├── .github └── workflows │ ├── publish.yml │ └── test.yml ├── .gitignore ├── LICENSE ├── README.md ├── llm_anyscale_endpoints.py ├── pyproject.toml └── tests └── test_llm_anyscale_endpoints.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", "3.12"] 16 | steps: 17 | - uses: actions/checkout@v4 18 | - name: Set up Python ${{ matrix.python-version }} 19 | uses: actions/setup-python@v5 20 | with: 21 | python-version: ${{ matrix.python-version }} 22 | cache: pip 23 | cache-dependency-path: pyproject.toml 24 | - name: Install dependencies 25 | run: | 26 | pip install -e '.[test]' 27 | - name: Run tests 28 | run: | 29 | pytest 30 | deploy: 31 | runs-on: ubuntu-latest 32 | needs: [test] 33 | environment: release 34 | permissions: 35 | id-token: write 36 | steps: 37 | - uses: actions/checkout@v4 38 | - name: Set up Python 39 | uses: actions/setup-python@v5 40 | with: 41 | python-version: "3.12" 42 | cache: pip 43 | cache-dependency-path: pyproject.toml 44 | - name: Install dependencies 45 | run: | 46 | pip install setuptools wheel build 47 | - name: Build 48 | run: | 49 | python -m build 50 | - name: Publish 51 | uses: pypa/gh-action-pypi-publish@release/v1 52 | 53 | -------------------------------------------------------------------------------- /.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", "3.12"] 14 | steps: 15 | - uses: actions/checkout@v4 16 | - name: Set up Python ${{ matrix.python-version }} 17 | uses: actions/setup-python@v5 18 | with: 19 | python-version: ${{ matrix.python-version }} 20 | cache: pip 21 | cache-dependency-path: pyproject.toml 22 | - name: Install dependencies 23 | run: | 24 | pip install -e '.[test]' 25 | - name: Run tests 26 | run: | 27 | pytest 28 | 29 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .venv 2 | __pycache__/ 3 | *.py[cod] 4 | *$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 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # llm-anyscale-endpoints 2 | 3 | [![PyPI](https://img.shields.io/pypi/v/llm-anyscale-endpoints.svg)](https://pypi.org/project/llm-anyscale-endpoints/) 4 | [![Changelog](https://img.shields.io/github/v/release/simonw/llm-anyscale-endpoints?include_prereleases&label=changelog)](https://github.com/simonw/llm-anyscale-endpoints/releases) 5 | [![Tests](https://github.com/simonw/llm-anyscale-endpoints/workflows/Test/badge.svg)](https://github.com/simonw/llm-anyscale-endpoints/actions?query=workflow%3ATest) 6 | [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/llm-anyscale-endpoints/blob/main/LICENSE) 7 | 8 | [LLM](https://llm.datasette.io/) plugin for models hosted by [Anyscale Endpoints](https://app.endpoints.anyscale.com/) 9 | 10 | ## Installation 11 | 12 | First, [install the LLM command-line utility](https://llm.datasette.io/en/stable/setup.html). 13 | 14 | Now install this plugin in the same environment as LLM. 15 | ```bash 16 | llm install llm-anyscale-endpoints 17 | ``` 18 | ## Configuration 19 | 20 | You will need an API key from Anyscale Endpoints. You can [obtain one here](https://app.endpoints.anyscale.com/). 