├── .github └── workflows │ ├── publish.yml │ └── test.yml ├── .gitignore ├── LICENSE ├── Pipfile ├── README.md ├── llm_markov └── __init__.py ├── setup.py └── tests ├── conftest.py └── test_llm_markov.py /.github/workflows/publish.yml: -------------------------------------------------------------------------------- 1 | name: Publish Python Package 2 | 3 | on: 4 | release: 5 | types: [created] 6 | 7 | permissions: 8 | contents: read 9 | 10 | jobs: 11 | test: 12 | runs-on: ubuntu-latest 13 | strategy: 14 | matrix: 15 | python-version: ["3.8", "3.9", "3.10", "3.11"] 16 | steps: 17 | - uses: actions/checkout@v3 18 | - name: Set up Python ${{ matrix.python-version }} 19 | uses: actions/setup-python@v4 20 | with: 21 | python-version: ${{ matrix.python-version }} 22 | cache: pip 23 | cache-dependency-path: setup.py 24 | - name: Install dependencies 25 | run: | 26 | pip install '.[test]' 27 | - name: Run tests 28 | run: | 29 | pytest 30 | deploy: 31 | runs-on: ubuntu-latest 32 | needs: [test] 33 | steps: 34 | - uses: actions/checkout@v3 35 | - name: Set up Python 36 | uses: actions/setup-python@v4 37 | with: 38 | python-version: "3.11" 39 | cache: pip 40 | cache-dependency-path: setup.py 41 | - name: Install dependencies 42 | run: | 43 | pip install setuptools wheel twine build 44 | - name: Publish 45 | env: 46 | TWINE_USERNAME: __token__ 47 | TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }} 48 | run: | 49 | python -m build 50 | twine upload dist/* 51 | -------------------------------------------------------------------------------- /.github/workflows/test.yml: -------------------------------------------------------------------------------- 1 | name: Test 2 | 3 | on: [push, pull_request] 4 | 5 | permissions: 6 | contents: read 7 | 8 | jobs: 9 | test: 10 | runs-on: ubuntu-latest 11 | strategy: 12 | matrix: 13 | python-version: ["3.8", "3.9", "3.10", "3.11"] 14 | steps: 15 | - uses: actions/checkout@v3 16 | - name: Set up Python ${{ matrix.python-version }} 17 | uses: actions/setup-python@v4 18 | with: 19 | python-version: ${{ matrix.python-version }} 20 | cache: pip 21 | cache-dependency-path: setup.py 22 | - name: Install dependencies 23 | run: | 24 | pip install '.[test]' 25 | - name: Run tests 26 | run: | 27 | pytest 28 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .venv 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | venv 6 | .eggs 7 | .pytest_cache 8 | *.egg-info 9 | .DS_Store 10 | .vscode 11 | dist 12 | build 13 | -------------------------------------------------------------------------------- /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 [yyyy] [name of copyright owner] 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 | -------------------------------------------------------------------------------- /Pipfile: -------------------------------------------------------------------------------- 1 | [[source]] 2 | url = "https://pypi.org/simple" 3 | verify_ssl = true 4 | name = "pypi" 5 | 6 | [packages] 7 | 8 | [dev-packages] 9 | 10 | [requires] 11 | python_version = "3.10" 12 | python_full_version = "3.10.10" 13 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # llm-markov 2 | 3 | [![PyPI](https://img.shields.io/pypi/v/llm-markov.svg)](https://pypi.org/project/llm-markov/) 4 | [![Changelog](https://img.shields.io/github/v/release/simonw/llm-markov?include_prereleases&label=changelog)](https://github.com/simonw/llm-markov/releases) 5 | [![Tests](https://github.com/simonw/llm-markov/workflows/Test/badge.svg)](https://github.com/simonw/llm-markov/actions?query=workflow%3ATest) 6 | [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/llm-markov/blob/main/LICENSE) 7 | 8 | Plugin for [LLM](https://llm.datasette.io/) adding a [Markov chain](https://en.wikipedia.org/wiki/Markov_chain) generating model 9 | 10 | ## Installation 11 | 12 | Install this plugin in the same environment as LLM. 13 | ```bash 14 | llm install llm-markov 15 | ``` 16 | ## Usage 17 | 18 | This plugin adds a model called `markov`. You can execute it like this: 19 | 20 | ```bash 21 | llm -m markov "The quick brown fox jumps over the lazy dog" 22 | ``` 23 | 24 | My default it will produce 100 words. You can control the number of words with the `-o number` option: 25 | 26 | ```bash 27 | llm -m markov -o 20 "The quick brown fox jumps over the lazy dog" 28 | ``` 29 | A delay of 0.02s is simulated between each token. You can modify this using the `-o delay` option - to `0` to disable it, or some other floating point number of seconds to customize it: 30 | 31 | ```bash 32 | llm -m markov "The quick brown fox jumps over the lazy dog" -o delay 0 33 | llm -m markov "The quick brown fox jumps over the lazy dog" -o delay 0.1 -o length 20 34 | ``` 35 | 36 | ## Development 37 | 38 | To set up this plugin locally, first checkout the code. Then create a new virtual environment: 39 | 40 | cd llm-markov 41 | python3 -m venv venv 42 | source venv/bin/activate 43 | 44 | Now install the dependencies and test dependencies: 45 | 46 | pip install -e '.