├── .github └── workflows │ ├── deploy.yaml │ └── test.yaml ├── .gitignore ├── CHANGELOG.md ├── LICENSE ├── MANIFEST.in ├── README.md ├── llm_ctx ├── __init__.py ├── _modidx.py └── core.py ├── nbs ├── 00_core.ipynb ├── _quarto.yml ├── index.ipynb ├── llms.txt ├── nbdev.yml └── styles.css ├── settings.ini └── setup.py /.github/workflows/deploy.yaml: -------------------------------------------------------------------------------- 1 | name: Deploy to GitHub Pages 2 | 3 | permissions: 4 | contents: write 5 | pages: write 6 | 7 | on: 8 | push: 9 | branches: [ "main", "master" ] 10 | workflow_dispatch: 11 | jobs: 12 | deploy: 13 | runs-on: ubuntu-latest 14 | steps: [uses: fastai/workflows/quarto-ghp@master] 15 | -------------------------------------------------------------------------------- /.github/workflows/test.yaml: -------------------------------------------------------------------------------- 1 | name: CI 2 | on: [workflow_dispatch, pull_request, push] 3 | 4 | jobs: 5 | test: 6 | runs-on: ubuntu-latest 7 | steps: [uses: fastai/workflows/nbdev-ci@master] 8 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | fast*.md 2 | posts/ 3 | .quarto 4 | .sesskey 5 | *.db-* 6 | *.db 7 | .gitattributes 8 | _proc/ 9 | sidebar.yml 10 | Gemfile.lock 11 | token 12 | _docs/ 13 | conda/ 14 | .last_checked 15 | .gitconfig 16 | *.bak 17 | *.log 18 | *~ 19 | ~* 20 | _tmp* 21 | tmp* 22 | tags 23 | 24 | # Byte-compiled / optimized / DLL files 25 | __pycache__/ 26 | *.py[cod] 27 | *$py.class 28 | 29 | # C extensions 30 | *.so 31 | 32 | # Distribution / packaging 33 | .Python 34 | env/ 35 | build/ 36 | develop-eggs/ 37 | dist/ 38 | downloads/ 39 | eggs/ 40 | .eggs/ 41 | lib/ 42 | lib64/ 43 | parts/ 44 | sdist/ 45 | var/ 46 | wheels/ 47 | *.egg-info/ 48 | .installed.cfg 49 | *.egg 50 | 51 | # PyInstaller 52 | # Usually these files are written by a python script from a template 53 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 54 | *.manifest 55 | *.spec 56 | 57 | # Installer logs 58 | pip-log.txt 59 | pip-delete-this-directory.txt 60 | 61 | # Unit test / coverage reports 62 | htmlcov/ 63 | .tox/ 64 | .coverage 65 | .coverage.* 66 | .cache 67 | nosetests.xml 68 | coverage.xml 69 | *.cover 70 | .hypothesis/ 71 | 72 | # Translations 73 | *.mo 74 | *.pot 75 | 76 | # Django stuff: 77 | *.log 78 | local_settings.py 79 | 80 | # Flask stuff: 81 | instance/ 82 | .webassets-cache 83 | 84 | # Scrapy stuff: 85 | .scrapy 86 | 87 | # Sphinx documentation 88 | docs/_build/ 89 | 90 | # PyBuilder 91 | target/ 92 | 93 | # Jupyter Notebook 94 | .ipynb_checkpoints 95 | 96 | # pyenv 97 | .python-version 98 | 99 | # celery beat schedule file 100 | celerybeat-schedule 101 | 102 | # SageMath parsed files 103 | *.sage.py 104 | 105 | # dotenv 106 | .env 107 | 108 | # virtualenv 109 | .venv 110 | venv/ 111 | ENV/ 112 | 113 | # Spyder project settings 114 | .spyderproject 115 | .spyproject 116 | 117 | # Rope project settings 118 | .ropeproject 119 | 120 | # mkdocs documentation 121 | /site 122 | 123 | # mypy 124 | .mypy_cache/ 125 | 126 | .vscode 127 | *.swp 128 | 129 | # osx generated files 130 | .DS_Store 131 | .DS_Store? 132 | .Trashes 133 | ehthumbs.db 134 | Thumbs.db 135 | .idea 136 | 137 | # pytest 138 | .pytest_cache 139 | 140 | # tools/trust-doc-nbs 141 | docs_src/.last_checked 142 | 143 | # symlinks to fastai 144 | docs_src/fastai 145 | tools/fastai 146 | 147 | # link checker 148 | checklink/cookies.txt 149 | 150 | # .gitconfig is now autogenerated 151 | .gitconfig 152 | 153 | _docs 154 | -------------------------------------------------------------------------------- /CHANGELOG.md: -------------------------------------------------------------------------------- 1 | # Release notes 2 | 3 | 4 | 5 | ## 0.0.1 6 | 7 | - Initial version 8 | 9 | 10 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright 2022, fastai 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include settings.ini 2 | include LICENSE 3 | include CONTRIBUTING.md 4 | include README.md 5 | recursive-exclude * __pycache__ 6 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # llm_ctx 2 | 3 | 4 | 5 | 6 | Given an `llms.txt` file, this provides a CLI and Python API to parse 7 | the file and create an XML context file from it. The input file should 8 | follow this format: 9 | 10 | # FastHTML 11 | 12 | > FastHTML is a python library which brings together Starlette, Uvicorn, HTMX, and fastcore's `FT` "FastTags" into a library for creating server-rendered hypermedia applications. 