Compare commits

...
12 Commits
Author SHA1 Message Date
Jared Dillard 8625868df7 add soft transfer 2025-05-18 21:19:19 -07:00
Jared Dillard b2aa7897d3 Clean up 2025-05-18 21:08:58 -07:00
Jared Dillard 12d695015e change features to how it works 2025-05-18 21:04:59 -07:00
Jared Dillard 29c400e122 fix linter 2025-05-18 20:55:54 -07:00
Jared Dillard 834a57a158 add missing file 2025-05-18 20:54:55 -07:00
Jared Dillard efbe8e0cda revert dev env 2025-05-18 20:54:45 -07:00
Jared Dillard 68860c7dda clean up readme 2025-05-18 20:51:52 -07:00
Jared Dillard 055261b3bb fix linter 2025-05-18 20:50:38 -07:00
Jared Dillard a274621b32 fix linter 2025-05-18 20:49:44 -07:00
Jared Dillard 2f62461703 Add advanced configuration 2025-05-18 20:47:58 -07:00
Jared Dillard da48421b03 Clean up project name 2025-05-18 20:47:19 -07:00
Jared Dillard 9385670cfe Move readme content to index.rst 2025-05-18 20:46:51 -07:00
6 changed files with 214 additions and 113 deletions
+2 -80
View File
@@ -5,87 +5,9 @@ A Sphinx extension that generates a summary `llms.txt` file, written in Markdown
[![PyPI version](https://img.shields.io/pypi/v/sphinx-llms-txt.svg)](https://pypi.python.org/pypi/sphinx-llms-txt)
[![Downloads](https://static.pepy.tech/badge/sphinx-llms-txt/month)](https://pepy.tech/project/sphinx-llms-txt)
## Installation
## Documentation
```bash
pip install sphinx-llms-txt
```
## Usage
1. Add the extension to your Sphinx configuration (`conf.py`):
```python
extensions = [
'sphinx_llms_txt',
]
```
## Configuration Options
### `llms_txt_full_file`
- **Type**: boolean
- **Default**: `'True'`
- **Description**: Whether to write the single output file
### `llms_txt_full_filename`
- **Type**: string
- **Default**: `'llms-full.txt'`
- **Description**: Name of the single output file
### `llms_txt_full_max_size`
- **Type**: integer or `None`
- **Default**: `None` (no limit)
- **Description**: Sets a maximum line count for `llms_txt_full_filename`.
If exceeded, the file is skipped and a warning is shown, but the build still completes.
### `llms_txt_file`
- **Type**: boolean
- **Default**: `True`
- **Description**: Whether to write the summary information file
### `llms_txt_filename`
- **Type**: string
- **Default**: `llms.txt`
- **Description**: Name of the summary information file
### `llms_txt_directives`
- **Type**: list of strings
- **Default**: `[]`
- **Description**: List of custom directive names to process for path resolution.
### `llms_txt_title`
- **Type**: string or `None`
- **Default**: `None`
- **Description**: Overrides the Sphinx project name as the heading in `llms.txt`.
### `llms_txt_summary`
- **Type**: string or `None`
- **Default**: `None`
- **Description**: Optional, but recommended, summary description for `llms.txt`.
### `llms_txt_exclude`
- **Type**: list of strings
- **Default**: `[]`
- **Description**: A list of pages to ignore (e.g., `["page1", "page_with_*"]`).
## Features
- Creates `llms.txt` and `llms-full.txt`
- Automatically add content from `include` directives
- Resolves relative paths in directives like `image` and `figure` to use full paths
- Ability to add list of custom directives with `llms_txt_directives`
- Optionally, prepend a base URL using Sphinx's `html_baseurl`
- Ability to exclude pages
See [sphinx-llms-txt documentation](https://sphinx-llms-txt.readthedocs.io/en/latest/index.html) for installation and configuration instructions.
## License
+170
View File
@@ -0,0 +1,170 @@
Advanced Configuration
======================
This page covers advanced configuration options for the sphinx-llms-txt extension.
