from langchain.prompts import PromptTemplate
from langchain_huggingface import HuggingFaceEndpoint
from PIL import Image
import os
import secrets
from pathlib import Path
import tempfile

# Initialize the Hugging Face BLIP model
image_captioning_model = HuggingFaceEndpoint(
    endpoint_url="https://api-inference.huggingface.co/models/Salesforce/blip-image-captioning-base",
    huggingfacehub_api_token=os.getenv("HUGGING_FACE_API"),  # Ensure you set this in your environment
    temperature=0.7,
    max_new_tokens=1024,
)
math_llm=HuggingFaceEndpoint(
    endpoint_url="https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-3B-Instruct",
    huggingfacehub_api_token=os.getenv("HUGGING_FACE_API"),  # Ensure you set this in your environment
    temperature=0.7,
    max_new_tokens=1024,)
# Function to process the image
def process_image(image, shouldConvert=False):
    # Ensure temporary directory exists
    uploaded_file_dir = os.environ.get("GRADIO_TEMP_DIR") or str(
        Path(tempfile.gettempdir()) / "gradio"
    )
    os.makedirs(uploaded_file_dir, exist_ok=True)
    
    # Save the uploaded image
    name = f"tmp{secrets.token_hex(20)}.jpg"
    filename = os.path.join(uploaded_file_dir, name)
    if shouldConvert:
        # Convert image to RGB mode if it contains transparency
        new_img = Image.new("RGB", size=(image.width, image.height), color=(255, 255, 255))
        new_img.paste(image, (0, 0), mask=image)
        image = new_img
    image.save(filename)

    # Define a PromptTemplate for text instruction
    template = """
    You are a helpful AI assistant.
    Please describe the math-related content in this image, ensuring that any LaTeX formulas are correctly transcribed. 
    Non-mathematical details do not need to be described.

    Image Path: {image}
    """
    prompt_template = PromptTemplate(
        input_variables=["image"],  # Dynamically insert the image path
        template=template
    )

    # Create the text instruction by rendering the prompt template
    prompt = prompt_template.format(image=f"file://{filename}")

    # Use the model with both the image and the generated prompt
    with open(filename, "rb") as img_file:
        response = image_captioning_model({
            "inputs": {
                "image": img_file,
                "text": prompt
            }
        })

    # Return the model's response
    return response

def get_math_response(image_description, user_question):
    template = """
    You are a helpful AI assistant specialized in solving math reasoning problems. 
    Analyze the following question carefully and provide a step-by-step explanation along with the answer.
    Image description : {image_description}
    Question: {user_question}?
    """

    prompt_template = PromptTemplate(
        input_variables=["user_question","image_description"],  # Define the placeholder(s) in the template
        template=template
    )
    formatted_prompt = prompt_template.format(user_question=user_question, image_description=image_description)

    # Pass the formatted prompt to the model
    response = math_llm(formatted_prompt)

    # Print the response
    yield response

def math_chat_bot(image, sketchpad, question, state):
    current_tab_index = state["tab_index"]
    image_description = None
    # Upload
    if current_tab_index == 0:
        if image is not None:
            image_description = process_image(image)
    # Sketch
    elif current_tab_index == 1:
        print(sketchpad)
        if sketchpad and sketchpad["composite"]:
            image_description = process_image(sketchpad["composite"], True)
    yield from get_math_response(image_description, question)
css = """
#qwen-md .katex-display { display: inline; }
#qwen-md .katex-display>.katex { display: inline; }
#qwen-md .katex-display>.katex>.katex-html { display: inline; }
"""
def tabs_select(e: gr.SelectData, _state):
    _state["tab_index"] = e.index

with gr.Blocks(css=css) as demo:

    state = gr.State({"tab_index": 0})
    with gr.Row():
        with gr.Column():
            with gr.Tabs() as input_tabs:
                with gr.Tab("Upload"):
                    input_image = gr.Image(type="pil", label="Upload"),
                with gr.Tab("Sketch"):
                    input_sketchpad = gr.Sketchpad(type="pil", label="Sketch", layers=False)
            input_tabs.select(fn=tabs_select, inputs=[state])
            input_text = gr.Textbox(label="input your question")
            with gr.Row():
                with gr.Column():
                    clear_btn = gr.ClearButton(
                        [*input_image, input_sketchpad, input_text])
                with gr.Column():
                    submit_btn = gr.Button("Submit", variant="primary")
        with gr.Column():
            output_md = gr.Markdown(label="answer",
                                    latex_delimiters=[{
                                        "left": "\\(",
                                        "right": "\\)",
                                        "display": True
                                    }, {
                                        "left": "\\begin\{equation\}",
                                        "right": "\\end\{equation\}",
                                        "display": True
                                    }, {
                                        "left": "\\begin\{align\}",
                                        "right": "\\end\{align\}",
                                        "display": True
                                    }, {
                                        "left": "\\begin\{alignat\}",
                                        "right": "\\end\{alignat\}",
                                        "display": True
                                    }, {
                                        "left": "\\begin\{gather\}",
                                        "right": "\\end\{gather\}",
                                        "display": True
                                    }, {
                                        "left": "\\begin\{CD\}",
                                        "right": "\\end\{CD\}",
                                        "display": True
                                    }, {
                                        "left": "\\[",
                                        "right": "\\]",
                                        "display": True
                                    }],
                                    elem_id="qwen-md")
        submit_btn.click(
            fn=math_chat_bot,
            inputs=[*input_image, input_sketchpad, input_text, state],
            outputs=output_md)
demo.launch()