import os
import gradio as gr
import asyncio
from langchain_core.prompts import PromptTemplate
from langchain_community.output_parsers.rail_parser import GuardrailsOutputParser
from langchain_community.document_loaders import PyPDFLoader
from langchain_google_genai import ChatGoogleGenerativeAI
import google.generativeai as genai
from langchain.chains.question_answering import load_qa_chain  # Import load_qa_chain


async def initialize(file_path, question):
    genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
    model = genai.GenerativeModel('gemini-pro')
    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
    
    # Refined prompt template to encourage precise and concise answers
    prompt_template = """Answer the question precisely and concisely using the provided context. Avoid any additional commentary or system messages.
                          If the answer is not contained in the context, respond with "answer not available in context".
                          
                          Context:
                          {context}
                          
                          Question:
                          {question}
                          
                          Answer:
                        """
    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
    
    if os.path.exists(file_path):
        pdf_loader = PyPDFLoader(file_path)
        pages = pdf_loader.load_and_split()
        context = "\n".join(f"Page {i+1}: {page.page_content}" for i, page in enumerate(pages[:30]))
        stuff_chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
        
        # Use ainvoke to get the result
        stuff_answer = await stuff_chain.ainvoke({"input_documents": pages, "question": question, "context": context})
        
        # Access the correct key for the answer
        answer = stuff_answer.get('output_text', '').strip()

        # Extract the page number where the context was found
        sources = []
        for i, page in enumerate(pages):
            if question.lower() in page.page_content.lower():
                sources.append(f"Page {i+1}")

        if sources:
            source_str = f" (Source: {', '.join(sources)})"
        else:
            source_str = " (Source: Not found in specific page)"

        # Add the clickable link to the source
        file_name = os.path.basename(file_path)
        source_link = f"[{file_name}](file://{os.path.abspath(file_path)})"
        return f"{answer} {source_str} - [Document: {source_link}]"
    else:
        return "Error: Unable to process the document. Please ensure the PDF file is valid."

# Define Gradio Interface
input_file = gr.File(label="Upload PDF File")
input_question = gr.Textbox(label="Ask about the document")
output_text = gr.Textbox(label="Answer - GeminiPro")

async def pdf_qa(file, question):
    answer = await initialize(file.name, question)
    return answer

# Create Gradio Interface with share=True to enable a public link
gr.Interface(fn=pdf_qa, inputs=[input_file, input_question], outputs=output_text, title="PDF Question Answering System", description="Upload a PDF file and ask questions about the content.").launch(share=True)