Skip to main content

🔬📖 X-ray GPT

PyPI version Release Building Code style: black

Generate kindle-like X-ray for e-books with LLM

🚀 Usage

pip install xraygpt
python -m xraygpt [epub_file]

🤖 LLM Support

Current this tool only support OpenAI (or compatible API like DeepSeek, Kimi, etc.) and Azure OpenAI by setting environment variables.

You can config following environment variables to use different LLM service:

  • OPENAI_API_BASE: OpenAI API or other compatible API base URL
  • OPENAI_API_KEY: OpenAI API key
  • OPENAI_API_VERSION: OpenAI API version
  • AZURE_OPENAI_ENDPOINT: Use Azure OpenAI endpoint instead of standard OpenAI

Model name can be set by command line argument --chat_model and --embedding_model.

📚 E-book Support

Currently only support .epub format. Output format is a .json file as WordDumb style. You can import this file manualy via Calibre. First select the book and click "Open book Folder". Then create/replace worddumb-custom-x-ray.json with the generated json file.

Generating X-Ray DB file is in progress.

🧑‍💻 Dev Setup

pip install -e '.[dev]'

🎩 Static analysis

make format

Metadata

Release files for xraygpt 0.2.10.post0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for xraygpt 0.2.10.post0
File Size Uploaded Provenance
xraygpt-0.2.10.post0.tar.gz 18.2 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for xraygpt 0.2.10.post0
File Interpreter ABI Platform
xraygpt-0.2.10.post0-py3-none-any.whl Python 3 none any Details

Total release size: 38.6 kB

Release files / xraygpt-0.2.10.post0.tar.gz

Download URL xraygpt-0.2.10.post0.tar.gz
Size 18.2 kB
Tags Source
SHA-256 checksum
How to use checksums
aa7c3fc6e294d4588400e0579bc1d803d4ff74a34a38067648939f9831465323
BLAKE2b-256 checksum
How to use checksums
9622bf5a5dc066924dcaecafaff8a225fe268e0ecf35fe13feeca3a68a059e21
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 24, 2025.

Transparency log

Release files / xraygpt-0.2.10.post0-py3-none-any.whl

Download URL xraygpt-0.2.10.post0-py3-none-any.whl
Size 20.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b867410997fc3768c4ca272c5c1a6ef57067a80c2768ddd5bb5e9c77db50a87f
BLAKE2b-256 checksum
How to use checksums
d3200a7cb70a2496ea2d32a5eb96ef88bbc52070a77e8148063aeaddd859f7d4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 24, 2025.

Transparency log

Security for xraygpt 0.2.10.post0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for xraygpt-0.2.10.post0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 24, 2025.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page