https://github.com/uzair-manzoor/query-docs-backend
The QueryDocs backend is built with FastAPI, handles PDF uploads, extracts text using PyMuPDF, and processes queries with LangChain's NLP capabilities. It stores document metadata in a SQLite database, ensuring efficient document management and accurate answers to user questions.
https://github.com/uzair-manzoor/query-docs-backend
fastapi fastapi-sqlalchemy langchain llms python-3 rander
Last synced: 3 months ago
JSON representation
The QueryDocs backend is built with FastAPI, handles PDF uploads, extracts text using PyMuPDF, and processes queries with LangChain's NLP capabilities. It stores document metadata in a SQLite database, ensuring efficient document management and accurate answers to user questions.
- Host: GitHub
- URL: https://github.com/uzair-manzoor/query-docs-backend
- Owner: Uzair-Manzoor
- License: mit
- Created: 2024-05-27T19:39:44.000Z (about 1 year ago)
- Default Branch: dev
- Last Pushed: 2024-06-15T06:36:20.000Z (about 1 year ago)
- Last Synced: 2025-02-14T08:33:16.306Z (4 months ago)
- Topics: fastapi, fastapi-sqlalchemy, langchain, llms, python-3, rander
- Language: Python
- Homepage: https://query-docs-backend.onrender.com/
- Size: 2.1 MB
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
## Setup Instructions
### Backend
1. Navigate to the `backend` directory.
2. Install dependencies: `pip install -r requirements.txt`
3. Run the application: `uvicorn main:app --reload`
### Frontend
1. Navigate to the `frontend` directory.
2. Install dependencies: `npm install`
3. Run the application: `npm start`
### 🔘 Follow the link for [Frontend Source Code](https://github.com/Uzair-Manzoor/query-docs-frontend.git)
## API Documentation
### Upload PDF
- Endpoint: `/upload`
- Method: `POST`
- Body: `file` (form-data)
### Ask Question
- Endpoint: `/ask`
- Method: `POST`
- Body: `filename`, `question`
## Application Overview
The application allows users to upload PDF documents and ask questions about their content. The backend uses FastAPI to handle requests and LangChain for NLP processing. The frontend is built with React.js.