Skip to main content

LLM fragment loader which converts various formats to Markdown.

Project description

llm-fragments-markitdown

PyPI Changelog Tests License

LLM fragment loader which converts various formats to Markdown.

Installation

Install this plugin in the same environment as LLM.

llm install llm-fragments-markitdown

Usage

Use the fragment loader like this:

llm -f md:path/to/file.html
llm -f md:https://simonwillison.net/2025/Apr/7/long-context-llm/

This will use the MarkItDown library to convert the argument into Markdown.

While this supports various formats out-of-the-box, more can be added as optional dependencies, for example:

llm install markitdown[all]  # Installs all optional dependencies
llm install markitdown[pdf, youtube-transcription]  # Installs just the PDF and YouTube transcript readers.

Development

To contribute to this tool, use uv. The following command will establish the venv and run tests:

uv run pytest

To run llm-fragments-markitdown locally, use:

uv run llm-fragments-markitdown

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_fragments_markitdown-0.1.0.tar.gz (40.2 kB view details)

Uploaded Source

Built Distribution

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

llm_fragments_markitdown-0.1.0-py3-none-any.whl (6.7 kB view details)

Uploaded Python 3

File details

Details for the file llm_fragments_markitdown-0.1.0.tar.gz.

File metadata

  • Download URL: llm_fragments_markitdown-0.1.0.tar.gz
  • Upload date:
  • Size: 40.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for llm_fragments_markitdown-0.1.0.tar.gz
Algorithm Hash digest
SHA256 3a890424f1bc5fe7e6c987a5446f0e499b1b726bebeb89d89ea72035763ff076
MD5 a619d9c38ccdefe1cd5dad9ae26b4d09
BLAKE2b-256 55f46244331cadd7795be64ac6186e173b56e1ecd3debf7200fce0e7978e34a6

See more details on using hashes here.

Provenance

The following attestation bundles were made for llm_fragments_markitdown-0.1.0.tar.gz:

Publisher: publish.yml on wolfmanstout/llm-fragments-markitdown

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_fragments_markitdown-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for llm_fragments_markitdown-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b7498025904fea13aa79f12f60d17cadbd5a76cf8a54892c0561cbac33a0c182
MD5 5cf17b196de0d3e0d7329cff41c657df
BLAKE2b-256 946dd8197ffe92c69342c95b929067abfabb71ecf8a4b3d3e8660f3e28195ee2

See more details on using hashes here.

Provenance

The following attestation bundles were made for llm_fragments_markitdown-0.1.0-py3-none-any.whl:

Publisher: publish.yml on wolfmanstout/llm-fragments-markitdown

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