import gradio as gr
from huggingface_hub import InferenceClient

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load your fine-tuned GPT-2 model from Hugging Face
MODEL_NAME = "hackergeek98/therapist01"  # Replace w 
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)

# Initialize conversation history
conversation_history = ""

# Function to generate responses
def generate_response(user_input):
    global conversation_history

    # Update conversation history with user input
    conversation_history += f"User: {user_input}\n"
    
    # Tokenize the conversation history
    inputs = tokenizer(conversation_history, return_tensors="pt", truncation=True, max_length=1024)

    # Generate a response from the model
    outputs = model.generate(inputs['input_ids'], max_length=1024, num_return_sequences=1, no_repeat_ngram_size=2)

    # Decode the model's output
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)

    # Update conversation history with the model's response
    conversation_history += f"Therapist: {response}\n"

    # Return the therapist's response
    return response

# Create Gradio interface
interface = gr.Interface(fn=generate_response,
                         inputs=gr.Textbox(label="Enter your message", lines=2),
                         outputs=gr.Textbox(label="Therapist Response", lines=2),
                         title="Virtual Therapist",
                         description="A fine-tuned GPT-2 model acting as a virtual therapist. Chat with the model and receive responses as if you are talking to a therapist.")

# Launch the app
interface.launch()


if __name__ == "__main__":
    demo.launch()