21 | 22 | You can set that as an environment variable called `LLM_ANYSCALE_ENDPOINTS_KEY`, or add it to the `llm` set of saved keys using: 23 | 24 | ```bash 25 | llm keys set anyscale-endpoints 26 | ``` 27 | ``` 28 | Enter key: 29 | ``` 30 | 31 | ## Usage 32 | 33 | To list available models, run: 34 | ```bash 35 | llm models list 36 | ``` 37 | You should see a list that looks something like this: 38 | ``` 39 | AnyscaleEndpoints: meta-llama/Llama-2-7b-chat-hf 40 | AnyscaleEndpoints: meta-llama/Llama-2-13b-chat-hf 41 | AnyscaleEndpoints: mistralai/Mixtral-8x7B-Instruct-v0.1 42 | AnyscaleEndpoints: mistralai/Mistral-7B-Instruct-v0.1 43 | AnyscaleEndpoints: meta-llama/Llama-2-70b-chat-hf 44 | AnyscaleEndpoints: meta-llama/Llama-3-8b-chat-hf 45 | AnyscaleEndpoints: meta-llama/Llama-3-70b-chat-hf 46 | AnyscaleEndpoints: codellama/CodeLlama-70b-Instruct-hf 47 | AnyscaleEndpoints: mistralai/Mixtral-8x22B-Instruct-v0.1 48 | AnyscaleEndpoints: mlabonne/NeuralHermes-2.5-Mistral-7B 49 | AnyscaleEndpoints: google/gemma-7b-it 50 | ``` 51 | To run a prompt against a model, pass its full model ID to the `-m` option, like this: 52 | ```bash 53 | llm -m mistralai/Mixtral-8x22B-Instruct-v0.1 \ 54 | 'Five strident names for a pet walrus' \ 55 | --system 'You love coming up with creative names for pets' 56 | ``` 57 | You can set a shorter alias for a model using the `llm aliases` command like so: 58 | ```bash 59 | llm aliases set mix22b mistralai/Mixtral-8x22B-Instruct-v0.1 60 | ``` 61 | Now you can prompt Mixtral-8x22B-Instruct-v0.1 using the alias `mix22b`: 62 | ```bash 63 | cat llm_anyscale_endpoints.py | \ 64 | llm -m mix22b -s 'explain this code' 65 | ``` 66 | 67 | You can refresh the list of models by running: 68 | ```bash 69 | llm anyscale-endpoints refresh 70 | ``` 71 | This will fetch the latest list of models from Anyscale Endpoints and story it in a local cache file. 72 | 73 | ## Development 74 | 75 | To set up this plugin locally, first checkout the code. Then create a new virtual environment: 76 | ```bash 77 | cd llm-anyscale-endpoints 78 | python3 -m venv venv 79 | source venv/bin/activate 80 | ``` 81 | Now install the dependencies and test dependencies: 82 | ```bash 83 | pip install -e '.[test]' 84 | ``` 85 | To run the tests: 86 | ```bash 87 | pytest 88 | ``` 89 | -------------------------------------------------------------------------------- /llm_anyscale_endpoints.py: -------------------------------------------------------------------------------- 1 | import click 2 | import httpx 3 | import json 4 | import llm 5 | from llm.default_plugins.openai_models import Chat 6 | 7 | MODELS = ( 8 | "meta-llama/Llama-2-7b-chat-hf", 9 | "meta-llama/Llama-2-13b-chat-hf", 10 | "mistralai/Mixtral-8x7B-Instruct-v0.1", 11 | "mistralai/Mistral-7B-Instruct-v0.1", 12 | "meta-llama/Llama-2-70b-chat-hf", 13 | "meta-llama/Llama-3-8b-chat-hf", 14 | "meta-llama/Llama-3-70b-chat-hf", 15 | "codellama/CodeLlama-70b-Instruct-hf", 16 | "mistralai/Mixtral-8x22B-Instruct-v0.1", 17 | "mlabonne/NeuralHermes-2.5-Mistral-7B", 18 | "google/gemma-7b-it" 19 | ) 20 | 21 | 22 | class AnyscaleEndpointChat(Chat): 23 | needs_key = "anyscale-endpoints" 24 | 25 | def __str__(self): 26 | return "AnyscaleEndpoints: {}".format(self.model_id) 27 | 28 | 29 | @llm.hookimpl 30 | def register_commands(cli): 31 | @cli.group(name="anyscale-endpoints") 32 | def anyscale_endpoints(): 33 | "llm-anyscale-endpoints plugin commands" 34 | 35 | @anyscale_endpoints.command(name="refresh") 36 | def refresh(): 37 | "Refresh the list of models from the Anyscale Endpoints API" 38 | key = llm.get_key("", "anyscale-endpoints", "LLM_ANYSCALE_ENDPOINTS_KEY") 39 | if not key: 40 | raise click.ClickException("No key found for Anyscale Endpoints") 41 | headers = {"Authorization": f"Bearer {key}"} 42 | response = httpx.get( 43 | "https://api.endpoints.anyscale.com/v1/models", headers=headers 44 | ) 45 | response.raise_for_status() 