[test]' 47 | 48 | To run the tests: 49 | 50 | pytest 51 | -------------------------------------------------------------------------------- /llm_markov/__init__.py: -------------------------------------------------------------------------------- 1 | from llm import Model, Prompt, hookimpl 2 | import llm 3 | from collections import defaultdict 4 | from pydantic import field_validator 5 | import random 6 | import time 7 | from typing import Optional 8 | 9 | DEFAULT_LENGTH = 100 10 | DEFAULT_DELAY = 0.02 11 | 12 | 13 | @hookimpl 14 | def register_models(register): 15 | register(Markov()) 16 | 17 | 18 | class Markov(Model): 19 | can_stream = True 20 | model_id = "markov" 21 | 22 | class Options(llm.Options): 23 | length: Optional[int] = None 24 | delay: Optional[float] = None 25 | 26 | @field_validator("length") 27 | def validate_length(cls, length): 28 | if length is None: 29 | return None 30 | if length < 2: 31 | raise ValueError("length must be >= 2") 32 | return length 33 | 34 | @field_validator("delay") 35 | def validate_delay(cls, delay): 36 | if delay is None: 37 | return None 38 | if not 0 <= delay <= 10: 39 | raise ValueError("delay must be between 0 and 10") 40 | return delay 41 | 42 | def execute(self, prompt, stream, response, conversation): 43 | length = prompt.options.length or DEFAULT_LENGTH 44 | delay = DEFAULT_DELAY 45 | if prompt.options.delay is not None: 46 | delay = prompt.options.delay 47 | 48 | if not stream: 49 | delay = 0 50 | 51 | transitions = defaultdict(list) 52 | all_words = prompt.prompt.split() 53 | for i in range(len(all_words) - 1): 54 | transitions[all_words[i]].append(all_words[i + 1]) 55 | 56 | result = [all_words[0]] 57 | for _ in range(length): 58 | if transitions[result[-1]]: 59 | token = random.choice(transitions[result[-1]]) 60 | else: 61 | token = random.choice(all_words) 62 | yield token + " " 63 | time.sleep(delay) 64 | result.append(token) 65 | 66 | def __str__(self): 67 | return "Markov: {}".format(self.model_id) 68 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from setuptools import setup 2 | import os 3 | 4 | VERSION = "0.1" 5 | 6 | 7 | def get_long_description(): 8 | with open( 9 | os.path.join(os.path.dirname(os.path.abspath(__file__)), "README.md"), 10 | encoding="utf8", 11 | ) as fp: 12 | return fp.read() 13 | 14 | 15 | setup( 16 | name="llm-markov", 17 | description="Plugin for LLM adding a Markov chain generating model", 18 | long_description=get_long_description(), 19 | long_description_content_type="text/markdown", 20 | author="Simon Willison", 21 | url="https://github.com/simonw/llm-markov", 22 | project_urls={ 23 | "Issues": "https://github.com/simonw/llm-markov/issues", 24 | "CI": "https://github.com/simonw/llm-markov/actions", 25 | "Changelog": "https://github.com/simonw/llm-markov/releases", 26 | }, 27 | license="Apache License, Version 2.0", 28 | classifiers=["License :: OSI Approved :: Apache Software License"], 29 | version=VERSION, 30 | packages=["llm_markov"], 31 | entry_points={"llm": ["llm_markov = llm_markov"]}, 32 | install_requires=["llm>=0.5"], 33 | extras_require={"test": ["pytest"]}, 34 | python_requires=">=3.7", 35 | ) 36 | -------------------------------------------------------------------------------- /tests/conftest.py: -------------------------------------------------------------------------------- 1 | import pytest 2 | 3 | 4 | @pytest.fixture 5 | def user_path(tmpdir): 6 | dir = tmpdir / "llm.datasette.io" 7 | dir.mkdir() 8 | return dir 9 | 10 | 11 | @pytest.fixture(autouse=True) 12 | def env_setup(monkeypatch, user_path): 13 | monkeypatch.setenv("LLM_USER_PATH", str(user_path)) 14 | -------------------------------------------------------------------------------- /tests/test_llm_markov.py: -------------------------------------------------------------------------------- 1 | from click.testing import CliRunner 2 | from llm.cli import cli 3 | import pytest 4 | import time 5 | 6 | 7 | @pytest.mark.parametrize("length", [10, 20]) 8 | def test_markov_prompt(length): 9 | runner = CliRunner() 10 | prompt = "the quick brown fox jumped over the lazy dog" 11 | args = [ 12 | prompt, 13 | "-m", 14 | "markov", 15 | "-o", 16 | "length", 17 | str(length), 18 | ] 19 | result = runner.invoke(cli, args) 20 | assert result.exit_code == 0, result.output 21 | words = result.output.strip().split() 22 | # ['lazy', 'dog', 'brown', 'fox', 'jumped', 'over', 'the', 'quick', 'brown'] 23 | # Every word should be one of the original prompt 24 | prompt_words = prompt.split() 25 | for word in words: 26 | assert word in prompt_words 27 | assert len(words) == length 28 | --------------------------------------------------------------------------------