13 | 14 | ## Docs 15 | 16 | - [Surreal](https://raw.githubusercontent.com/AnswerDotAI/surreal/main/README.md): Tiny jQuery alternative with Locality of Behavior 17 | - [FastHTML quick start](https://docs.fastht.ml/tutorials/quickstart_for_web_devs.html.md): An overview of FastHTML features 18 | 19 | ## Examples 20 | 21 | - [Todo list application](https://raw.githubusercontent.com/AnswerDotAI/fasthtml/main/examples/adv_app.py) 22 | 23 | ## Optional 24 | 25 | - [Starlette docs](https://gist.githubusercontent.com/jph00/809e4a4808d4510be0e3dc9565e9cbd3/raw/9b717589ca44cedc8aaf00b2b8cacef922964c0f/starlette-sml.md): A subset of the Starlette documentation useful for FastHTML development 26 | 27 | ## Install 28 | 29 | ``` sh 30 | pip install llm-ctx 31 | ``` 32 | 33 | ## How to use 34 | 35 | To get help for the CLI: 36 | 37 | ``` sh 38 | llms_txt2ctx -h 39 | ``` 40 | 41 | To convert an `llms.txt` file to XML context and save to `llms.md`: 42 | 43 | ``` sh 44 | llms_txt2ctx llms.txt > llms.md 45 | ``` 46 | 47 | Pass `--optional False` to skip the ‘optional’ section of the input 48 | file. 49 | -------------------------------------------------------------------------------- /llm_ctx/__init__.py: -------------------------------------------------------------------------------- 1 | __version__ = "0.0.2" 2 | from .core import * 3 | -------------------------------------------------------------------------------- /llm_ctx/_modidx.py: -------------------------------------------------------------------------------- 1 | # Autogenerated by nbdev 2 | 3 | d = { 'settings': { 'branch': 'main', 4 | 'doc_baseurl': '/llm-ctx', 5 | 'doc_host': 'https://AnswerDotAI.github.io', 6 | 'git_url': 'https://github.com/AnswerDotAI/llm-ctx', 7 | 'lib_path': 'llm_ctx'}, 8 | 'syms': { 'llm_ctx.core': { 'llm_ctx.core.Doc': ('core.html#doc', 'llm_ctx/core.py'), 9 | 'llm_ctx.core.Section': ('core.html#section', 'llm_ctx/core.py'), 10 | 'llm_ctx.core._parse_links': ('core.html#_parse_links', 'llm_ctx/core.py'), 11 | 'llm_ctx.core.get_sizes': ('core.html#get_sizes', 'llm_ctx/core.py'), 12 | 'llm_ctx.core.llms_txt2ctx': ('core.html#llms_txt2ctx', 'llm_ctx/core.py'), 13 | 'llm_ctx.core.mk_ctx': ('core.html#mk_ctx', 'llm_ctx/core.py'), 14 | 'llm_ctx.core.parse_llm_txt': ('core.html#parse_llm_txt', 'llm_ctx/core.py')}}} 15 | -------------------------------------------------------------------------------- /llm_ctx/core.py: -------------------------------------------------------------------------------- 1 | # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/00_core.ipynb. 2 | 3 | # %% auto 0 4 | __all__ = ['Sections', 'Project', 'parse_llm_txt', 'Doc', 'Section', 'mk_ctx', 'get_sizes', 'llms_txt2ctx'] 5 | 6 | # %% ../nbs/00_core.ipynb 2 7 | from fastcore.utils import * 8 | from fastcore.xml import * 9 | from fastcore.script import * 10 | import httpx 11 | 12 | # %% ../nbs/00_core.ipynb 5 13 | def _parse_links(content): 14 | link_pat = r'^\s*-\s*\[(.+?)\]\((.+?)\)(?:\s*:\s*(.*))?$' 15 | return [dict(zip(['title','url','info'], m.groups())) 16 | for m in re.finditer(link_pat, content, re.M)] 17 | 18 | def parse_llm_txt(md): 19 | "Parse fasthtml markdown into structured dict" 20 | title = re.findall(r'^# (.+)$', md, re.M)[0] 21 | summary = re.findall(r'^> (.+)$', md, re.M)[0] 22 | section_pat = r'^## (.+)$' 23 | sec_spl = re.split(section_pat, md, flags=re.MULTILINE)[1:] 24 | sections = {t.strip():_parse_links(c) 25 | for t,c in zip(sec_spl[::2], sec_spl[1::2])} 26 | return dict2obj(dict(title=title.strip(), summary=summary.strip(), sections=sections)) 27 | 28 | # %% ../nbs/00_core.ipynb 12 29 | Sections = partial(ft, 'sections') 30 | Project = partial(ft, 'project') 31 | 32 | # %% ../nbs/00_core.ipynb 13 33 | def Doc(url, **kw): 34 | "Create a `Doc` FT object with the text retrieved from `url` as the child, and `kw` as attrs." 