├── .github └── workflows │ ├── publish.yml │ └── test.yml ├── .gitignore ├── LICENSE ├── README.md ├── llm_embed_jina.py ├── pyproject.toml └── tests └── test_embed_jina.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: Cache models 25 | uses: actions/cache@v3 26 | with: 27 | path: ~/.cache/torch 28 | key: ${{ runner.os }}-torch- 29 | - name: Install dependencies 30 | run: | 31 | pip install -e '.[test]' 32 | - name: Run tests 33 | run: | 34 | pytest -s 35 | deploy: 36 | runs-on: ubuntu-latest 37 | needs: [test] 38 | steps: 39 | - uses: actions/checkout@v3 40 | - name: Set up Python 41 | uses: actions/setup-python@v4 42 | with: 43 | python-version: "3.11" 44 | cache: pip 45 | cache-dependency-path: setup.py 46 | - name: Install dependencies 47 | run: | 48 | pip install setuptools wheel twine build 49 | - name: Publish 50 | env: 51 | TWINE_USERNAME: __token__ 52 | TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }} 53 | run: | 54 | python -m build 55 | twine upload dist/* 56 | -------------------------------------------------------------------------------- /.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: Cache models 23 | uses: actions/cache@v3 24 | with: 25 | path: ~/.cache 26 | key: ${{ runner.os }}-torch- 27 | - name: Install dependencies 28 | run: | 29 | pip install -e '.[test]' 30 | - name: Run tests 31 | run: | 32 | pytest -s 33 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .venv 2 | __pycache__/ 3 | *.py[cod] 4 | *$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-embed-jina 2 | 3 | [![PyPI](https://img.shields.io/pypi/v/llm-embed-jina.svg)](https://pypi.org/project/llm-embed-jina/) 4 | [![Changelog](https://img.shields.io/github/v/release/simonw/llm-embed-jina?include_prereleases&label=changelog)](https://github.com/simonw/llm-embed-jina/releases) 5 | [![Tests](https://github.com/simonw/llm-embed-jina/workflows/Test/badge.svg)](https://github.com/simonw/llm-embed-jina/actions?query=workflow%3ATest) 6 | [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/llm-embed-jina/blob/main/LICENSE) 7 | 8 | Embedding models from Jina AI 9 | 10 | ## Background 11 | 12 | [Jina AI Launches World's First Open-Source 8K Text Embedding, Rivaling OpenAI](https://jina.ai/news/jina-ai-launches-worlds-first-open-source-8k-text-embedding-rivaling-openai/) introduces these models. 13 | 14 | See also [Embeddings: What they are and why they matter](https://simonwillison.net/2023/Oct/23/embeddings/) for background on embeddings and an explanation of the LLM embeddings tool. 15 | 16 | Here's [my blog post about how I built this plugin](https://simonwillison.net/2023/Oct/26/llm-embed-jina/). 17 | 18 | ## Installation 19 | 20 | Install this plugin in the same environment as [LLM](https://llm.datasette.io/). 21 | 22 | llm install llm-embed-jina 23 | 24 | ## Usage 25 | 26 | This plugin adds support for three new embedding models: 27 | 28 | - [`jina-embeddings-v2-small-en`](https://huggingface.co/jinaai/jina-embeddings-v2-small-en): 33 million parameters. 29 | - [`jina-embeddings-v2-base-en`](https://huggingface.co/jinaai/jina-embeddings-v2-base-en): 137 million parameters. 30 | - [`jina-embeddings-v2-large-en`](https://huggingface.co/jinaai/jina-embeddings-v2-large-en): 435 million parameters - not yet released, but it will work once it has been released. 31 | 32 | The models will be downloaded the first time you try to use them. 33 | 34 | See [the LLM documentation](https://llm.datasette.io/en/stable/embeddings/index.html) for everything you can do. 35 | 36 | To get started embedding a single string, run the following: 37 | 38 | ```bash 39 | llm embed -m jina-embeddings-v2-small-en -c 'Hello world' 40 | ``` 41 | This will output a JSON array of 512 floating point numbers to your terminal. 