import google.generativeai as genai
from PIL import Image
from dotenv import load_dotenv
import os
load_dotenv()

genai.configure(api_key="AIzaSyCo0UmOYwiSKUD7-cCVg94M4U1xIKeoS00")
def extract_questions_from_image(image_path):
    image = Image.open(image_path)
    model = genai.GenerativeModel("gemini-1.5-flash")
    prompt = (
        "Analyze the provided image and extract all the questions present in it. "
        "Return only the extracted questions in a structured format, as follows:\n\n"
        "**Output Format:**\n"
        "Q1: [First question]\n"
        "Q2: [Second question]\n"
        "Q3: [Third question]\n"
        "... \n\n"
        "If there are no questions in the image, return 'None' without any additional text."
    )
    response = model.generate_content([image, prompt])
    return response.text.strip()

from PyPDF2 import PdfReader
import google.generativeai as genai

def extract_questions_from_pdf(pdf_path):
    # Read text from the PDF
    pdf_reader = PdfReader("sst.pdf")
    text = "\n".join([page.extract_text() for page in pdf_reader.pages if page.extract_text()])
    
    # Initialize the AI model
    model = genai.GenerativeModel("gemini-1.5-flash")
    prompt = (
        "Analyze the provided text and extract all the questions present in it. "
        "Return only the extracted questions in a structured format, as follows:\n\n"
        "**Output Format:**\n"
        "Q1: [First question]\n"
        "Q2: [Second question]\n"
        "Q3: [Third question]\n"
        "... \n\n"
        "If there are no questions in the text, return 'None' without any additional text."
    )
    
    # Generate response
    response = model.generate_content([text, prompt])
    return response.text.strip()

file_path = "data/sst.pdf"  # Change this to your file path
if file_path.lower().endswith((".png", ".jpg", ".jpeg")):
    result = extract_questions_from_image(file_path)
elif file_path.lower().endswith(".pdf"):
    result = extract_questions_from_pdf(file_path)
else:
    result = "Unsupported file format. Please use PNG, JPG, or PDF."
# Print the extracted questions
qw = result.split("\n")

from openai import OpenAI
client = OpenAI(
        api_key=os.getenv('API_KEY'),
        base_url=os.getenv('GENERATOR_BASE_URL'),
)
prompt = """
Analyze the following sentence and classify it according to Bloom's Taxonomy levels. 
Return the results as a probability distribution where the sum of all 6 levels equals 1.

Bloom's Taxonomy Levels:
1. Remembering: Recall facts and basic concepts
2. Understanding: Explain ideas or concepts
3. Applying: Use information in new situations
4. Analyzing: Draw connections among ideas
5. Evaluating: Justify a stand or decision
6. Creating: Produce new or original work

For the given sentence, provide your assessment in JSON format with the following structure:
{{
    "remembering": float,
    "understanding": float,
    "applying": float,
    "analyzing": float,
    "evaluating": float,
    "creating": float
}}

Ensure that:
- Each value is between 0 and 1
- The sum of all six values equals exactly 1
- The distribution reflects the cognitive level required by the sentence

Sentence to analyze: "{input_sentence}"

Return only the JSON output without any additional explanation or commentary.
"""

import json

# iterate through q1 and pass it to get response
for i in qw:
    formatted_prompt = prompt.format(input_sentence=i)
    response = client.chat.completions.create(
        model=os.getenv("MODEL_NAME"),
        messages=[{"role": "user", "content": formatted_prompt}]
    )
    
    # Extract the content from the response
    response_content = response.choices[0].message.content
    
    # Clean the response (remove markdown code blocks if present)
    json_str = response_content.strip().replace('```json', '').replace('```', '').strip()
    
    try:
        # Parse the JSON string
        bloom_scores = json.loads(json_str)
        
        print("\n")
        print("sentence:", i)
        print("Bloom Score:")
        print(json.dumps(bloom_scores, indent=4))  # Pretty print the JSON
    except json.JSONDecodeError as e:
        print(f"Error parsing JSON: {e}")
        print("Raw response:", response_content)