.config.bos_token_id,
        eos_token_id=model.config.eos_token_id,
        pad_token_id=model.config.eos_token_id,
        temperature=0.1,
        do_sample=True
    )

    # Decode the response
    response_text = tokenizer.decode(output[0], skip_special_tokens=True)

    return response_text

# Define the device
device = "cuda" if torch.cuda.is_available() else "cpu"

# Use the base model's ID
model_id = "SuperAGI/SAM"

tokenizer = AutoTokenizer.from_pretrained(model_id = model_id, trust_remote_code=True)
# tokenizer.pad_token = tokenizer.eos_token
# tokenizer.padding_side = 'left'

# Specify the configuration class for the model
#model_config = AutoConfig.from_pretrained(base_model_id)

model = MistralForCaumodel = AutoModelForCausalLM.from_pretrained(model_id)

class ChatBot:
    def __init__(self):
        self.history = []

class ChatBot:
    def __init__(self):
        # Initialize the ChatBot class with an empty history
        self.history = []

    def predict(self, user_input, system_prompt="You are an expert medical analyst:"):
        # Combine the user's input with the system prompt
        formatted_input = f"<s>[INST]{system_prompt} {user_input}[/INST]"

        # Encode the formatted input using the tokenizer
        user_input_ids = tokenizer.encode(formatted_input, return_tensors="pt")

        # Generate a response using the PEFT model
        response = peft_model.generate(input_ids=user_input_ids, max_length=512, pad_token_id=tokenizer.eos_token_id)

        # Decode the generated response to text
        response_text = tokenizer.decode(response[0], skip_special_tokens=True)
        
        return response_text  # Return the generated response

bot = ChatBot()

title = "🚀👋🏻Welcome to Tonic's🤖SuperAGI/SAM Chat🚀"
description = "SAM is an Agentic-Native LLM that excels at complex reasoning. You can use this Space to test out the current model [Tonic/superagi-sam](https://huggingface.co/Tonic/superagi-sam) or duplicate this Space and use it locally or on 🤗HuggingFace. [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)."
examples = [["[Question:] What is the proper treatment for buccal herpes?", "You are a medicine and public health expert, you will receive a question, answer the question, and provide a complete answer"]]


def main():
    with gr.Blocks() as demo:
        gr.Markdown(title)
        gr.Markdown(description)
        with gr.Row():
            with gr.Column():
                example_instruction = gr.Textbox(label="Example Instruction")
                example_answer = gr.Textbox(label="Example Answer")
            with gr.Column():
                user_input = gr.Textbox(label="Your Question")
                system_prompt = gr.Textbox(label="System Prompt", value="You are an expert medical analyst:")
        submit_btn = gr.Button("Submit")
        output = gr.Textbox(label="Response")

        submit_btn.click(
            fn=bot.predict,
            inputs=[example_instruction, example_answer, user_input, system_prompt],
            outputs=output
        )

    demo.launch()

if __name__ == "__main__":
    main()