https://github.com/mayankdiwate/pdfgpt
PDFgpt is a document analysis app that allows users to upload PDFs and interact with them through natural language queries. Built with React, TypeScript, and Vite on the frontend, and FastAPI, LangChain, and PostgreSQL on the backend.
https://github.com/mayankdiwate/pdfgpt
fastapi langchain openai postgresql python reactjs tailwindcss typescript vite
Last synced: 3 months ago
JSON representation
PDFgpt is a document analysis app that allows users to upload PDFs and interact with them through natural language queries. Built with React, TypeScript, and Vite on the frontend, and FastAPI, LangChain, and PostgreSQL on the backend.
- Host: GitHub
- URL: https://github.com/mayankdiwate/pdfgpt
- Owner: MayankDiwate
- Created: 2024-11-12T13:06:53.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-13T10:34:18.000Z (over 1 year ago)
- Last Synced: 2025-01-13T20:38:15.443Z (over 1 year ago)
- Topics: fastapi, langchain, openai, postgresql, python, reactjs, tailwindcss, typescript, vite
- Language: TypeScript
- Homepage: https://pdf-gpt-client.vercel.app
- Size: 56.6 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
PDFgpt
**Description**:
PDFGPT is a web application that allows users to upload PDF documents and interact with them using natural language queries. Leveraging a combination of AI and language processing, the app can analyze the content of uploaded PDFs and provide users with detailed responses, summaries, or insights from the document. This application uses a React-based frontend, powered by TypeScript and Vite, and a FastAPI backend that integrates LangChain for natural language processing and PostgreSQL for data storage.
---
### Features
- **PDF Upload & Processing**: Users can upload PDFs for analysis.
- **Natural Language Querying**: Query the document with natural language for insights, summaries, or answers.
- **Interactive Chat Interface**: An easy-to-use interface for seamless interactions.
- **Efficient & Scalable**: Built with FastAPI and PostgreSQL to ensure speed and scalability.
### Tech Stack
- **Client**: React, TypeScript, Vite
- **Server**: FastAPI, LangChain
- **Database**: PostgreSQL
---
### Setup and Installation
1. **Clone the repository**:
```bash
git clone
cd pdfgpt
```
2. **Client Setup**:
- Navigate to the client folder:
```bash
cd client
```
- Install dependencies:
```bash
npm install
```
- Start the development server:
```bash
npm run dev
```
3. **Server Setup**:
- Navigate to the server folder:
```bash
cd ../server
```
- Create a virtual environment and install dependencies:
```bash
python -m venv env
source env/bin/activate # For MacOS/Linux
env\Scripts\activate # For Windows
pip install -r requirements.txt
```
- Start the FastAPI server:
```bash
uvicorn main:app --reload
```
4. **Database Setup**:
- Ensure PostgreSQL is installed and running.
- Create a new PostgreSQL database and update the connection details in the server configuration.
5. **Run the Application**:
- The client should now be running at `http://localhost:5173` and the server at `http://localhost:8000`.
---
### Usage
1. Open the frontend application and upload a PDF document.
2. Use the chat interface to ask questions or request summaries of the document.
### Future Enhancements
- Add support for multiple document formats.
- Implement user authentication.
- Add analytics for user queries.
---
### Contributing
Feel free to open issues or submit pull requests with improvements or bug fixes.
---
### License
This project is licensed under the MIT License.