| Name | llms-txt-action JSON |
| Version |
1.0.2
JSON |
| download |
| home_page | None |
| Summary | GitHub Action to make documentation more accessible to LLMs. |
| upload_time | 2025-01-07 22:10:26 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.9 |
| license | MIT |
| keywords |
documentation
github-action
llm
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# llms-txt-actions
[](https://github.com/demodrive-ai/llms-txt-action/releases)
[](https://github.com/demodrive-ai/llms-txt-action/actions)
[](LICENSE)
### Make your documentation LLM friendly.
This Github action/CLI tool can automatically generate markdown (.md) files for each endpoint in your documentation as per the standard proposed by [answer.ai](https://www.answer.ai/), for more details read: https://llmstxt.org/.
It completely runs locally be default, by passing MODEL_API_KEY one can choose to engage hosted cloud AI services to generate page summaries.
## Features
- 📄 **Content Processing**: Generate LLM-ready markdown (.md) files from popular document frameworks such as [Readthedocs](https://readthedocs.io/), [MKDocs](https://www.mkdocs.org/), [Sphinx](https://www.sphinx-doc.org/en/master/index.html#) and more.
- 🌈 **All Formats** : Can process HTML, PDF, Images, DOCX, PPTX, XLSX (thanks to [docling](https://github.com/DS4SD/docling)) and convert them to Markdown. (coming soon)
- 0️⃣ **Zero Config**: Works out of the box for most file based documentation framework.
- 💾 **Generate Summaries**: Using LLMs, we generate concise summary of each page.
- 📕 **BYO-Model**: Thanks to [litellm](https://github.com/BerriAI/litellm), you can use upto 150 models like OpenAI, VertexAI, Cohere, Anthropic.
## Quick Start
There are two ways to access this library.
1. Add this to your GitHub workflow:
```yaml
steps:
- name: Make docs LLM ready
uses: demodrive-ai/llms-txt-action@v1
# OR You can choose to use an AI model to generate summaries, its completely optional.
steps:
- name: Make docs LLM ready
env:
MODEL_API_KEY: ${{ secrets.MODEL_API_KEY }}
uses: demodrive-ai/llms-txt-action@v1
# any other inputs you would like to set.
```
OR
You can use it outside of Github Action.
```bash
# python 3.9 or above
pip install llms-txt-action
llms-txt --docs-dir site/
# The first run takes a while as it downloads models files from the intrnet.
```
## Input Parameters
| Parameter | Required | Default | Description |
|---------------------|----------|------------|----------------------------------------------|
| `docs_dir` | No | `site/` | Documentation output directory |
| `skip_llms_txt` | No | `true` | Skip llms.txt file generation. |
| `skip_llms_full_txt` | No | `true` | skip llms-full.txt file generation. |
| `skip_md_files` | No | `true` | Skip generation of markdown files |
| `llms_txt_name` | No | `llms.txt` | Name of the llms.txt output file |
| `llms_full_txt_name`| No | `llms-full.txt` | Name of the llms-full.txt output file |
| `sitemap_path` | No | `sitemap.xml` | Path relative to docs_dir to the sitemap.xml file [default: sitemap.xml] |
| `model_name` | No | `gpt-4o` | Whether to push generated files to github artifacts |
## Secret Parameters
| Parameter | Required | Default | Description |
|---------------------|----------|------------|----------------------------------------------|
| `MODEL_API_KEY` | No | None | This key (eg. OPENAI_API_KEY) will be used to summarize pages to create llms.txt. Needs to match the `model_name` provider. If using the default model_name, pass OPENAI_API_KEY. |
## Local Development
1. Clone and install:
```bash
# clone the repo
uv sync
```
1. Run the crawler:
```bash
uv run python -m "llms_txt_action.entrypoint" --docs-dir site/
```
## Examples
### ReadtheDocs
To integrate llms-txt-action with ReadtheDocs, you'll need to configure two files in your project:
1. `.readthedocs.yaml` - The main ReadtheDocs configuration file that defines the build environment and process
2. `docs/requirements.txt` - Python package dependencies needed for building your documentation
Here's how to set up both files:
```yaml
# .readthedocs.yaml
version: 2
build:
os: ubuntu-22.04
tools:
python: "3.12" # ^3.9 is supported.
jobs:
post_build:
- llms-txt --docs-dir $READTHEDOCS_OUTPUT/html
mkdocs:
configuration: mkdocs.yml
python:
install:
- requirements: docs/requirements.txt
```
```txt
# docs/requirements.txt
llms-txt-action
```
### MkDocs + Github Pages
MkDocs is a fast and simple static site generator that's geared towards building project documentation. Here's how to integrate llms-txt-action with MkDocs when deploying to GitHub Pages:
1. First, ensure you have a working MkDocs setup with your documentation source files.
2. Create or update your GitHub Actions workflow file (e.g., `.github/workflows/docs.yml`) with the following configuration:
```yaml
# github action - .github/workflows/docs.yml
- name: Generate static files
run : mkdocs build
- name: Make docs LLM ready
uses: demodrive-ai/llms-txt-action@v1
- name: Deploy to Github
run : mkdocs gh-deploy --dirty
# --dirty helps keep the generated .md and .txt files from getting deleted.
```
### Sphinx + Github Pages
Sphinx is a popular documentation generator for Python projects. Here's how to integrate llms-txt-action with Sphinx and GitHub Pages:
1. First, ensure you have a working Sphinx documentation setup with a `docs/` directory containing your source files and configuration.
