app.py

import os
import pdfplumber
import gradio as gr
from dotenv import load_dotenv
from groq import Groq

# Load environment variables
load_dotenv()
GROQ_API_KEY = os.getenv("GROQ_API_KEY")
print("Groq API Key:", GROQ_API_KEY)  # TEMP: Check if it's loaded

# Instantiate Groq client
client = Groq(api_key=GROQ_API_KEY)

# Function to extract text from PDF
def extract_text_from_pdf(pdf_file):
    text = ""
    with pdfplumber.open(pdf_file.name) as pdf:
        for page in pdf.pages:
            page_text = page.extract_text()
            if page_text:
                text += page_text
    return text

# Split text into manageable chunks (by character count)
def split_text_into_chunks(text, max_chars=2000):
    words = text.split()
    chunks = []
    chunk = ""

    for word in words:
        if len(chunk) + len(word) + 1 <= max_chars:
            chunk += " " + word
        else:
            chunks.append(chunk.strip())
            chunk = word
    if chunk:
        chunks.append(chunk.strip())

    return chunks

# Summarize a single chunk using Groq
def summarize_chunk(chunk):
    prompt = f"Summarize the following PDF section:\n\n{chunk}"
    try:
        response = client.chat.completions.create(
            messages=[{"role": "user", "content": prompt}],
            model="llama3-8b-8192",
        )
        return response.choices[0].message.content.strip()
    except Exception as e:
        return f"Error during summarization: {e}"

# Main summarization function
def summarize_pdf(pdf_file):
    text = extract_text_from_pdf(pdf_file)
    if not text.strip():
        return "No extractable text found in the PDF."

    chunks = split_text_into_chunks(text, max_chars=2000)
    summaries = []

    for i, chunk in enumerate(chunks):
        summary = summarize_chunk(chunk)
        summaries.append(f"🔹 **Section {i+1} Summary:**\n{summary}\n")

    final_summary = "\n".join(summaries)
    return final_summary

# Gradio interface
iface = gr.Interface(
    fn=summarize_pdf,
    inputs=gr.File(label="Upload PDF", file_types=[".pdf"]),
    outputs="text",
    title="📄 PDF Summarizer with Groq",
    description="Upload a large PDF and get section-wise AI summaries using Groq's LLaMA3 model."
)

if __name__ == "__main__":
    iface.launch()