Skip to main content

Natural Language Notebooks

This project has been archived.

The maintainers of this project have marked this project as archived. No new releases are expected.

Project description

NLBook: Natural Language Notebooks.

Authors:

Luca de Alfaro, dealfaro@acm.org

Overview

Natural Language Notebooks (NLBook) allow you to create notebooks where the cells are written in natural language. The natural language is automatically converted to code via AI, and executed. The results of the execution are then displayed below the natural language cell.

In NLBooks, natural language is the programming language. The goal of NLBooks is to allow users to create and share notebooks in natural language, without having to write code, or understand the code that is shared with them. Actions to be performed are described in natural language, and the natural languate is retained, so users can edit it, improve it, and share it. We are building methods for verifying that the code implementation is faithful to the natural language description, so that users can trust the notebooks they receive from others.

Natural Language Notebooks have two type of cells:

  • Action cells, where the user describes in natural language the action to be performed (e.g., "Load the dataset from file data.csv and display the first 10 rows"). The system converts the description to code, executes it, and displays the results below the cell.

  • Comment cells, where the user can add comments, section headers, and so forth, using markdown syntax.

Differently from other notebook systems, NLBooks are executed from start to end: random cell execution order, as in Jupyter notebooks, is not allowed. This ensures that the results are obtained in the same order in which a human reader would read the notebook.

This project is in an early stage of development.

Running NLBook

nlbook path/to/notebook.nlb

(where .nlb is a Natural Language Notebook file; you can use other extensions if you wish). For a list of command-lien options, do:

nlbook --help

If you want to be able to generate or check code from explanations, you need to add a Gemini API key in the settings (click on the gear icon in the top-right corner of the web interface).

Development

Run with:

python -m nlbook.main --debug

Running with the VSCode launch.json does not work, due to a VScode bug/quirk. See DEVELOP.md for development instructions, and see TODO.md for planned features.

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

nlbook-0.0.5.tar.gz (894.5 kB view details)

Uploaded Source

Built Distribution

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

nlbook-0.0.5-py3-none-any.whl (900.1 kB view details)

Uploaded Python 3

File details

Details for the file nlbook-0.0.5.tar.gz.

File metadata

  • Download URL: nlbook-0.0.5.tar.gz
  • Upload date:
  • Size: 894.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for nlbook-0.0.5.tar.gz
Algorithm Hash digest
SHA256 581ca0f2584a27027e891aacb14b431b748b0d5f1a0aeabc445a680bf4ac977a
MD5 65a4b1810561f32a6dadcfb3bae90c61
BLAKE2b-256 2d394d8c4abaffd66eb17a5a84892836b0d642f37b3ff356136a928a6c9fe3d0

See more details on using hashes here.

File details

Details for the file nlbook-0.0.5-py3-none-any.whl.

File metadata

  • Download URL: nlbook-0.0.5-py3-none-any.whl
  • Upload date:
  • Size: 900.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for nlbook-0.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 9def528f8cb33a5787891a9027724831a04e134b3f952d3bc4ff6e90028da374
MD5 fb0b10a087cdb037235d6b64f26e317b
BLAKE2b-256 39cc8a2e37bf714035dc753adf8a5f01b544723573e0760511189228cdc34d11

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