35 | re_comment = re.compile('^$', flags=re.MULTILINE) 36 | txt = [o for o in httpx.get(url).text.splitlines() if not re_comment.search(o)] 37 | return ft('doc', '\n'.join(txt), **kw) 38 | 39 | # %% ../nbs/00_core.ipynb 14 40 | def Section(nm, items): 41 | "Create a `Section` FT object containing a `Doc` object for each child." 42 | return ft(nm, *[Doc(**o) for o in items]) 43 | 44 | # %% ../nbs/00_core.ipynb 15 45 | def mk_ctx(d, optional=True): 46 | "Create a `Project` with a `Section` for each H2 part in `d`, optionally skipping the 'optional' section." 47 | skip = '' if optional else 'Optional' 48 | sections = [Section(k, v) for k,v in d.sections.items() if k!=skip] 49 | return Project(title=d.title, summary=d.summary)(*sections) 50 | 51 | # %% ../nbs/00_core.ipynb 19 52 | def get_sizes(ctx): 53 | return {o.tag:{p.title:len(p.children[0]) for p in o.children} for o in ctx.children} 54 | 55 | # %% ../nbs/00_core.ipynb 22 56 | @call_parse 57 | def llms_txt2ctx( 58 | fname:str, # File name to read 59 | optional:bool_arg=True # Skip 'optional' section? 60 | ): 61 | "Print a `Project` with a `Section` for each H2 part in file read from `fname`, optionally skipping the 'optional' section.." 62 | d = parse_llm_txt(Path(fname).read_text()) 63 | ctx = mk_ctx(d, optional=optional) 64 | print(to_xml(ctx)) 65 | -------------------------------------------------------------------------------- /nbs/00_core.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": null, 6 | "id": "04e76a3b", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "#| default_exp core" 11 | ] 12 | }, 13 | { 14 | "cell_type": "markdown", 15 | "id": "b0499d4c", 16 | "metadata": {}, 17 | "source": [ 18 | "# llm_ctx\n", 19 | "> Source code for llm_ctx" 20 | ] 21 | }, 22 | { 23 | "cell_type": "code", 24 | "execution_count": null, 25 | "id": "130e84f2", 26 | "metadata": {}, 27 | "outputs": [], 28 | "source": [ 29 | "#| export\n", 30 | "from fastcore.utils import *\n", 31 | "from fastcore.xml import *\n", 32 | "from fastcore.script import *\n", 33 | "import httpx" 34 | ] 35 | }, 36 | { 37 | "cell_type": "markdown", 38 | "id": "81c3ec89", 39 | "metadata": {}, 40 | "source": [ 41 | "We'll use an `llms.txt` file for FastHTML for our examples." 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": null, 47 | "id": "e7d9506c", 48 | "metadata": {}, 49 | "outputs": [], 50 | "source": [ 51 | "path = Path('llms.txt')\n", 52 | "txt = path.read_text()" 53 | ] 54 | }, 55 | { 56 | "cell_type": "code", 57 | "execution_count": null, 58 | "id": "eb998194", 59 | "metadata": {}, 60 | "outputs": [], 61 | "source": [ 62 | "#| export\n", 63 | "def _parse_links(content):\n", 64 | " link_pat = r'^\\s*-\\s*\\[(.+?)\\]\\((.+?)\\)(?:\\s*:\\s*(.*))?$'\n", 65 | " return [dict(zip(['title','url','info'], m.groups())) \n", 66 | " for m in re.finditer(link_pat, content, re.M)]\n", 67 | "\n", 68 | "def parse_llm_txt(md):\n", 69 | " \"Parse fasthtml markdown into structured dict\"\n", 70 | " title = re.findall(r'^# (.+)$', md, re.M)[0]\n", 71 | " summary = re.findall(r'^> (.+)$', md, re.M)[0]\n", 72 | " section_pat = r'^## (.+)$'\n", 73 | " sec_spl = re.split(section_pat, md, flags=re.MULTILINE)[1:]\n", 74 | " sections = {t.strip():_parse_links(c)\n", 75 | " for t,c in zip(sec_spl[::2], sec_spl[1::2])}\n", 76 | " return dict2obj(dict(title=title.strip(), summary=summary.strip(), sections=sections))" 77 | ] 78 | }, 79 | { 80 | "cell_type": "markdown", 81 | "id": "ced02e5c", 82 | "metadata": {}, 83 | "source": [ 84 | "The returned `dict` contains the summary and title of the file..." 85 | ] 86 | }, 87 | { 88 | "cell_type": "code", 89 | "execution_count": null, 90 | "id": "58119655", 91 | "metadata": {}, 92 | "outputs": [ 93 | { 94 | "data": { 95 | "text/plain": [ 96 | "('FastHTML',\n", 97 | " 'FastHTML is a python library which brings together Starlette, Uvicorn, HTMX, and fastcore\\'s `FT` \"FastTags\" into a library for creating