2. Create or update your GitHub Actions workflow file (e.g., `.github/workflows/docs.yml`) with the following configuration:
```yaml
#...
#...
- name: Build HTML
uses: ammaraskar/sphinx-action@master
- name: Make docs LLM Ready
uses: demodrive-ai/llms-txt-action@v1
with:
name: docs-dir
path: docs/build/html/
- name: Deploy
uses: peaceiris/actions-gh-pages@v3
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
publish_dir: docs/build/html
#...
#...
```
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "llms-txt-action",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "documentation, github-action, llm",
"author": null,
"author_email": "DemoDrive AI <founders@demodrive.tech>",
"download_url": "https://files.pythonhosted.org/packages/62/ec/d6e34cd9f98e6d0395026e1efeaede166cb670ccabad1b6cc49ba24ebbb0/llms_txt_action-1.0.2.tar.gz",
"platform": null,
"description": "# llms-txt-actions\n\n[](https://github.com/demodrive-ai/llms-txt-action/releases)\n[](https://github.com/demodrive-ai/llms-txt-action/actions)\n[](LICENSE)\n\n\n### Make your documentation LLM friendly.\n\nThis Github action/CLI tool can automatically generate markdown (.md) files for each endpoint in your documentation as per the standard proposed by [answer.ai](https://www.answer.ai/), for more details read: https://llmstxt.org/.\n\n\n\nIt completely runs locally be default, by passing MODEL_API_KEY one can choose to engage hosted cloud AI services to generate page summaries.\n\n## Features\n\n- \ud83d\udcc4 **Content Processing**: Generate LLM-ready markdown (.md) files from popular document frameworks such as [Readthedocs](https://readthedocs.io/), [MKDocs](https://www.mkdocs.org/), [Sphinx](https://www.sphinx-doc.org/en/master/index.html#) and more.\n- \ud83c\udf08 **All Formats** : Can process HTML, PDF, Images, DOCX, PPTX, XLSX (thanks to [docling](https://github.com/DS4SD/docling)) and convert them to Markdown. (coming soon)\n- 0\ufe0f\u20e3 **Zero Config**: Works out of the box for most file based documentation framework.\n- \ud83d\udcbe **Generate Summaries**: Using LLMs, we generate concise summary of each page.\n- \ud83d\udcd5 **BYO-Model**: Thanks to [litellm](https://github.com/BerriAI/litellm), you can use upto 150 models like OpenAI, VertexAI, Cohere, Anthropic.\n\n\n## Quick Start\n\nThere are two ways to access this library.\n\n1. Add this to your GitHub workflow:\n\n```yaml\n\n steps:\n - name: Make docs LLM ready\n uses: demodrive-ai/llms-txt-action@v1\n\n # OR You can choose to use an AI model to generate summaries, its completely optional.\n steps:\n - name: Make docs LLM ready\n env:\n MODEL_API_KEY: ${{ secrets.MODEL_API_KEY }}\n uses: demodrive-ai/llms-txt-action@v1\n # any other inputs you would like to set.\n```\nOR\n\nYou can use it outside of Github Action.\n\n```bash\n# python 3.9 or above\npip install llms-txt-action\n\nllms-txt --docs-dir site/\n# The first run takes a while as it downloads models files from the intrnet.\n```\n\n## Input Parameters\n| Parameter | Required | Default | Description |\n|---------------------|----------|------------|----------------------------------------------|\n| `docs_dir` | No | `site/` | Documentation output directory |\n| `skip_llms_txt` | No | `true` | Skip llms.txt file generation. |\n| `skip_llms_full_txt` | No | `true` | skip llms-full.txt file generation. |\n| `skip_md_files` | No | `true` | Skip generation of markdown files |\n| `llms_txt_name` | No | `llms.txt` | Name of the llms.txt output file |\n| `llms_full_txt_name`| No | `llms-full.txt` | Name of the llms-full.txt output file |\n| `sitemap_path` | No | `sitemap.xml` | Path relative to docs_dir to the sitemap.xml file [default: sitemap.xml] |\n| `model_name` | No | `gpt-4o` | Whether to push generated files to github artifacts |\n\n\n\n\n## Secret Parameters\n| Parameter | Required | Default | Description |\n|---------------------|----------|------------|----------------------------------------------|\n| `MODEL_API_KEY` | No | None | This key (eg. OPENAI_API_KEY) will be used to summarize pages to create llms.txt. Needs to match the `model_name` provider. If using the default model_name, pass OPENAI_API_KEY. |\n\n\n\n\n## Local Development\n\n1. Clone and install:\n\n ```bash\n # clone the repo\n uv sync\n ```\n\n1. Run the crawler:\n\n ```bash\n uv run python -m \"llms_txt_action.entrypoint\" --docs-dir site/\n ```\n\n## Examples\n\n### ReadtheDocs\n\nTo integrate llms-txt-action with ReadtheDocs, you'll need to configure two files in your project:\n\n1. `.readthedocs.yaml` - The main ReadtheDocs configuration file that defines the build environment and process\n2. `docs/requirements.txt` - Python package dependencies needed for building your documentation\n\nHere's how to set up both files:\n\n```yaml\n# .readthedocs.yaml\nversion: 2\n\nbuild:\n os: ubuntu-22.04\n tools:\n python: \"3.12\" # ^3.9 is supported.