Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/aigptcode/askyourdocuments

Welcome to the Document QA system! This repository contains the code for a system that allows you to ask questions about your documents and get answers based on their contents. It supports a wide range of document formats, including PDF, Word, Excel, PowerPoint, text files, and even images!
https://github.com/aigptcode/askyourdocuments

ai api assistant chatbot gpt-4 hugging-face huggingface huggingface-transformers microsoft openai openai-api pdf pdf-generation windows word

Last synced: 30 days ago
JSON representation

Host: GitHub
URL: https://github.com/aigptcode/askyourdocuments
Owner: AiGptCode
Created: 2024-03-18T17:15:12.000Z (9 months ago)
Default Branch: main
Last Pushed: 2024-03-24T21:26:40.000Z (9 months ago)
Last Synced: 2024-03-24T22:28:59.941Z (9 months ago)
Topics: ai, api, assistant, chatbot, gpt-4, hugging-face, huggingface, huggingface-transformers, microsoft, openai, openai-api, pdf, pdf-generation, windows, word
Language: Python
Homepage:
Size: 24.4 KB
Stars: 7
Watchers: 2
Forks: 3
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

# 💻 Ask your Documents 🤖

👋 Welcome to the Document QA system! This repository contains the code for a system that allows you to ask questions about your documents and get answers based on their contents. It supports a wide range of document formats, including PDF, Word, Excel, PowerPoint, text files, and even images!

## 🚀 Features

* 💻 Supports a variety of document formats, including PDF, Word, Excel, PowerPoint, text files, and images
* 🤖 Uses the Hugging Face Transformers library to create embeddings for document chunks
* 🔍 Uses the FAISS library to create an index for those embeddings, allowing for efficient similarity search
* 💬 Allows users to ask questions about their documents and get answers based on the contents of those documents
* ⚡️ Uses multiprocessing to parallelize the creation of the index for improved performance

## 📋 Requirements

* Python 3.6 or higher
* The following Python packages:
+ transformers
+ langchain
+ fitz
+ Pillow
+ textract
+ pandas
+ python-pptx
+ concurrent-futures
+ opencv-python (for image support)

## 🔧 Usage

1. Clone this repository to your local machine:
```bash
git clone https://github.com/AiGptCode/AskyourDocuments.git
```
2. Install the required Python packages:
```bash
pip install transformers langchain fitz pillow textract pandas python-pptx opencv-python concurrent-futures
```
3. Set your Hugging Face API key as an environment variable:
```bash
export HUGGINGFACE_API_TOKEN=your-api-key
```
4. Run the `main.py` script and enter the path to the directory containing your documents:
```bash
python AskyourDocuments.py
```
5. Ask a question about your documents and get an answer based on the contents of those documents.

Note: If you want to include images in your search, make sure they are in a supported format (e.g., JPEG, PNG) and are located in the same directory as your other documents.

## 🤝 Contributing

If you would like to contribute to this project, please follow these steps:

1. Fork this repository to your own GitHub account.
2. Create a new branch for your changes:
```bash
git checkout -b my-feature-branch
```
3. Make your changes and commit them:
```bash
git commit -am 'Add some feature'
```
4. Push your changes to your fork:
```bash
git push origin my-feature-branch
```
5. Open a pull request against the original repository.

## 📄 License

This project is licensed under the MIT License.

## 🎉 Acknowledgments