42 | 43 | To calculate and store embeddings for every README in the current directory (try this somewhere with a `node_modules` directory to get lots of READMEs) run this: 44 | 45 | ```bash 46 | llm embed-multi jina-readmes \ 47 | -m jina-embeddings-v2-small-en \ 48 | --files . '**/README.md' --store 49 | ``` 50 | Then you can run searches against them like this: 51 | ```bash 52 | llm similar jina-readmes -c 'utility functions' 53 | ``` 54 | Add `| jq` to pipe it through [jq](https://jqlang.github.io/jq/) for pretty-printed output, or ` | jq .id` to just see the matching filenames. 55 | 56 | ## Development 57 | 58 | To set up this plugin locally, first checkout the code. Then create a new virtual environment: 59 | ```bash 60 | cd llm-embed-jina 61 | python3 -m venv venv 62 | source venv/bin/activate 63 | ``` 64 | Now install the dependencies and test dependencies: 65 | ```bash 66 | llm install -e '.[test]' 67 | ``` 68 | To run the tests: 69 | ```bash 70 | pytest 71 | ``` 72 | -------------------------------------------------------------------------------- /llm_embed_jina.py: -------------------------------------------------------------------------------- 1 | import llm 2 | from transformers import AutoModel 3 | 4 | MAX_LENGTH = 8192 5 | 6 | 7 | @llm.hookimpl 8 | def register_embedding_models(register): 9 | for model_id in ( 10 | "jina-embeddings-v2-small-en", 11 | "jina-embeddings-v2-base-en", 12 | "jina-embeddings-v2-large-en", 13 | ): 14 | register(JinaEmbeddingModel(model_id)) 15 | 16 | 17 | class JinaEmbeddingModel(llm.EmbeddingModel): 18 | def __init__(self, model_id): 19 | self.model_id = model_id 20 | self._model = None 21 | 22 | def embed_batch(self, texts): 23 | if self._model is None: 24 | self._model = AutoModel.from_pretrained( 25 | "jinaai/{}".format(self.model_id), trust_remote_code=True 26 | ) 27 | results = self._model.encode([text[:MAX_LENGTH] for text in texts]) 28 | return (list(map(float, result)) for result in results) 29 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [project] 2 | name = "llm-embed-jina" 3 | version = "0.1.2" 4 | description = "Embedding models from Jina AI" 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", 13 | "transformers", 14 | "torch", 15 | ] 16 | 17 | [project.urls] 18 | Homepage = "https://github.com/simonw/llm-embed-jina" 19 | Changelog = "https://github.com/simonw/llm-embed-jina/releases" 20 | Issues = "https://github.com/simonw/llm-embed-jina/issues" 21 | CI = "https://github.com/simonw/llm-embed-jina/actions" 22 | 23 | [project.entry-points.llm] 24 | embed_jina = "llm_embed_jina" 25 | 26 | [project.optional-dependencies] 27 | test = ["pytest"] 28 | -------------------------------------------------------------------------------- /tests/test_embed_jina.py: -------------------------------------------------------------------------------- 1 | from click.testing import CliRunner 2 | from llm.cli import cli 3 | import llm 4 | 5 | 6 | def test_jina_embed_small(): 7 | model = llm.get_embedding_model("jina-embeddings-v2-small-en") 8 | floats = model.embed("hello world") 9 | assert len(floats) == 512 10 | assert all(isinstance(f, float) for f in floats) 11 | 12 | 13 | def test_jina_embed_long_string(): 14 | model = llm.get_embedding_model("jina-embeddings-v2-small-en") 15 | outputs = list(model.embed_multi(["a" * 9000, "two"])) 16 | for floats in outputs: 17 | assert len(floats) == 512 18 | 19 | 20 | def test_jina_embed_multi(tmpdir): 21 | db_path = str(tmpdir / "test.db") 22 | runner = CliRunner() 23 | result = runner.invoke( 24 | cli, 25 | [ 26 | "embed-multi", 27 | "-m", 28 | "jina-embeddings-v2-small-en", 29 | "test", 30 | "-", 31 | "-d", 32 | db_path, 33 | ], 34 | input='[{"id": "a", "text": "abc"}]', 35 | catch_exceptions=False, 36 | ) 37 | assert result.exit_code == 0 38 | --------------------------------------------------------------------------------