server-rendered hypermedia applications. The `FastHTML` class itself inherits from `Starlette`, and adds decorator-based routing with many additions, Beforeware, automatic `FT` to HTML rendering, and much more. Although parts of its API are inspired by FastAPI, it is *not* compatible with FastAPI syntax and is not targeted at creating API services. FastHTML includes support for Pico CSS and the fastlite sqlite library, although using both are optional; sqlite can be used directly or via the fastsql library, and any CSS framework can be used. FastHTML is compatible with web components and any vanilla JS library, but not with React, Vue, or Svelte. Support for the Surreal and css-scope-inline libraries are also included, but both are optional.')" 98 | ] 99 | }, 100 | "execution_count": null, 101 | "metadata": {}, 102 | "output_type": "execute_result" 103 | } 104 | ], 105 | "source": [ 106 | "d = parse_llm_txt(txt)\n", 107 | "d.title, d.summary" 108 | ] 109 | }, 110 | { 111 | "cell_type": "markdown", 112 | "id": "183ec528", 113 | "metadata": {}, 114 | "source": [ 115 | "...along with each of the H2-defined sections." 116 | ] 117 | }, 118 | { 119 | "cell_type": "code", 120 | "execution_count": null, 121 | "id": "1be1a3db", 122 | "metadata": {}, 123 | "outputs": [ 124 | { 125 | "data": { 126 | "text/plain": [ 127 | "['Docs', 'Examples', 'Optional']" 128 | ] 129 | }, 130 | "execution_count": null, 131 | "metadata": {}, 132 | "output_type": "execute_result" 133 | } 134 | ], 135 | "source": [ 136 | "list(d.sections)" 137 | ] 138 | }, 139 | { 140 | "cell_type": "markdown", 141 | "id": "6c58f319", 142 | "metadata": {}, 143 | "source": [ 144 | "Each section contains a list of URLs and optional extra info on each one." 145 | ] 146 | }, 147 | { 148 | "cell_type": "code", 149 | "execution_count": null, 150 | "id": "4c86b0dd", 151 | "metadata": {}, 152 | "outputs": [ 153 | { 154 | "data": { 155 | "text/plain": [ 156 | "(#1) [{'title': 'Starlette documentation', 'url': 'https://gist.githubusercontent.com/jph00/809e4a4808d4510be0e3dc9565e9cbd3/raw/9b717589ca44cedc8aaf00b2b8cacef922964c0f/starlette-sml.md', 'info': 'A subset of the Starlette documentation useful for FastHTML development'}]" 157 | ] 158 | }, 159 | "execution_count": null, 160 | "metadata": {}, 161 | "output_type": "execute_result" 162 | } 163 | ], 164 | "source": [ 165 | "d.sections.Optional" 166 | ] 167 | }, 168 | { 169 | "cell_type": "code", 170 | "execution_count": null, 171 | "id": "e4a529a9", 172 | "metadata": {}, 173 | "outputs": [], 174 | "source": [ 175 | "#| export\n", 176 | "Sections = partial(ft, 'sections')\n", 177 | "Project = partial(ft, 'project')" 178 | ] 179 | }, 180 | { 181 | "cell_type": "code", 182 | "execution_count": null, 183 | "id": "f5f184ad", 184 | "metadata": {}, 185 | "outputs": [], 186 | "source": [ 187 | "#| export\n", 188 | "def Doc(url, **kw):\n", 189 | " \"Create a `Doc` FT object with the text retrieved from `url` as the child, and `kw` as attrs.\"\n", 190 | " re_comment = re.compile('^$', flags=re.MULTILINE)\n", 191 | " txt = [o for o in httpx.get(url).text.splitlines() if not re_comment.search(o)]\n", 192 | " return ft('doc', '\\n'.join(txt), **kw)" 193 | ] 194 | }, 195 | { 196 | "cell_type": "code", 197 | "execution_count": null, 198 | "id": "470abbfe", 199 | "metadata": {}, 200 | "outputs": [], 201 | "source": [ 202 | "#| export\n", 203 | "def Section(nm, items):\n", 204 | " \"Create a `Section` FT object containing a `Doc` object for each child.\"\n", 205 | " return ft(nm, *[Doc(**o) for o in items])" 206 | ] 207 | }, 208 | { 209 | "cell_type": "code", 210 | "execution_count": null, 211 | "id": "e9a15def", 212 | "metadata": {}, 213 | "outputs": [], 214 | "source": [ 215 | "#| export\n", 216 | "def mk_ctx(d, optional=True):\n", 217 | " \"Create a `Project` with a `Section` for each H2 part in `d`, optionally skipping the 'optional' section.\"\n", 218 | " skip = '' if optional else 'Optional'\n", 219 | " sections = [Section(k, v) for k,v in d.sections.items() if k!