Skip to main content

library for extracting reference from documents

Project description

PDF Reference Extraction and Verification Library

This library is designed to extract references from a PDF file, check them against the Semantic Scholar database, and save the results to a Markdown file.

Overview

The library performs the following steps:

  1. Extract Text from PDF: Reads the content of a PDF file and extracts the text.
  2. Split Text into Chunks: Splits the extracted text into smaller chunks to manage large texts efficiently.
  3. Extract References: Uses the OpenAI API to extract references from the text.
  4. Save References: Saves the extracted references to a Markdown file.
  5. Check References in Semantic Scholar: (Optional) Checks if the extracted references are present in the Semantic Scholar database.

Installation and Setup

To install the required dependencies, you can use the following command:

rye sync

Ensure you have a .env file in the root directory of your project with the following content:

OPENAI_API_KEY="YOUR_OPENAI_KEY"
SEMANTIC_SCHOLARE_API_KEY="YOUR_SEMANTIC_SCHOLAR_KEY"

Usage

To use the library, ensure you have the required environment variables set and run the script. The extracted references will be saved to a Markdown file named references.md.

Example

Here is an example of how to use the library:

import logging
import os
from dotenv import load_dotenv
from biblio.find_reference import process_pdf

logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')

load_dotenv()

def main():
    """
    Main function that processes a PDF, extracts text, and saves the references.
    """
    pdf_path = 'test/558779153.pdf'
    references_output_path = 'references.md'

    openai_api_key = os.getenv('OPENAI_API_KEY')
    semantic_scholar_api_key = os.getenv('SEMANTIC_SCHOLARE_API_KEY')

    if not openai_api_key:
        raise EnvironmentError("OPENAI_API_KEY environment variable not set.")
    if not semantic_scholar_api_key:
        raise EnvironmentError("SEMANTIC_SCHOLARE_API_KEY environment variable not set.")

    logging.debug("Starting PDF processing...")

    process_pdf(pdf_path, references_output_path, openai_api_key, semantic_scholar_api_key)

    logging.debug("Processing completed.")

if __name__ == "__main__":
    main()

Contributing

We welcome contributions to this project. If you would like to contribute, please follow these steps:

  1. Fork the repository.
  2. Create a new branch for your feature or bugfix.
  3. Make your changes.
  4. Submit a pull request with a detailed description of your changes.

License

This project is licensed under the MIT License. See the LICENSE file for more information.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

scrapebiblio-0.0.1.tar.gz (87.5 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

scrapebiblio-0.0.1-py3-none-any.whl (9.6 kB view details)

Uploaded Python 3

File details

Details for the file scrapebiblio-0.0.1.tar.gz.

File metadata

  • Download URL: scrapebiblio-0.0.1.tar.gz
  • Upload date:
  • Size: 87.5 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.12.3

File hashes

Hashes for scrapebiblio-0.0.1.tar.gz
Algorithm Hash digest
SHA256 1b776617aa011300cd2d34dee64e4910f50c17788227f15e38b57d78872432f3
MD5 2b697582d29811923494c3bcf164d13d
BLAKE2b-256 ee76150aff0953d47d5ec30f3d2d4474ca71eac65305aff9e4b935beeb1e38b2

See more details on using hashes here.

File details

Details for the file scrapebiblio-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: scrapebiblio-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 9.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.12.3

File hashes

Hashes for scrapebiblio-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 657bfa6f277ebd0eb8ebff1ea8d0c6932ee42379e408e97d6247e580056a4b39
MD5 406a0d8eca4169b33a5d5c35f36589e6
BLAKE2b-256 4fc5ef18f096e470ae20ad9ccee7dfa14119125608c4ddaf91b02d182c5d063a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page