\n jobs:\n post_build:\n - llms-txt --docs-dir $READTHEDOCS_OUTPUT/html\n\nmkdocs:\n configuration: mkdocs.yml\n\npython:\n install:\n - requirements: docs/requirements.txt\n\n```\n\n```txt\n# docs/requirements.txt\nllms-txt-action\n```\n\n### MkDocs + Github Pages\n\nMkDocs is a fast and simple static site generator that's geared towards building project documentation. Here's how to integrate llms-txt-action with MkDocs when deploying to GitHub Pages:\n\n1. First, ensure you have a working MkDocs setup with your documentation source files.\n\n2. Create or update your GitHub Actions workflow file (e.g., `.github/workflows/docs.yml`) with the following configuration:\n\n\n```yaml\n# github action - .github/workflows/docs.yml\n\n - name: Generate static files\n run : mkdocs build\n\n - name: Make docs LLM ready\n uses: demodrive-ai/llms-txt-action@v1\n\n - name: Deploy to Github\n run : mkdocs gh-deploy --dirty\n # --dirty helps keep the generated .md and .txt files from getting deleted.\n```\n\n### Sphinx + Github Pages\nSphinx is a popular documentation generator for Python projects. Here's how to integrate llms-txt-action with Sphinx and GitHub Pages:\n\n1. First, ensure you have a working Sphinx documentation setup with a `docs/` directory containing your source files and configuration.\n\n2. Create or update your GitHub Actions workflow file (e.g., `.github/workflows/docs.yml`) with the following configuration:\n\n```yaml\n#...\n#...\n - name: Build HTML\n uses: ammaraskar/sphinx-action@master\n - name: Make docs LLM Ready\n uses: demodrive-ai/llms-txt-action@v1\n with:\n name: docs-dir\n path: docs/build/html/\n - name: Deploy\n uses: peaceiris/actions-gh-pages@v3\n with:\n github_token: ${{ secrets.GITHUB_TOKEN }}\n publish_dir: docs/build/html\n#...\n#...\n```\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "GitHub Action to make documentation more accessible to LLMs.",
"version": "1.0.2",
"project_urls": {
"Homepage": "https://github.com/demodrive-ai/llms-txt-action",
"Repository": "https://github.com/demodrive-ai/llms-txt-action"
},
"split_keywords": [
"documentation",
" github-action",
" llm"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "2816991dab3bfefa8ec092edc47b631c1c0613ddf3ec4603ef252d0dadc53215",
"md5": "c03b7f6812ab841e8ad3fbf56aab0247",
"sha256": "0e78f783e5b936d345f68ea21b69686b61b8a761ef1e90031f33671aa2118c34"
},
"downloads": -1,
"filename": "llms_txt_action-1.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c03b7f6812ab841e8ad3fbf56aab0247",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 9927,
"upload_time": "2025-01-07T22:10:23",
"upload_time_iso_8601": "2025-01-07T22:10:23.732642Z",
"url": "https://files.pythonhosted.org/packages/28/16/991dab3bfefa8ec092edc47b631c1c0613ddf3ec4603ef252d0dadc53215/llms_txt_action-1.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "62ecd6e34cd9f98e6d0395026e1efeaede166cb670ccabad1b6cc49ba24ebbb0",
"md5": "a130ba537aacd19c6b459234b58b11e3",
"sha256": "b74213ae12f4694147188e45b32513652246fcc1551cb47f13945cd3d4ec1880"
},
"downloads": -1,
"filename": "llms_txt_action-1.0.2.tar.gz",
"has_sig": false,
"md5_digest": "a130ba537aacd19c6b459234b58b11e3",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 296612,
"upload_time": "2025-01-07T22:10:26",
"upload_time_iso_8601": "2025-01-07T22:10:26.663895Z",
"url": "https://files.pythonhosted.org/packages/62/ec/d6e34cd9f98e6d0395026e1efeaede166cb670ccabad1b6cc49ba24ebbb0/llms_txt_action-1.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-07 22:10:26",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "demodrive-ai",
"github_project": "llms-txt-action",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "llms-txt-action"
}