=skip]\n", 220 | " return Project(title=d.title, summary=d.summary)(*sections)" 221 | ] 222 | }, 223 | { 224 | "cell_type": "code", 225 | "execution_count": null, 226 | "id": "2f9598d0", 227 | "metadata": {}, 228 | "outputs": [], 229 | "source": [ 230 | "ctx = mk_ctx(d)" 231 | ] 232 | }, 233 | { 234 | "cell_type": "code", 235 | "execution_count": null, 236 | "id": "c3546156", 237 | "metadata": {}, 238 | "outputs": [ 239 | { 240 | "data": { 241 | "text/plain": [ 242 | "('FastHTML quick start', 'A brief overview of many FastHTML features')" 243 | ] 244 | }, 245 | "execution_count": null, 246 | "metadata": {}, 247 | "output_type": "execute_result" 248 | } 249 | ], 250 | "source": [ 251 | "d0 = ctx.children[0].children[2]\n", 252 | "d0.title,d0.info" 253 | ] 254 | }, 255 | { 256 | "cell_type": "code", 257 | "execution_count": null, 258 | "id": "78b7b83c", 259 | "metadata": {}, 260 | "outputs": [ 261 | { 262 | "data": { 263 | "text/plain": [ 264 | "'# Web Devs Quickstart\\n\\n\\n\\n
\\n\\n> **Note**\\n>\\n> We’re going to be adding more to this document, so check back\\n> frequently for updates.\\n\\n
\\n\\n## Installation\\n\\n``` bash\\npip instal'" 265 | ] 266 | }, 267 | "execution_count": null, 268 | "metadata": {}, 269 | "output_type": "execute_result" 270 | } 271 | ], 272 | "source": [ 273 | "d0.children[0][:180]" 274 | ] 275 | }, 276 | { 277 | "cell_type": "code", 278 | "execution_count": null, 279 | "id": "7d6816a9", 280 | "metadata": {}, 281 | "outputs": [], 282 | "source": [ 283 | "#| export\n", 284 | "def get_sizes(ctx):\n", 285 | " return {o.tag:{p.title:len(p.children[0]) for p in o.children} for o in ctx.children}" 286 | ] 287 | }, 288 | { 289 | "cell_type": "code", 290 | "execution_count": null, 291 | "id": "213f450b", 292 | "metadata": {}, 293 | "outputs": [ 294 | { 295 | "data": { 296 | "text/plain": [ 297 | "{'docs': {'Surreal': 17720,\n", 298 | " 'CSS Scope Inline': 7836,\n", 299 | " 'FastHTML quick start': 19364,\n", 300 | " 'HTMX reference': 26427},\n", 301 | " 'examples': {'Todo list application': 18588, 'Websockets application': 693},\n", 302 | " 'optional': {'Starlette documentation': 48331}}" 303 | ] 304 | }, 305 | "execution_count": null, 306 | "metadata": {}, 307 | "output_type": "execute_result" 308 | } 309 | ], 310 | "source": [ 311 | "get_sizes(ctx)" 312 | ] 313 | }, 314 | { 315 | "cell_type": "code", 316 | "execution_count": null, 317 | "id": "983b6532", 318 | "metadata": {}, 319 | "outputs": [ 320 | { 321 | "data": { 322 | "text/plain": [ 323 | "151269" 324 | ] 325 | }, 326 | "execution_count": null, 327 | "metadata": {}, 328 | "output_type": "execute_result" 329 | } 330 | ], 331 | "source": [ 332 | "Path('fasthtml.md').write_text(to_xml(ctx))" 333 | ] 334 | }, 335 | { 336 | "cell_type": "code", 337 | "execution_count": null, 338 | "id": "57880ed3", 339 | "metadata": {}, 340 | "outputs": [], 341 | "source": [ 342 | "#| export\n", 343 | "@call_parse\n", 344 | "def llms_txt2ctx(\n", 345 | " fname:str, # File name to read\n", 346 | " optional:bool_arg=True # Skip 'optional' section?\n", 347 | "):\n", 348 | " \"Print a `Project` with a `Section` for each H2 part in file read from `fname`, optionally skipping the 'optional' section..\"\n", 349 | " d = parse_llm_txt(Path(fname).read_text())\n", 350 | " ctx = mk_ctx(d, optional=optional)\n", 351 | " print(to_xml(ctx))" 352 | ] 353 | }, 354 | { 355 | "cell_type": "code", 356 | "execution_count": null, 357 | "id": "0a8c4f14", 358 | "metadata": {}, 359 | "outputs": [], 360 | "source": [ 361 | "from contextlib import redirect_stdout" 362 | ] 363 | }, 364 | { 365 | "cell_type": "code", 366 | "execution_count": null, 367 | "id": "a572b85c", 368 | "metadata": {}, 369 | "outputs": [], 370 | "source": [ 371 | "with open('fasthtml-noopt.md', 'w') as f:\n", 372 | " with redirect_stdout(f): llms_txt2ctx.