app.py

import streamlit as st
import os
import google.generativeai as genai
import json
from PIL import Image
import re
import json
import tempfile

# Define constants
TEXT_PROMPT = """Use the provided document. Read the list of quadratic equations. 
Return your response as a JSON list. Do not include any extra text, explanations, or backslashes.

Example JSON output:
[
  "x^2 - 5x + 6 = 0",
  "2x^2 + 3x - 1 = 0",
  "x^2 - 9 = 0",
  "3x^2 - 2x + 4 = 0",
  "x^2 + 8x + 15 = 0"
]
"""

MODEL_ID = "gemini-2.0-flash-exp"  # Keep the model ID as is
try:
    api_key = os.getenv("GEMINI_API_KEY")
    model_id = MODEL_ID
    genai.configure(api_key=api_key)
except Exception as e:
    st.error(f"Error: {e}")
    st.stop()

model = genai.GenerativeModel(MODEL_ID)
chat = model.start_chat()

def get_local_file_path(img_file="problem1.png"):
    """
    Returns the path to the local PDF file.
    """
    try:
        file_path = os.path.join("problems", img_file)
        if not os.path.exists(file_path):
            raise FileNotFoundError(f"{file_path} does not exist.")
        return file_path
    except Exception as e:
        st.error(f"Failed to find the local file: {e}")
        st.stop()  # Stop if the file is not found

# Initialize conversation history in Streamlit session state
if "conversation_history" not in st.session_state:
    st.session_state.conversation_history = []
if "uploaded_file_part" not in st.session_state:  # Store the file *part*
    st.session_state.uploaded_file_part = None
if "uploaded_pdf_path" not in st.session_state:
    st.session_state.uploaded_pdf_path = get_local_file_path()

def multimodal_prompt(pdf_path, text_prompt, file_type="PDF"):
    """
    Sends a multimodal prompt to Gemini, handling file uploads efficiently.
    Args:
        pdf_path: The path to the file (PDF or image).
        text_prompt: The text prompt for the model.
        file_type: "PDF" or "image" to specify the file type.
    Returns:
        The model's response as a string, or an error message.
    """
    try:
        if file_type == "PDF":
            mime_type = "application/pdf"
        elif file_type == "image":
            import mimetypes
            mime_type, _ = mimetypes.guess_type(pdf_path)
            if mime_type is None:
              return "Could not determine MIME type for image. Please check the file path or type."
        else:
            return "Invalid file_type. Must be 'PDF' or 'image'."

        if st.session_state.get("uploaded_file_part") is None:  # First time, upload
            pdf_part = genai.upload_file(pdf_path, mime_type=mime_type)
            st.session_state.uploaded_file_part = pdf_part
            prompt = [text_prompt, pdf_part]  # First turn includes the actual file
        else:  # Subsequent turns, reference the file
            prompt = [text_prompt, st.session_state.uploaded_file_part]  # Subsequent turns include the file reference

        response = chat.send_message(prompt)

        # Update conversation history
        st.session_state.conversation_history.append({"role": "user", "content": text_prompt, "has_file": True})
        st.session_state.conversation_history.append({"role": "assistant", "content": response.text})
        return response.text

    except Exception as e:
        return f"An error occurred: {e}"

def get_equation(response):
    # Remove the ```json and ``` and extra spaces.
    try:
        json_string = response.replace('```json', '').replace('```', '').strip()

        # Parse the JSON string into a Python list.
        problems_list = json.loads(json_string)

        # return the first item found
        return problems_list[0] 

    except json.JSONDecodeError:
        st.error("Invalid JSON format in the response.")
        return None
    except Exception as e:
        st.error(f"An unexpected error occurred: {e}")
        return None

if "problem_step" not in st.session_state:
    st.session_state.problem_step = 0   

# --- Main Page ---
st.title("📚❓Problem Solving Tutor")
about = """
**How to use this App**
Replace this placeholder with the actual text.
"""

with st.spinner("Loading the problem..."):
    if st.session_state.get("uploaded_pdf_path") is None:
        st.session_state.uploaded_pdf_path = get_local_file_path("problem1.png")

    filepath = st.session_state.uploaded_pdf_path
    response = multimodal_prompt(filepath, TEXT_PROMPT, file_type="image")

# --- Display the image ---
st.image(filepath, caption="Problem Image", use_container_width=True)

equation = get_equation(response)
st.write(f"**Equation:** {equation}")   

problem_step = st.session_state.problem_step
if problem_step == 0:
    #Show instructions to submit the answer
    st.write("Please write down your answer in a piece of paper.  Take a picture of the paper and submit it in the next step.")
    st.write("Click the button below to proceed.")
    img_file_buffer = st.camera_input("Take a picture of your answer.")

    if img_file_buffer is not None:
        # process the answer
        st.write("Processing your answer...")

       # Save the image to a temporary file
        with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
            temp_file.write(img_file_buffer.read())
            image_path = temp_file.name
            st.write("Image saved to:", image_path) 

            # create the text prompt
            text_prompt = "Use the provided image. The image shoqs, a student's answer to the problem. Evaluate the answer and provide a correct solution. Provide feedback how can the student improve their answer."

            if st.button("Ask Tutor for Feedback"):
                if text_prompt:
                    with st.spinner("AI is thinking..."):
                        response = multimodal_prompt(image_path, text_prompt, file_type="image")
                        st.markdown(response)

                        if st.button("Next"):
                            # Evaluate the response
                            if "Correct" in response:
                                st.write("Correct! 🎉")
                                st.session_state.problem_step = 1
                            else:
                                st.write("Incorrect. 😞")
                                st.session_state.problem_step = 0
                        

    else:
        st.write("Please take a picture of your answer.")


st.markdown("Visit our Hugging Face Space!")
st.markdown("© 2025 WVSU AI Dev Team 🤖 ✨")