Skip to main content

Generate Python docstrings automatically with LLM and syntax trees.

Project description

llm-docsmith

Generate Python docstrings automatically with LLM and syntax trees.

Installation

Install this plugin in the same environment as LLM.

llm install llm-docsmith

Usage

Pass a Python file as argument to llm docsmith:

llm docsmith ./scripts/main.py

The file will be edited to include the generated docstrings.

Options:

  • -m/--model: Use a model other than the configured LLM default model
  • -o/--output: Only show the modified code, without modifying the file
  • -v/--verbose: Verbose output of prompt and response
  • --git: Only update docstrings for functions and classes that have been changed since the last commit
  • --git-base: Git reference to compare against (default: HEAD)
  • --only-missing: Only add docstrings to functions and classes that don't have them yet

Only Missing Mode

The --only-missing flag tells docsmith to only generate docstrings for functions and classes that don't already have one. This is useful when you want to preserve existing docstrings and only add documentation where it's missing:

# Only add docstrings where they are missing
llm docsmith ./scripts/main.py --only-missing

Git Integration

The --git flag enables Git integration, which will only update docstrings for functions and classes that have been changed since the last commit. This is useful for large codebases where you only want to update docstrings for modified code.

# Update docstrings only for changed functions and classes
llm docsmith ./scripts/main.py --git

It's also possible to compare against a different git reference to find changed, for instance the main branch:

# Compare against a specific Git reference
llm docsmith ./scripts/main.py --git --git-base main

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

llm_docsmith-0.3.1.tar.gz (17.7 kB view details)

Uploaded Source

Built Distribution

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

llm_docsmith-0.3.1-py3-none-any.whl (13.2 kB view details)

Uploaded Python 3

File details

Details for the file llm_docsmith-0.3.1.tar.gz.

File metadata

  • Download URL: llm_docsmith-0.3.1.tar.gz
  • Upload date:
  • Size: 17.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for llm_docsmith-0.3.1.tar.gz
Algorithm Hash digest
SHA256 fb83aa3729342d6cddbbd64b56d92f737a20fc9646a28e7ff5e80abc136e3cd3
MD5 03f4a4a220b1948881aa4b23c6967e14
BLAKE2b-256 b1d5c4a630390fdae47adcb7cf0b0dc1eb9ea65dc1b7bede6daf704a75e7cb5b

See more details on using hashes here.

Provenance

The following attestation bundles were made for llm_docsmith-0.3.1.tar.gz:

Publisher: publish.yml on mathpn/llm-docsmith

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file llm_docsmith-0.3.1-py3-none-any.whl.

File metadata

  • Download URL: llm_docsmith-0.3.1-py3-none-any.whl
  • Upload date:
  • Size: 13.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for llm_docsmith-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 1ae958366073aa335200e6cd85560aa96c595efc85167692bf89b907a0c8cefa
MD5 0a36416bf92ce5678b320d7524f93b7e
BLAKE2b-256 94578644ca52ef5077cf5ed2f05b17aa1cc88027da47983d1150a9ad3a90468d

See more details on using hashes here.

Provenance

The following attestation bundles were made for llm_docsmith-0.3.1-py3-none-any.whl:

Publisher: publish.yml on mathpn/llm-docsmith

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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