https://github.com/kowshik24/pineconepdfextractor

PineconePDFExtractor is a Python library for extracting text from PDF files for pinecone.
https://github.com/kowshik24/pineconepdfextractor

Last synced: 25 days ago
JSON representation

PineconePDFExtractor is a Python library for extracting text from PDF files for pinecone.

• Host: GitHub
• URL: https://github.com/kowshik24/pineconepdfextractor
• Owner: kowshik24
• License: other
• Created: 2024-01-20T18:25:12.000Z (12 months ago)
• Default Branch: main
• Last Pushed: 2024-01-22T13:50:05.000Z (12 months ago)
• Last Synced: 2024-04-23T23:54:34.694Z (9 months ago)
• Language: Python
• Size: 13.7 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# PineconePDFExtractor

PineconePDFExtractor is a Python library for extracting text from PDF files for pinecone.

## Installation

Use the package manager [pip](https://pip.pypa.io/en/stable/) to install PineconePDFExtractor.

## Google Colab

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1dTGaIHgq5KtV06Sno5-4EGUwQiiKXfbE?usp=sharing)

```bash

pip install PineconePDFExtractor

```

## Check the latest version here:

https://pypi.org/project/PineconePDFExtractor/

## Usage

```python

from pdf.PineconePDFExtractor import PdfProcessor

# Create a PineconePDFExtractor instance with a batch size of 200

extractor = PdfProcessor(200)

# Process a list of PDF files

result = extractor.process_files(['file1.pdf', 'file2.pdf'])

# The result is a dictionary with the batch size and a list of documents

# Each document is a dictionary with the id (file name without extension), metadata (number of pages), source (file path), and text (extracted text)

## Example result

# {

#   'batch_size': 200,

#   'documents': [

#     {

#       'id': 'file1',

#       'metadata': {

#         'pages': 1

#       },

#       'source': 'file1.pdf',

#       'text': 'This is the extracted text from file1.pdf'

#     },

#     {

#       'id': 'file2',

#       'metadata': {

#         'pages': 2

#       },

#       'source': 'file2.pdf',

#       'text': 'This is the extracted text from file2.pdf'

#     }

#   ]

# }