__wrapped__('llms.txt', optional=False)" 373 | ] 374 | }, 375 | { 376 | "cell_type": "markdown", 377 | "id": "c56f6c64", 378 | "metadata": {}, 379 | "source": [ 380 | "## Export -" 381 | ] 382 | }, 383 | { 384 | "cell_type": "code", 385 | "execution_count": null, 386 | "id": "bc7ea80e", 387 | "metadata": {}, 388 | "outputs": [], 389 | "source": [ 390 | "#|hide\n", 391 | "#|eval: false\n", 392 | "from nbdev import nbdev_export\n", 393 | "nbdev_export()" 394 | ] 395 | }, 396 | { 397 | "cell_type": "code", 398 | "execution_count": null, 399 | "id": "e0ec6dd5", 400 | "metadata": {}, 401 | "outputs": [], 402 | "source": [] 403 | } 404 | ], 405 | "metadata": { 406 | "kernelspec": { 407 | "display_name": "python3", 408 | "language": "python", 409 | "name": "python3" 410 | } 411 | }, 412 | "nbformat": 4, 413 | "nbformat_minor": 5 414 | } 415 | -------------------------------------------------------------------------------- /nbs/_quarto.yml: -------------------------------------------------------------------------------- 1 | project: 2 | type: website 3 | 4 | format: 5 | html: 6 | theme: cosmo 7 | css: styles.css 8 | toc: true 9 | keep-md: true 10 | commonmark: default 11 | 12 | website: 13 | twitter-card: true 14 | open-graph: true 15 | repo-actions: [issue] 16 | navbar: 17 | background: primary 18 | search: true 19 | sidebar: 20 | style: floating 21 | 22 | metadata-files: [nbdev.yml, sidebar.yml] 23 | -------------------------------------------------------------------------------- /nbs/index.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": null, 6 | "metadata": {}, 7 | "outputs": [], 8 | "source": [ 9 | "#| hide\n", 10 | "from llm_ctx import *" 11 | ] 12 | }, 13 | { 14 | "cell_type": "markdown", 15 | "metadata": {}, 16 | "source": [ 17 | "# llm_ctx\n", 18 | "\n", 19 | "> Create an LLM XML context document from an llms.txt file" 20 | ] 21 | }, 22 | { 23 | "cell_type": "markdown", 24 | "metadata": {}, 25 | "source": [ 26 | "Given an `llms.txt` file, this provides a CLI and Python API to parse the file and create an XML context file from it. The input file should follow this format:\n", 27 | "\n", 28 | "```\n", 29 | "# FastHTML\n", 30 | "\n", 31 | "> FastHTML is a python library which brings together Starlette, Uvicorn, HTMX, and fastcore's `FT` \"FastTags\" into a library for creating server-rendered hypermedia applications.\n", 32 | "\n", 33 | "## Docs\n", 34 | "\n", 35 | "- [Surreal](https://raw.githubusercontent.com/AnswerDotAI/surreal/main/README.md): Tiny jQuery alternative with Locality of Behavior\n", 36 | "- [FastHTML quick start](https://docs.fastht.ml/tutorials/quickstart_for_web_devs.html.md): An overview of FastHTML features\n", 37 | "\n", 38 | "## Examples\n", 39 | "\n", 40 | "- [Todo list application](https://raw.githubusercontent.com/AnswerDotAI/fasthtml/main/examples/adv_app.py)\n", 41 | "\n", 42 | "## Optional\n", 43 | "\n", 44 | "- [Starlette docs](https://gist.githubusercontent.com/jph00/809e4a4808d4510be0e3dc9565e9cbd3/raw/9b717589ca44cedc8aaf00b2b8cacef922964c0f/starlette-sml.md): A subset of the Starlette documentation useful for FastHTML development\n", 45 | "```" 46 | ] 47 | }, 48 | { 49 | "cell_type": "markdown", 50 | "metadata": {}, 51 | "source": [ 52 | "## Install" 53 | ] 54 | }, 55 | { 56 | "cell_type": "markdown", 57 | "metadata": {}, 58 | "source": [ 59 | "```sh\n", 60 | "pip install llm-ctx\n", 61 | "```" 62 | ] 63 | }, 64 | { 65 | "cell_type": "markdown", 66 | "metadata": {}, 67 | "source": [ 68 | "## How to use" 69 | ] 70 | }, 71 | { 72 | "cell_type": "markdown", 73 | "metadata": {}, 74 | "source": [ 75 | "To get help for the CLI:\n", 76 | "\n", 77 | "```sh\n", 78 | "llms_txt2ctx -h\n", 79 | "```\n", 80 | "\n", 81 | "To convert an `llms.txt` file to XML context and save to `llms.md`:\n", 82 | "\n", 83 | "```sh\n", 84 | "llms_txt2ctx llms.txt > llms.md\n", 85 | "```\n", 86 | "\n", 87 | "Pass `--optional False` to skip the 'optional' section of the input file." 88 | ] 89 | }, 90 | { 91 | "cell_type": "code", 92 | "execution_count": null, 93 | "metadata": {}, 94 | "outputs": [], 95 | "source": [] 96 | } 97 | ], 98 | "metadata": { 99 | "kernelspec": { 100 | "display_name": "Python 3 (ipykernel)", 101 | "language": "python", 102 | "name": "python3" 103 | }, 104 | "language_info": { 105 | "codemirror_mode": { 106 | "name": "ipython", 107 | "version": 3 108 | }, 109 | "file_extension": ".py", 110 | "mimetype": "text/x-python", 