# import gradio as gr
# from huggingface_hub import InferenceClient
# import pandas as pd

# """
# 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")

# ################################################################

# # Load your CSV file
# df = pd.read_csv("your_file.csv")

# # Create dropdowns for exam name, year, and problem number
# exam_names = df["exam name"].unique()
# year_options = df["year"].unique()
# problem_numbers = df["problem number"].unique()

# exam_dropdown = gr.Dropdown(exam_names, label="Exam Name")
# year_dropdown = gr.Dropdown(year_options, label="Year")
# problem_dropdown = gr.Dropdown(problem_numbers, label="Problem Number")

# # Define the functions for the three buttons
# def solve_problem(exam, year, problem):
#     problem_statement = df[(df["exam name"] == exam) & (df["year"] == year) & (df["problem number"] == problem)]["problem statement"].values[0]
#     prompt = f"Solve the following problem: {problem_statement}"
#     response = client.chat_completion(prompt, max_tokens=512, temperature=0.7, top_p=0.95)
#     return response.choices[0].text

# def give_hints(exam, year, problem):
#     problem_statement = df[(df["exam name"] == exam) & (df["year"] == year) & (df["problem number"] == problem)]["problem statement"].values[0]
#     prompt = f"Give hints for the following problem: {problem_statement}"
#     response = client.chat_completion(prompt, max_tokens=512, temperature=0.7, top_p=0.95)
#     return response.choices[0].text

# def create_similar_problem(exam, year, problem):
#     problem_statement = df[(df["exam name"] == exam) & (df["year"] == year) & (df["problem number"] == problem)]["problem statement"].values[0]
#     prompt = f"Create a similar problem to the following one: {problem_statement}"
#     response = client.chat_completion(prompt, max_tokens=512, temperature=0.7, top_p=0.95)
#     return response.choices[0].text

# ################################################################

# 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)",
#         ),
#     ],
# )

# ################################################################

# # Create Gradio interface with Blocks context
# with gr.Blocks() as dropdown_interface:
#     with gr.Column():
#         exam_dropdown.render()
#         year_dropdown.render()
#         problem_dropdown.render()
        
#         solve_button = gr.Button("Solve Problem")
#         hints_button = gr.Button("Give Hints")
#         similar_problem_button = gr.Button("Create Similar Problem")
        
#         output_text = gr.Textbox(label="Output")
    
#         solve_button.click(solve_problem, inputs=[exam_dropdown, year_dropdown, problem_dropdown], outputs=output_text)
#         hints_button.click(give_hints, inputs=[exam_dropdown, year_dropdown, problem_dropdown], outputs=output_text)
#         similar_problem_button.click(create_similar_problem, inputs=[exam_dropdown, year_dropdown, problem_dropdown], outputs=output_text)

# ################################################################

# # Combine both interfaces into a tabbed layout
# tabbed_interface = gr.TabbedInterface(
#     [dropdown_interface, demo],
#     ["Problem Solver", "Chat Interface"]
# )

# ################################################################

# # Launch the app
# if __name__ == "__main__":
#     tabbed_interface.launch()


import pandas as pd
import gradio as gr
from huggingface_hub import InferenceClient

# Initialize the InferenceClient
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

# Load your CSV file
df = pd.read_csv("your_file.csv")

# Create dropdowns for exam name, year, and problem number
exam_names = df["exam name"].unique()
year_options = df["year"].unique()
problem_numbers = df["problem number"].unique()

exam_dropdown = gr.Dropdown(exam_names, label="Exam Name")
year_dropdown = gr.Dropdown(year_options, label="Year")
problem_dropdown = gr.Dropdown(problem_numbers, label="Problem Number")

# Define the functions for the three buttons
def solve_problem(exam, year, problem):
    problem_statement = df[(df["exam name"] == exam) & (df["year"] == year) & (df["problem number"] == problem)]["problem statement"].values[0]
    prompt = f"Solve the following problem: {problem_statement}"
    response = client.text_generation(prompt, max_new_tokens=512, temperature=0.7, top_p=0.95, model = "HuggingFaceH4/zephyr-7b-beta")
    return response[0]['generated_text']

def give_hints(exam, year, problem):
    problem_statement = df[(df["exam name"] == exam) & (df["year"] == year) & (df["problem number"] == problem)]["problem statement"].values[0]
    prompt = f"Give hints for the following problem: {problem_statement}"
    response = client.text_generation(prompt, max_new_tokens=512, temperature=0.7, top_p=0.95, model = "HuggingFaceH4/zephyr-7b-beta")
    return response[0]['generated_text']

def create_similar_problem(exam, year, problem):
    problem_statement = df[(df["exam name"] == exam) & (df["year"] == year) & (df["problem number"] == problem)]["problem statement"].values[0]
    prompt = f"Create a similar problem to the following one: {problem_statement}"
    response = client.text_generation(prompt, max_new_tokens=512, temperature=0.7, top_p=0.95, model = "HuggingFaceH4/zephyr-7b-beta")
    return response[0]['generated_text']

# Define the chat response function
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

# Create Gradio interface with Blocks context
with gr.Blocks() as dropdown_interface:
    with gr.Column():
        exam_dropdown.render()
        year_dropdown.render()
        problem_dropdown.render()
        
        solve_button = gr.Button("Solve Problem")
        hints_button = gr.Button("Give Hints")
        similar_problem_button = gr.Button("Create Similar Problem")
        
        output_text = gr.Textbox(label="Output")
    
        solve_button.click(solve_problem, inputs=[exam_dropdown, year_dropdown, problem_dropdown], outputs=output_text)
        hints_button.click(give_hints, inputs=[exam_dropdown, year_dropdown, problem_dropdown], outputs=output_text)
        similar_problem_button.click(create_similar_problem, inputs=[exam_dropdown, year_dropdown, problem_dropdown], outputs=output_text)

chat_interface = 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)",
        ),
    ],
)

# Combine both interfaces into a tabbed layout
tabbed_interface = gr.TabbedInterface(
    [dropdown_interface, chat_interface],
    ["Problem Solver", "Chat Interface"]
)

# Launch the app
if __name__ == "__main__":
    tabbed_interface.launch()