.. _customizing_llms_files:
Customizing the LLMs Files
^^^^^^^^^^^^^^^^^^^^^^^^^^
By default, the extension generates two files:
1. ``llms.txt`` - A summary file in Markdown format
2. ``llms-full.txt`` - A complete documentation file in reStructuredText format
You can customize these files in several ways:
.. _changing_filenames:
Changing Filenames
~~~~~~~~~~~~~~~~~~
You can change the default filenames by setting these values in your ``conf.py``:
.. code-block:: python
llms_txt_filename = "custom-summary.txt"
llms_txt_full_filename = "custom-docs.txt"
.. _disabling_file_generation:
Disabling File Generation
~~~~~~~~~~~~~~~~~~~~~~~~~
If you only want one of the files, you can disable generation of the other:
.. code-block:: python
# Disable summary file
llms_txt_file = False
# Disable full documentation file
llms_txt_full_file = False
.. _custom_summary:
Adding a Custom Summary
~~~~~~~~~~~~~~~~~~~~~~~
The summary file can include a custom description of your project:
.. code-block:: python
llms_txt_summary = """
This documentation explains how to use MyProject to build amazing
applications. The project provides a comprehensive API for handling
data processing and visualization.
"""
.. note:: The summary can span multiple lines and will be properly formatted in the output file.
.. _custom_title:
Custom Title
~~~~~~~~~~~~
By default, the project name from Sphinx is used as the title in ``llms.txt``. You can override this:
.. code-block:: python
llms_txt_title = "My Custom Project Documentation"
.. _handling_large_documentation:
Handling Large Documentation
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
For very large documentation sets, generating the full documentation file might exceed reasonable size limits.
You can set a maximum line count:
.. code-block:: python
llms_txt_full_max_size = 10000 # Maximum 10,000 lines
If the generated file would exceed this limit, the extension will skip its generation and show a warning, allowing the build to complete.
.. tip:: Use :ref:`excluding_content` to remove less relevant pages.
.. _custom_directive_handling:
Custom Directive Handling
^^^^^^^^^^^^^^^^^^^^^^^^^
.. _path_resolution:
Path Resolution
~~~~~~~~~~~~~~~
The extension resolves paths in the common directives ``[ 'image', 'figure']`` by default.
You can add custom directives to this list:
.. code-block:: python
llms_txt_directives = [
"my-custom-image-directive",
"another-directive-with-paths",
]
This ensures that paths in your custom directives are properly resolved in the generated files.
.. _excluding_content:
Excluding Content
^^^^^^^^^^^^^^^^^
You can exclude specific pages from being included in the generated files:
.. code-block:: python
llms_txt_exclude = [
"search", # Exclude the search page
"genindex", # Exclude the index page
"private_*", # Exclude all pages starting with 'private_'
]
This is useful for excluding auto-generated pages, indexes, or content that isn't relevant for LLM consumption.
.. _using_html_baseurl:
Using HTML Base URL
^^^^^^^^^^^^^^^^^^^
If you want to include absolute URLs for resources in your documentation, you can use Sphinx's built-in ``html_baseurl`` configuration:
.. code-block:: python
html_baseurl = "https://example.com/docs/"
When this option is set, all resolved paths in directives will be prefixed with this URL, creating absolute paths in the generated files.
.. _integration_examples:
Integration Examples
^^^^^^^^^^^^^^^^^^^^
Complete Configuration Example
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Here's a complete example showing multiple configuration options:
.. code-block:: python
# File names and generation options
llms_txt_filename = "ai-summary.txt"
llms_txt_full_filename = "ai-full-docs.txt"
llms_txt_full_max_size = 50000
# Content customization
llms_txt_title = "Project Documentation for AI Assistants"
llms_txt_summary = """
This is a comprehensive documentation set for our project.
It includes API references, usage examples, and tutorials.
"""
# Path handling
html_baseurl = "https://docs.example.com/"
llms_txt_directives = ["custom-image", "custom-include"]
# Content filtering
llms_txt_exclude = ["search", "genindex", "404", "private_*"]
+1 -1
View File
@@ -12,7 +12,7 @@ import subprocess
# -- Project information -----------------------------------------------------
project = "Sphinx llms.txt Generator"
project = "sphinx-llms-txt"
copyright = "Jared Dillard"
author = "Jared Dillard"
llms_txt_summary = """
+14 -13
View File
@@ -5,7 +5,8 @@ Project Configuration Values
- **Type**: boolean
- **Default**: ``True``
- **Description**: Whether to write the single output file
- **Description**: Whether to write the single output file.
See :ref:`disabling_file_generation`.
.. versionadded:: 0.1.0
@@ -13,7 +14,8 @@ Project Configuration Values
- **Type**: string
- **Default**: ``'llms-full.txt'``
- **Description**: Name of the single output file
- **Description**: Name of the single output file.
See :ref:`changing_filenames`.
.. versionadded:: 0.1.0
@@ -23,6 +25,7 @@ Project Configuration Values
- **Default**: ``None`` (no limit)
- **Description**: Sets a maximum line count for ``llms_txt_full_filename``.
