Metadata-Version: 2.1
Name: DocumentsReader
Version: 1.1.5
Summary: A package to read and process documents
Home-page: 
Author: Your Name
Author-email: your.email@example.com
License: MIT
Description-Content-Type: text/markdown
Requires-Dist: WeasyPrint (==62.1)
Requires-Dist: Pillow (==10.1.0)
Requires-Dist: python-docx (==1.1.2)
Requires-Dist: python-pptx (==0.6.23)
Requires-Dist: openpyxl (==3.1.2)
Requires-Dist: pdf2image (==1.17.0)
Requires-Dist: torch (==2.1.2)
Requires-Dist: torchvision (==0.16.2)
Requires-Dist: transformers (==4.40.0)
Requires-Dist: sentencepiece (==0.1.99)
Requires-Dist: accelerate (==0.30.1)
Requires-Dist: bitsandbytes (==0.43.1)

```markdown
# DocumentsReader

# Document to JSON Converter

This project provides a script to extract data in json format from various types of documents (PDF, DOCX, TXT, PPT, Excel, HTML) using a pre-trained model.

## Requirements

Before you begin, ensure you have the following software installed:

- Python 3.10+
- pip (Python package installer)

## Installation

1. Install the necessary Python package:

    ```sh
    pip install documentsreader
    ```

2. Install Poppler (required for `pdf2image`):

    - **Ubuntu/Debian**:
      ```sh
      sudo apt-get install poppler-utils
      ```
    - **macOS** (using Homebrew):
      ```sh
      brew install poppler
      ```
## Example

1. The script will load document, apply the pre-trained model, and generate JSON responses.

- **Documents Processing**:
  - The script loads a pre-trained model using the `transformers` library.
  - It generates a JSON response using the model.
  - The responses can be printed or saved for further analysis.

This README provides an overview of how to set up and use the scripts for to generating JSON data from these documents using a pre-trained model.
```
