https://github.com/tawfikhammad/inquiro
AI-powered research assistant built with FastAPI. It enables users to read PDF research papers. generate summaries using LLMs, and interact with paper content through an intelligent chat interface.
https://github.com/tawfikhammad/inquiro
fastapi llm rag research-paper summarizer
Last synced: about 2 months ago
JSON representation
AI-powered research assistant built with FastAPI. It enables users to read PDF research papers. generate summaries using LLMs, and interact with paper content through an intelligent chat interface.
- Host: GitHub
- URL: https://github.com/tawfikhammad/inquiro
- Owner: tawfikhammad
- License: apache-2.0
- Created: 2025-04-26T20:14:36.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-11-06T16:10:51.000Z (8 months ago)
- Last Synced: 2025-11-06T16:22:33.756Z (8 months ago)
- Topics: fastapi, llm, rag, research-paper, summarizer
- Language: TypeScript
- Homepage:
- Size: 663 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🧠 Inquiro — Research Assistant API
**Inquiro** is an intelligent research assistant built with **FastAPI**, designed to simplify the management, summarization, and understanding of academic papers. With seamless integration of **LLMs** (Gemini) and **vector databases** (Qdrant), Inquiro allows you to:
- Upload and organize research papers by project
- Automatically generate intelligent summaries
- Chat with the collection of papers content for deeper understanding
- Translate or explain selection text in paper.
- Facilitate notes taking.
- Manage data with MongoDB and Qdrant
---
## Features
- **File Upload**: Upload and validate PDF research papers by project.
- **Auto Summarization**: Extract content and summarize using LLMs.
- **Paper Chat**: Ask questions and receive answers from paper content.
- **Markdown Editing**: View, edit, and update summaries in `.md` format.
- **Modular Architecture**: Clean separation of routes, controllers, models.
- **Translator**: Translate the selection text.
- **MongoDB Integration**: Store project, paper, and summary metadata.
- **Qdrant Vector DB**: Efficient document embedding and retrieval.
---
## Project Structure
```
backend/
├── main.py # FastAPI app entry
├── routes/ # API endpoints
├── controllers/ # Business logic
├── models/ # DB models and schemas
├── AI/
│ ├── LLM/ # LLM providers (Gemini)
│ └── VectorDB/ # Vector DB (Qdrant)
├── utils/ # Utilities for PDFs, paths, enums
└── config/ # App settings and environment
```
## Tech Stack
- **Backend**: FastAPI
- **Database**: MongoDB (via Motor)
- **LLMs**: OpenAI / Cohere / Gemini
- **Vector DB**: Qdrant
- **PDF Processing**: PyMuPDF
- **Async File Handling**: Aiofiles
---
## 🤝 Contributions
PRs are welcome! If you want to contribute or report a bug, please open an issue or submit a pull request.
# This Project is Under Active Developing