📄 AI-Powered PDF Summarizer

🚀 BHUTORIA.AI-Powered PDF Summarizer is a tool that extracts and summarizes research papers from Uploaded PDFs using gemini-1.5-flash. The system provides structured, downloadable summaries to help researchers and professionals quickly grasp key findings.

---

🛠 Features

• 🌐 Upload a research paper pdf to fetch and summarize papers.
• 📑 Extracts technical content (architecture, implementation, results).
• 🔍 Optimized for large text processing with parallel summarization.
• 🎨 Modern UI built with Streamlit.
• 📥 Download summary as a Markdown file.

---

🚀 Tech Stack

Component	Technology
Frontend	Streamlit
Backend	FastAPI
LLM Model	Google Gemma 3
PDF Processing	PyMuPDF (fitz)
Text Chunking	LangChain RecursiveCharacterTextSplitter

---

🎬 Demo

1️⃣ **Upload a pdf from your local device **
2️⃣ Click "Summarize PDF" 🚀
3️⃣ Get a structured summary with technical insights 📝
4️⃣ Download summary as Pdf 📥

---

🔧 Installation & Setup

1️⃣ Clone the Repository

git clone https://github.com/farhan11166/MP2-rag-intraiit
cd MP2-rag-intraiit

2️⃣ Install Dependencies

pip install -r requirements.txt

3️⃣ SET GOOGLE GEMINI AND EXA API KEY in a.env file

GOOGLE_API_KEY=[YOUR-API-KEY] EXA_API_KEY=[YOUR-API-KEY]

### 3️⃣ Start the Backend (FastAPI)

```bash
uvicorn main:app --host 0.0.0.0 --port 8000 --reload

4️⃣ Start the Frontend (Streamlit)

streamlit run frontend.py

---

📜 API Endpoints

🔹 Health Check

GET /health

Response:

{"status": "ok", "message": "FastAPI backend is running!"}

🔹 Summarize

Summarize

POST /summarize/

Request Body:

{
  "filename": "example.pdf",
  "content": "<base64-encoded-pdf>"
}

Response:

{
  "summary": "Structured summary of the research paper..."
}