https://github.com/arjunprabhulal/gemma3_pdf_summarizer
A high-performance PDF summarization tool powered by Google's Gemma 3 LLM. Features parallel processing, async operations, and intelligent chunking for technical paper analysis. Built with FastAPI, Streamlit, and Ollama.
https://github.com/arjunprabhulal/gemma3_pdf_summarizer
fastapi gemma3 google-cloud-platform ollama pdf-summarizer streamlit
Last synced: 3 months ago
JSON representation
A high-performance PDF summarization tool powered by Google's Gemma 3 LLM. Features parallel processing, async operations, and intelligent chunking for technical paper analysis. Built with FastAPI, Streamlit, and Ollama.
- Host: GitHub
- URL: https://github.com/arjunprabhulal/gemma3_pdf_summarizer
- Owner: arjunprabhulal
- Created: 2025-04-05T02:14:32.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-04-12T22:25:42.000Z (over 1 year ago)
- Last Synced: 2025-12-28T11:26:35.753Z (7 months ago)
- Topics: fastapi, gemma3, google-cloud-platform, ollama, pdf-summarizer, streamlit
- Language: Python
- Homepage:
- Size: 160 KB
- Stars: 20
- Watchers: 2
- Forks: 7
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 📄 AI-Powered PDF Summarizer
🚀 **AI-Powered PDF Summarizer** is a tool that extracts and summarizes **research papers** from **ArXiv PDFs** using **Ollama (Gemma 3 LLM)**. The system provides structured, downloadable summaries to help researchers and professionals quickly grasp key findings.
---
## 🛠 Features
- 🌐 **Input an ArXiv PDF URL** 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](https://streamlit.io/) |
| **Backend** | [FastAPI](https://fastapi.tiangolo.com/) |
| **LLM Platform** | [Ollama](https://ollama.com/) |
| **LLM Model** | [Google Gemma 3](https://developers.googleblog.com/en/introducing-gemma3/) |
| **PDF Processing** | [PyMuPDF (fitz)](https://pymupdf.readthedocs.io/) |
| **Text Chunking** | [LangChain RecursiveCharacterTextSplitter](https://python.langchain.com/docs/modules/data_connection/document_transformers/text_splitters/) |
---
## 🎬 Demo
1️⃣ **Enter an ArXiv PDF URL**
2️⃣ **Click "Summarize PDF"** 🚀
3️⃣ **Get a structured summary** with **technical insights** 📝
4️⃣ **Download as Markdown** 📥
---
## 🔧 Installation & Setup
### 1️⃣ Clone the Repository
```bash
git clone https://github.com/arjunprahulal/gemma3_pdf_summarizer.git
cd gemma3_pdf_summarizer
```
### 2️⃣ Install Dependencies
```bash
pip install -r requirements.txt
```
### 3️⃣ Install Ollama and Gemma 3 LLM
Install Ollama - MacOS/Linux
```bash
curl -fsSL https://ollama.com/install.sh | sh
```
Download Gemma 3 Model
```bash
ollama pull gemma3:27b
```
### 3️⃣ Start the Backend (FastAPI)
```bash
uvicorn main:app --host 0.0.0.0 --port 8000 --reload
```
### 4️⃣ Start the Frontend (Streamlit)
```bash
streamlit run frontend.py
```
---
## 📜 API Endpoints
### 🔹 Health Check
```http
GET /health
```
Response:
```json
{"status": "ok", "message": "FastAPI backend is running!"}
```
### 🔹 Summarize
Summarize an ArXiv Paper
```
POST /summarize_arxiv/
```
Request Body:
```
{
"url": "https://arxiv.org/pdf/2401.02385.pdf"
}
```
Response:
```
{
"summary": "Structured summary of the research paper..."
}
```