If exceeded, the file is skipped and a warning is shown, but the build still completes.
See :ref:`handling_large_documentation`.
.. versionadded:: 0.2.0
@@ -30,7 +33,8 @@ Project Configuration Values
- **Type**: boolean
- **Default**: ``True``
- **Description**: Whether to write the summary information file
- **Description**: Whether to write the summary information file.
See :ref:`disabling_file_generation`.
.. versionadded:: 0.2.0
@@ -38,7 +42,8 @@ Project Configuration Values
- **Type**: string
- **Default**: ``llms.txt``
- **Description**: Name of the summary information file
- **Description**: Name of the summary information file.
See :ref:`changing_filenames`.
.. versionadded:: 0.2.0
@@ -47,6 +52,7 @@ Project Configuration Values
- **Type**: list of strings
- **Default**: ``[]`` (empty list)
- **Description**: List of custom directive names to process for path resolution.
See :ref:`path_resolution`.
.. versionadded:: 0.1.0
@@ -55,6 +61,7 @@ Project Configuration Values
- **Type**: string or ``None``
- **Default**: ``None``
- **Description**: Overrides the Sphinx project name as the heading in ``llms.txt``.
See :ref:`custom_title`.
.. versionadded:: 0.2.0
@@ -63,6 +70,7 @@ Project Configuration Values
- **Type**: string or ``None``
- **Default**: ``None``
- **Description**: Optional, but recommended, summary description for ``llms.txt``.
See :ref:`custom_summary`.
.. versionadded:: 0.2.0
@@ -70,14 +78,7 @@ Project Configuration Values
- **Type**: list of strings
- **Default**: ``[]``
- **Description**: A list of pages to ignore (e.g., ``["page1", "page_with_*"]``).
- **Description**: A list of pages to ignore.
See :ref:`excluding_content`.
.. versionadded:: 0.2.1
.. confval:: llms_txt_rm_directives
- **Type**: boolean
- **Default**: ``False``
- **Description**: Whether to remove all directives from the output files.
.. versionadded:: 0.2.3
+26
View File
@@ -1,6 +1,11 @@
Getting Started
===============
Demo
----
You can see this Sphinx project's `llms.txt`_ and `llms-full.txt`_ files as a simple example.
Installation
------------
@@ -22,3 +27,24 @@ Add the extension to your Sphinx configuration (``conf.py``):
]
Once added, the extension will automatically generate the LLMs.txt files during the build process.
See :doc:`advanced-configuration` for more information about how to use **sphinx-llms-txt**.
How It Works
-----------
During the Sphinx build process:
1. **Content Collection**: Scans all of your documentation's ``_source`` pages and collects their content
2. **Directive Processing**: Resolves ``include`` directives by automatically incorporating their content
3. **Path Resolution**: Transforms relative paths in directives to full paths
4. **Output Generation**: Creates two optional files:
- ``llms.txt``: A concise summary of your documentation, in Markdown
- ``llms-full.txt``: A comprehensive version with all documentation content, in reStructuredText
5. **Content Filtering**: Allows you to exclude specific pages from the generated files
.. _llms.txt: https://sphinx-llms-txt.readthedocs.io/en/latest/llms.txt
.. _llms-full.txt: https://sphinx-llms-txt.readthedocs.io/en/latest/llms-full.txt
+1 -19
View File
@@ -9,31 +9,13 @@ A `Sphinx`_ extension that generates a summary ``llms.txt`` file, written in Mar
:maxdepth: 2
getting-started
advanced-configuration
configuration-values
contributing
changelog
Features
--------
Sphinx LLMs.txt provides the following features:
- Creates ``llms.txt`` and ``llms-full.txt``
- Automatically add content from ``include`` directives
- Resolves relative paths in directives like ``image`` and ``figure`` to use full paths
- Ability to add list of custom directives with ``llms_txt_directives``
- Optionally, prepend a base URL using Sphinx's ``html_baseurl``
- Ability to exclude pages
Example
-------
You can see this Sphinx projects `llms.txt`_ and `llms-full.txt`_ files as a simple example.
.. _Sphinx: http://sphinx-doc.org/
.. _llms.txt: https://sphinx-llms-txt.readthedocs.io/en/latest/llms.txt
.. _llms-full.txt: https://sphinx-llms-txt.readthedocs.io/en/latest/llms-full.txt
.. |PyPI version| image:: https://img.shields.io/pypi/v/sphinx-llms-txt.svg
:target: https://pypi.python.org/pypi/sphinx-llms-txt