111 | "name": "python", 112 | "nbconvert_exporter": "python", 113 | "pygments_lexer": "ipython3", 114 | "version": "3.11.8" 115 | } 116 | }, 117 | "nbformat": 4, 118 | "nbformat_minor": 4 119 | } 120 | -------------------------------------------------------------------------------- /nbs/llms.txt: -------------------------------------------------------------------------------- 1 | # FastHTML 2 | 3 | > FastHTML is a python library which brings together Starlette, Uvicorn, HTMX, and fastcore's `FT` "FastTags" into a library for creating server-rendered hypermedia applications. The `FastHTML` class itself inherits from `Starlette`, and adds decorator-based routing with many additions, Beforeware, automatic `FT` to HTML rendering, and much more. Although parts of its API are inspired by FastAPI, it is *not* compatible with FastAPI syntax and is not targeted at creating API services. FastHTML includes support for Pico CSS and the fastlite sqlite library, although using both are optional; sqlite can be used directly or via the fastsql library, and any CSS framework can be used. FastHTML is compatible with web components and any vanilla JS library, but not with React, Vue, or Svelte. Support for the Surreal and css-scope-inline libraries are also included, but both are optional. 4 | 5 | ## Docs 6 | 7 | - [Surreal](https://raw.githubusercontent.com/AnswerDotAI/surreal/main/README.md): Tiny jQuery alternative for plain Javascript with inline Locality of Behavior, providing `me` and `any` functions 8 | - [CSS Scope Inline](https://raw.githubusercontent.com/gnat/css-scope-inline/main/README.md): A JS library which allow `me` to be used in CSS selectors, by using a `MutationObserver` to monitor the DOM 9 | - [FastHTML quick start](https://docs.fastht.ml/tutorials/quickstart_for_web_devs.html.md): A brief overview of many FastHTML features 10 | - [HTMX reference](https://raw.githubusercontent.com/bigskysoftware/htmx/master/www/content/reference.md): Brief description of all HTMX attributes, CSS classes, headers, events, extensions, js lib methods, and config options 11 | 12 | ## Examples 13 | 14 | - [Todo list application](https://raw.githubusercontent.com/AnswerDotAI/fasthtml/main/examples/adv_app.py) 15 | - [Websockets application](https://raw.githubusercontent.com/AnswerDotAI/fasthtml/main/examples/basic_ws.py) 16 | 17 | ## Optional 18 | 19 | - [Starlette documentation](https://gist.githubusercontent.com/jph00/809e4a4808d4510be0e3dc9565e9cbd3/raw/9b717589ca44cedc8aaf00b2b8cacef922964c0f/starlette-sml.md): A subset of the Starlette documentation useful for FastHTML development 20 | 21 | -------------------------------------------------------------------------------- /nbs/nbdev.yml: -------------------------------------------------------------------------------- 1 | project: 2 | output-dir: _docs 3 | 4 | website: 5 | title: "llm_ctx" 6 | site-url: "https://AnswerDotAI.github.io/llm_ctx" 7 | description: "Create an LLM XML context document from an llms.txt file" 8 | repo-branch: main 9 | repo-url: "https://github.com/AnswerDotAI/llm_ctx" 10 | -------------------------------------------------------------------------------- /nbs/styles.css: -------------------------------------------------------------------------------- 1 | .cell { 2 | margin-bottom: 1rem; 3 | } 4 | 5 | .cell > .sourceCode { 6 | margin-bottom: 0; 7 | } 8 | 9 | .cell-output > pre { 10 | margin-bottom: 0; 11 | } 12 | 13 | .cell-output > pre, .cell-output > .sourceCode > pre, .cell-output-stdout > pre { 14 | margin-left: 0.8rem; 15 | margin-top: 0; 16 | background: none; 17 | border-left: 2px solid lightsalmon; 18 | border-top-left-radius: 0; 19 | border-top-right-radius: 0; 20 | } 21 | 22 | .cell-output > .sourceCode { 23 | border: none; 24 | } 25 | 26 | .cell-output > .sourceCode { 27 | background: none; 28 | margin-top: 0; 29 | } 30 | 31 | div.description { 32 | padding-left: 2px; 33 | padding-top: 5px; 34 | font-style: italic; 35 | font-size: 135%; 36 | opacity: 70%; 37 | } 38 | -------------------------------------------------------------------------------- /settings.ini: -------------------------------------------------------------------------------- 1 | [DEFAULT] 2 | repo = llm-ctx 3 | lib_name = llm-ctx 4 | version = 0.0.2 5 | min_python = 3.7 6 | license = apache2 7 | black_formatting = False 8 | console_scripts = llms_txt2ctx=llm_ctx.core:llms_txt2ctx 9 | doc_path = _docs 10 | lib_path = llm_ctx 11 | nbs_path = nbs 12 | recursive = True 13 | tst_flags = notest 14 | put_version_in_init = True 15 | branch = main 16 | custom_sidebar = False 17 | doc_host = https://AnswerDotAI.github.io 18 | doc_baseurl = /llm-ctx 19 | git_url = https://github.com/AnswerDotAI/llm-ctx 20 | title = llm-ctx 21 | audience = Developers 22 | author = Jeremy Howard 23 | author_email = github@jhoward.fastmail.fm 24 | copyright = 2024 onwards, Jeremy Howard 25 | description = Create an LLM XML context document from an llms.txt file 26 | keywords = nbdev jupyter notebook python 27 | language = English 28 | status = 3 29 | user = AnswerDotAI 30 | requirements = fastcore httpx 31 | conda_user = fastai 32 | readme_nb = index.ipynb 33 | allowed_metadata_keys = 34 | allowed_cell_metadata_keys = 35 | jupyter_hooks = False 36 | clean_ids = True 37 | clear_all = False 38 | cell_number = True 39 | 40 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from pkg_resources import parse_version 2 | from configparser import ConfigParser 3 | import setuptools, shlex 4 | assert parse_version(setuptools.__version__)>=parse_version('36.2') 5 | 6 | # note: all settings are in settings.ini; edit there, not here 7 | config = ConfigParser(delimiters=['=']) 8 | config.read('settings.ini', encoding='utf-8') 9 | cfg = config['DEFAULT'] 10 | 11 | cfg_keys = 'version description keywords author author_email'.split() 12 | expected = cfg_keys + "lib_name user branch license status min_python audience language".split() 13 | for o in expected: assert o in cfg, "missing expected setting: {}".format(o) 14 | setup_cfg = {o:cfg[o] for o in cfg_keys} 15 | 16 | licenses = { 17 | 'apache2': ('Apache Software License 2.0','OSI Approved :: Apache Software License'), 18 | 'mit': ('MIT License', 'OSI Approved :: MIT License'), 19 | 'gpl2': ('GNU General Public License v2', 'OSI Approved :: GNU General Public License v2 (GPLv2)'), 20 | 'gpl3': ('GNU General Public License v3', 'OSI Approved :: GNU General Public License v3 (GPLv3)'), 21 | 'bsd3': ('BSD License', 'OSI Approved :: BSD License'), 22 | } 23 | statuses = [ '1 - Planning', '2 - Pre-Alpha', '3 - Alpha', 24 | '4 - Beta', '5 - Production/Stable', '6 - Mature', '7 - Inactive' ] 25 | py_versions = '3.6 3.7 3.8 3.9 3.10'.split() 26 | 27 | requirements = shlex.split(cfg.get('requirements', '')) 28 | if cfg.get('pip_requirements'): requirements += shlex.split(cfg.get('pip_requirements', '')) 29 | min_python = cfg['min_python'] 30 | lic = licenses.get(cfg['license'].lower(), (cfg['license'], None)) 31 | dev_requirements = (cfg.get('dev_requirements') or '').split() 32 | 33 | setuptools.setup( 34 | name = cfg['lib_name'], 35 | license = lic[0], 36 | classifiers = [ 37 | 'Development Status :: ' + statuses[int(cfg['status'])], 38 | 'Intended Audience :: ' + cfg['audience'].title(), 39 | 'Natural Language :: ' + cfg['language'].title(), 40 | ] + ['Programming Language :: Python :: '+o for o in py_versions[py_versions.index(min_python):]] + (['License :: ' + lic[1] ] if lic[1] else []), 41 | url = cfg['git_url'], 42 | packages = setuptools.find_packages(), 43 | include_package_data = True, 44 | install_requires = requirements, 45 | extras_require={ 'dev': dev_requirements }, 46 | dependency_links = cfg.get('dep_links','').split(), 47 | python_requires = '>=' + cfg['min_python'], 48 | long_description = open('README.md', encoding='utf-8').read(), 49 | long_description_content_type = 'text/markdown', 50 | zip_safe = False, 51 | entry_points = { 52 | 'console_scripts': cfg.get('console_scripts','').split(), 53 | 'nbdev': [f'{cfg.get("lib_path")}={cfg.get("lib_path")}._modidx:d'] 54 | }, 55 | **setup_cfg) 56 | 57 | 58 | --------------------------------------------------------------------------------