https://github.com/amirespahbodi/qa_site
api that you send a text to server and asks some question on that text, written in python/fastapi
https://github.com/amirespahbodi/qa_site
fastapi langchain langchain-python python
Last synced: 3 months ago
JSON representation
api that you send a text to server and asks some question on that text, written in python/fastapi
- Host: GitHub
- URL: https://github.com/amirespahbodi/qa_site
- Owner: AmirEspahbodi
- Created: 2024-06-16T11:55:29.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2024-09-19T19:01:04.000Z (8 months ago)
- Last Synced: 2025-01-02T15:50:57.631Z (5 months ago)
- Topics: fastapi, langchain, langchain-python, python
- Language: Python
- Homepage:
- Size: 111 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Question-Answer Website
This project is a fully functional question-answer web application that allows users to upload a file and ask questions about its contents. The system processes the file, extracts the text, and enables users to query the text for specific information.
## How to run sever
```bash
git clone https://github.com/your-username/question-answer-website.git
cd question-answer-website
poetry install
poetry run python main.py
```
## Features
- **File Upload:** Users can upload various document formats.
- **Natural Language Processing:** The system processes uploaded documents and answers user questions based on the content of the file.
- **Asynchronous Web Server:** FastAPI provides a fast, asynchronous backend to handle file uploads and question-answer logic.
- **ChromaDB:** Used to store and index text for efficient querying.
- **Document Parsing:** Utilizes PyPDF to handle PDF files and Python-magic to identify file types.
- **Language Processing:** Leverages LangChain and NLTK for NLP capabilities.
## Technology Stack
- **FastAPI:** Provides the web framework for handling requests and delivering responses asynchronously.
- **LangChain:** Chains together different language models to help answer complex queries.
- **ChromaDB:** Efficient vector database for text indexing and retrieval.
- **PyPDF:** Handles the parsing and extraction of text from PDF files.
- **Python-magic:** Identifies file types for proper handling.
- **NLTK:** Aids in text tokenization and processing for natural language queries.
## How It Works
- **Upload a File**: Users upload a file through the frontend interface.
- **File Parsing**: The backend parses the file to extract the text using PyPDF or another parser based on the file type identified by Python-magic.
- **Text Storage**: The extracted text is stored in ChromaDB, allowing for fast, efficient searches.
- **Ask a Question**: Users can ask questions related to the content of the uploaded file.
- **Answer Generation**: LangChain processes the user's query using NLP techniques, returning the most relevant answer from the document.