46 | models = response.json()["data"] 47 | # Filter out just the ones with "rayllm_metadata": {"engine_config": {"model_type": "text-generation"}} 48 | text_generation = [ 49 | model["id"] 50 | for model in models 51 | if model.get("rayllm_metadata", {}) 52 | .get("engine_config", {}) 53 | .get("model_type") 54 | == "text-generation" 55 | ] 56 | if not text_generation: 57 | raise click.ClickException("No text-generation models found") 58 | path = llm.user_dir() / "llm-anyscale-endpoints.json" 59 | path.write_text(json.dumps(text_generation, indent=4)) 60 | click.echo("{} models saved to {}".format(len(text_generation), path), err=True) 61 | click.echo(json.dumps(text_generation, indent=4)) 62 | 63 | 64 | @llm.hookimpl 65 | def register_models(register): 66 | # Only do this if the key is set 67 | key = llm.get_key("", "anyscale-endpoints", "LLM_ANYSCALE_ENDPOINTS_KEY") 68 | if not key: 69 | return 70 | # If llm-anyscale-endpoints.json exists, use that - otherwise use MODELS 71 | path = llm.user_dir() / "llm-anyscale-endpoints.json" 72 | if path.exists(): 73 | model_ids = json.loads(path.read_text()) 74 | else: 75 | model_ids = MODELS 76 | 77 | for model_id in model_ids: 78 | register( 79 | AnyscaleEndpointChat( 80 | model_id=model_id, 81 | model_name=model_id, 82 | api_base="https://api.endpoints.anyscale.com/v1", 83 | ) 84 | ) 85 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [project] 2 | name = "llm-anyscale-endpoints" 3 | version = "0.6" 4 | description = " LLM plugin for models hosted by Anyscale Endpoints" 5 | readme = "README.md" 6 | authors = [{name = "Simon Willison"}] 7 | license = {text = "Apache-2.0"} 8 | classifiers = [ 9 | "License :: OSI Approved :: Apache Software License" 10 | ] 11 | dependencies = [ 12 | "llm>=0.8", 13 | ] 14 | 15 | [project.urls] 16 | Homepage = "https://github.com/simonw/llm-anyscale-endpoints" 17 | Changelog = "https://github.com/simonw/llm-anyscale-endpoints/releases" 18 | Issues = "https://github.com/simonw/llm-anyscale-endpoints/issues" 19 | CI = "https://github.com/simonw/llm-anyscale-endpoints/actions" 20 | 21 | [project.entry-points.llm] 22 | anyscale_endpoints = "llm_anyscale_endpoints" 23 | 24 | [project.optional-dependencies] 25 | test = ["pytest", "pytest-httpx"] 26 | -------------------------------------------------------------------------------- /tests/test_llm_anyscale_endpoints.py: -------------------------------------------------------------------------------- 1 | from click.testing import CliRunner 2 | from llm.cli import cli 3 | from llm_anyscale_endpoints import MODELS 4 | import json 5 | import pytest 6 | 7 | 8 | @pytest.fixture 9 | def user_path(monkeypatch, tmpdir): 10 | dir = tmpdir / "llm.datasette.io" 11 | dir.mkdir() 12 | monkeypatch.setenv("LLM_USER_PATH", str(dir)) 13 | return dir 14 | 15 | 16 | @pytest.mark.parametrize("set_key", (False, True)) 17 | def test_llm_models(set_key, user_path): 18 | runner = CliRunner() 19 | if set_key: 20 | (user_path / "keys.json").write_text( 21 | json.dumps({"anyscale-endpoints": "x"}), "utf-8" 22 | ) 23 | result = runner.invoke(cli, ["models", "list"]) 24 | assert result.exit_code == 0, result.output 25 | fragments = ["AnyscaleEndpoints: {}".format(model_id) for model_id in MODELS] 26 | for fragment in fragments: 27 | if set_key: 28 | assert fragment in result.output 29 | else: 30 | assert fragment not in result.output 31 | --------------------------------------------------------------------------------