Skip to main content

nb4llm

Convert Jupyter notebooks to and from a readable, LLM-friendly text format.

Python 3.9+ License: MIT CI


🚀 Features

  • Convert .ipynb → .txt: Extracts markdown and code cells as readable, chunked blocks.
  • Convert .txt → .ipynb: Reconstructs a notebook from the text format.
  • Language-aware: Preserves code cell language (Python, R, Julia, etc).
  • Robust chunking: Handles nested code fences and markdown.
  • CLI tool: Easy to use from the command line or scripts.
  • Pre-commit, Black, isort, flake8: Modern Python dev workflow.

📦 Installation

pip install -e .
# or, for development:
pip install -e .[dev]

📝 Usage

Convert a notebook to text

nb4llm notebook.ipynb
# Output: notebook.txt

Convert a notebook to a specific text file

nb4llm notebook.ipynb output.txt

Convert text back to a notebook

nb4llm --reverse notebook.txt
# Output: notebook.ipynb

Convert text to a specific notebook file

nb4llm --reverse notebook.txt output.ipynb

Show help

nb4llm --help

🧑‍💻 Example Text Format

# my_notebook.ipynb

```markdown
Some markdown text
# Some code
print(\"Hello, world!\")

---

## 🛠️ Development

### **Run tests**

```bash
pytest tests/

Run formatting and linting

pre-commit run --all-files

Type checking

mypy src/

🧩 Project Structure

nb4llm/
├── src/
│   └── nb4llm/
│       ├── __init__.py
│       ├── cli.py
│       └── converter.py
├── tests/
│   ├── test_cli.py
│   ├── test_converter.py
│   └── conftest.py
├── pyproject.toml
├── .pre-commit-config.yaml
├── .flake8
└── README.md

📝 Contributing

  1. Fork the repo and create a feature branch.
  2. Make your changes and add tests.
  3. Run pre-commit run --all-files and pytest.
  4. Submit a pull request!

📄 License

MIT License. See LICENSE for details.


Built for robust, LLM-friendly notebook processing.


Let me know if you want this written to your README.md or want to tweak any section!

Contact

name: Amber Malpas github: AmberLee2427 email: malpas.1@osu.edu

Metadata

Release files for nb4llm 0.1.3

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

Source distribution (sdist)

Source distribution for nb4llm 0.1.3
File Size Uploaded Provenance
nb4llm-0.1.3.tar.gz 9.1 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for nb4llm 0.1.3
File Interpreter ABI Platform
nb4llm-0.1.3-py3-none-any.whl Python 3 none any Details

Total release size: 16.1 kB

Release files / nb4llm-0.1.3.tar.gz

Download URL nb4llm-0.1.3.tar.gz
Size 9.1 kB
Tags Source
SHA-256 checksum
How to use checksums
62962d1f95cff3ca2d519f352717cb5c8ee9f8fed082adc46eed401fa4539473
BLAKE2b-256 checksum
How to use checksums
c2a76321afaa5b3cbcfe144a2827ac0aeec7cfcc7c67dda3548e158631ccce01
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.11.13

Release files / nb4llm-0.1.3-py3-none-any.whl

Download URL nb4llm-0.1.3-py3-none-any.whl
Size 7.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e51e3db6154d2982009667aa485e989728c577e6f4671cd9a18cf5f11d3cc32b
BLAKE2b-256 checksum
How to use checksums
878f560f231d35e86054fe452522029030f53cd5218e35e6617767fbd24f55d9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.11.13

Security for nb4llm 0.1.3

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

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.

Release history Release notifications | RSS feed

This release

0.1.3 This release

2 release files No provenance

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