Adds LLMs text for improved AI queries

Author: jamie-lemon

docs/conf.py

@@ -201,7 +201,8 @@
 # Add any extra paths that contain custom files (such as robots.txt or
 # .htaccess) here, relative to this directory. These files are copied
 # directly to the root of the documentation.
-# html_extra_path = []
+# Using to copy over the LLM specific files
+html_extra_path = ["llms"]
 
 # If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
 # using the given strftime format.

docs/llms/_x.txt

@@ -0,0 +1,150 @@
+# PyMuPDF
+
+> # PyMuPDF
+> 
+> **PyMuPDF** is a high performance **Python** library for data extraction, analysis, conversion & manipulation of [PDF (and other) documents](https://pymupdf.readthedocs.io/en/latest/the-basics.html#supported-file-types).
+> 
+> # Community
+> Join us on **Discord** here: [#pymupdf](https://discord.gg/TSpYGBW4eq)
+> 
+> 
+> # Installation
+> 
+> **PyMuPDF** requires **Python 3.10 or later**, install using **pip** with:
+> 
+> `pip install PyMuPDF`
+> 
+> There are **no mandatory** external dependencies. However, some [optional features](#pymupdf-optional-features) become available only if additional packages are installed.
+> 
+> You can also try without installing by visiting [PyMuPDF.io](https://pymupdf.io/#examples).
+> 
+> 
+> # Usage
+> 
+> Basic usage is as follows:
+> 
+> ```python
+> import pymupdf # imports the pymupdf library
+> doc = pymupdf.open("example.pdf") # open a document
+> for page in doc: # iterate the document pages
+>   text = page.get_text() # get plain text encoded as UTF-8
+> 
+> ```
+> 
+> 
+> # Documentation
+> 
+> Full documentation can be found on [pymupdf.readthedocs.io](https://pymupdf.readthedocs.io).
+> 
+> 
+> 
+> # <a id="pymupdf-optional-features"></a>Optional Features
+> 
+> * [fontTools](https://pypi.org/project/fonttools/) for creating font subsets.
+> * [pymupdf-fonts](https://pypi.org/project/pymupdf-fonts/) contains some nice fonts for your text output.
+> * [Tesseract-OCR](https://github.com/tesseract-ocr/tesseract) for optical character recognition in images and document pages.
+> 
+> 
+> 
+> # About
+> 
+> **PyMuPDF** adds **Python** bindings and abstractions to [MuPDF](https://mupdf.com/), a lightweight **PDF**, **XPS**, and **eBook** viewer, renderer, and toolkit. Both **PyMuPDF** and **MuPDF** are maintained and developed by [Artifex Software, Inc](https://artifex.com).
+> 
+> **PyMuPDF** was originally written by [Jorj X. McKie](mailto:jorj.x.mckie@outlook.de).
+> 
+> 
+> # License and Copyright
+> 
+> **PyMuPDF** is available under [open-source AGPL](https://www.gnu.org/licenses/agpl-3.0.html) and commercial license agreements. If you determine you cannot meet the requirements of the **AGPL**, please contact [Artifex](https://artifex.com/contact/pymupdf-inquiry.php) for more information regarding a commercial license.
+
+
+2015-2026, Artifex
+
+## Pages
+
+- [Welcome to <cite>PyMuPDF</cite>](index.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [PyMuPDF4LLM](pymupdf4llm/index.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [PyMuPDF Pro](pymupdf-pro/index.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [FAQ](faq/index.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [OCR](ocr/index.html.md): How automatic OCR works in PyMuPDF4LLM, when to force it, and how to swap in a different OCR engine.
+- [404!](404.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [feature-matrix th {](about-feature-matrix.html.md): border-style: hidden;
+- [copying-graph .about-graph-area.a {](about-performance.html.md): -webkit-tap-highlight-color: rgba(0,0,0,0); /\* make transparent link selection, adjust last value o...
+- [Features Comparison](about.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Operator Algebra for Geometry Objects](algebra.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Annot](annot.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [The PyMuPDF4LLM API](pymupdf4llm/api.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Appendix 1: Details on Text Extraction](app1.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Appendix 2: Considerations on Embedded Files](app2.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Appendix 3: Assorted Technical Information](app3.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Appendix 4: Performance Comparison Methodology](app4.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Archive](archive-class.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Change Log](changes.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Classes](classes.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Color Database](colors.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Colorspace](colorspace.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Converting Files](converting-files.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Working together: DisplayList and TextPage](coop_low.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Device](device.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [DisplayList](displaylist.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [DocumentWriter](document-writer-class.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Document](document.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [FAQ](faq.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Font](font.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Footer](footer.html.md): <p style="color:#999" id="footerDisclaimer">This software is provided AS-IS with no warranty, either...
+- [Functions](functions.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Glossary](glossary.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Header-404](header-404.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Header](header.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Opening Files](how-to-open-a-file.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Identity](identity.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [PyMuPDF4LLM](pymupdf4llm/index-new.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Installation](installation.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [IRect](irect.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Link](link.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [linkDest](linkdest.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Low Level Functions and Classes](lowlevel.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Matrix](matrix.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Command line interface](module.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [OCR support](new-ocr.html.md): new-ocr.rst
+- [OCR Plugins](pymupdf4llm/ocr-plugins.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Outline](outline.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Packaging for Linux distributions](packaging.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Page](page.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Pixmap](pixmap.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Point](point.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Pyodide](pyodide.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Quad](quad.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [PyMuPDF, LLM & RAG](rag.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Annotations](recipes-annotations.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Common Issues and their Solutions](recipes-common-issues-and-their-solutions.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Drawing and Graphics](recipes-drawing-and-graphics.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Images](recipes-images.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Journalling](recipes-journalling.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Low-Level Interfaces](recipes-low-level-interfaces.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Multiprocessing](recipes-multiprocessing.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [OCR - Optical Character Recognition](recipes-ocr.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Optional Content Support](recipes-optional-content.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Stories](recipes-stories.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Text](recipes-text.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Recipes](recipes.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Rect](rect.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Resources](resources.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Shape](shape.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Story](story-class.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [feature-matrix th {](supported-files-table.html.md): border-style: hidden;
+- [Tesseract Language Packs](ocr/tesseract-language-packs.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [TextPage](textpage.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [TextWriter](textwriter.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [The Basics](the-basics.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Tools](tools.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Tutorial](tutorial.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Constants and Enumerations](vars.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Version](version.html.md): This documentation covers PyMuPDF 1.27.2.3.
+- [Widget](widget.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Xml](xml-class.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+- [Deprecated Names](znames.html.md): PyMuPDF is a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+
+---
+
+For more comprehensive documentation, see [llms-full.txt](llms-full.txt)