import gradio as gr
from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
import torch

# Image Classification Model
image_pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")

def predict_image(input_img):
    predictions = image_pipeline(input_img)
    return input_img, {p["label"]: p["score"] for p in predictions} 

image_gradio_app = gr.Interface(
    fn=predict_image,
    inputs=gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"),
    outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)],
    title="Hot Dog? Or Not?",
)

# Chatbot Model
tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium")
chatbot_model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-medium")

def predict_chatbot(input, history=[]):
    new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt')
    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
    history = chatbot_model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id).tolist()
    response = tokenizer.decode(history[0]).split("")

    response_tuples = [(response[i], response[i+1]) for i in range(0, len(response)-1, 2)]
    return response_tuples, history

chatbot_gradio_app = gr.Blocks()
with chatbot_gradio_app as demo:
    chatbot = gr.Chatbot()
    state = gr.State([])
    with gr.Row():
        txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter")
    txt.submit(predict_chatbot, [txt, state], [chatbot, state])

# Launch both interfaces
if __name__ == "__main__":
    gr.Interface(
        columns=2,
        children=[image_gradio_app, chatbot_gradio_app]
    ).launch()