| Name | llm-embed-onnx JSON |
| Version |
0.1
JSON |
| download |
| home_page | |
| Summary | Run embedding models using ONNX |
| upload_time | 2024-01-28 22:22:47 |
| maintainer | |
| docs_url | None |
| author | Simon Willison |
| requires_python | >=3.9 |
| license | Apache-2.0 |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# llm-embed-onnx
[](https://pypi.org/project/llm-embed-onnx/)
[](https://github.com/simonw/llm-embed-onnx/releases)
[](https://github.com/simonw/llm-embed-onnx/actions/workflows/test.yml)
[](https://github.com/simonw/llm-embed-onnx/blob/main/LICENSE)
Run embedding models using ONNX
This LLM plugin is a wrapper around [onnx_embedding_models](https://github.com/taylorai/onnx_embedding_models) by Benjamin Anderson.
## Installation
Install this plugin in the same environment as [LLM](https://llm.datasette.io/).
```bash
llm install llm-embed-onnx
```
## Usage
This plugin adds the following embedding models, which can be listed using `llm embed-models`:
```
onnx-bge-micro
onnx-gte-tiny
onnx-minilm-l6
onnx-minilm-l12
onnx-bge-small
onnx-bge-base
onnx-bge-large
```
You can run any of these models using `llm embed` command:
```bash
llm embed -m onnx-bge-micro -c "Example content"
```
This will output a 384 length JSON array of floating point numbers, starting:
```
[-0.03910085942622519, -0.0030843335461659795, 0.032797761260860724,
```
The first time you use any of these models the model will be downloaded to the `llm_embed_onnx` directory in your [LLM data directory](https://llm.datasette.io/en/stable/setup.html#setting-a-custom-directory-location). On macOS this defaults to:
`~/Library/Application Support/io.datasette.llm/llm_embed_onnx`
For more on how to use these embedding models see [the LLM embeddings documentation](https://llm.datasette.io/en/stable/embeddings/index.html).
## Development
To set up this plugin locally, first checkout the code. Then create a new virtual environment:
```bash
cd llm-embed-onnx
python3 -m venv venv
source venv/bin/activate
```
Now install the dependencies and test dependencies:
```bash
llm install -e '.[test]'
```
To run the tests:
```bash
pytest
```
Raw data
{
"_id": null,
"home_page": "",
"name": "llm-embed-onnx",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": "",
"keywords": "",
"author": "Simon Willison",
"author_email": "",
"download_url": "https://files.pythonhosted.org/packages/3d/34/1d5c0f5ed5c34a0ee04468d3e149c827280e97c08013fe48669b5e3ed100/llm-embed-onnx-0.1.tar.gz",
"platform": null,
"description": "# llm-embed-onnx\n\n[](https://pypi.org/project/llm-embed-onnx/)\n[](https://github.com/simonw/llm-embed-onnx/releases)\n[](https://github.com/simonw/llm-embed-onnx/actions/workflows/test.yml)\n[](https://github.com/simonw/llm-embed-onnx/blob/main/LICENSE)\n\nRun embedding models using ONNX\n\nThis LLM plugin is a wrapper around [onnx_embedding_models](https://github.com/taylorai/onnx_embedding_models) by Benjamin Anderson.\n\n## Installation\n\nInstall this plugin in the same environment as [LLM](https://llm.datasette.io/).\n```bash\nllm install llm-embed-onnx\n```\n## Usage\n\nThis plugin adds the following embedding models, which can be listed using `llm embed-models`:\n\n```\nonnx-bge-micro\nonnx-gte-tiny\nonnx-minilm-l6\nonnx-minilm-l12\nonnx-bge-small\nonnx-bge-base\nonnx-bge-large\n```\n\nYou can run any of these models using `llm embed` command:\n\n```bash\nllm embed -m onnx-bge-micro -c \"Example content\"\n```\nThis will output a 384 length JSON array of floating point numbers, starting:\n```\n[-0.03910085942622519, -0.0030843335461659795, 0.032797761260860724,\n```\nThe first time you use any of these models the model will be downloaded to the `llm_embed_onnx` directory in your [LLM data directory](https://llm.datasette.io/en/stable/setup.html#setting-a-custom-directory-location). On macOS this defaults to:\n\n`~/Library/Application Support/io.datasette.llm/llm_embed_onnx`\n\nFor more on how to use these embedding models see [the LLM embeddings documentation](https://llm.datasette.io/en/stable/embeddings/index.html).\n\n## Development\n\nTo set up this plugin locally, first checkout the code. Then create a new virtual environment:\n```bash\ncd llm-embed-onnx\npython3 -m venv venv\nsource venv/bin/activate\n```\nNow install the dependencies and test dependencies:\n```bash\nllm install -e '.[test]'\n```\nTo run the tests:\n```bash\npytest\n```\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Run embedding models using ONNX",
"version": "0.1",
"project_urls": {
"CI": "https://github.com/simonw/llm-embed-onnx/actions",
"Changelog": "https://github.com/simonw/llm-embed-onnx/releases",
"Homepage": "https://github.com/simonw/llm-embed-onnx",
"Issues": "https://github.com/simonw/llm-embed-onnx/issues"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "4346f2c5df1d94e783874aa5db1bfbb80e88893dde198377a4fe501999baeec5",
"md5": "8ff993d7018c5df9fd481384f9397ec7",
"sha256": "946a9694f046f09965e12d481220dc8a146b0f6bbabe5f37457ebe2b2d4431f0"
},
"downloads": -1,
"filename": "llm_embed_onnx-0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8ff993d7018c5df9fd481384f9397ec7",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 7382,
"upload_time": "2024-01-28T22:22:46",
"upload_time_iso_8601": "2024-01-28T22:22:46.954191Z",
"url": "https://files.pythonhosted.org/packages/43/46/f2c5df1d94e783874aa5db1bfbb80e88893dde198377a4fe501999baeec5/llm_embed_onnx-0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "3d341d5c0f5ed5c34a0ee04468d3e149c827280e97c08013fe48669b5e3ed100",
"md5": "4f5d51616f16ddaf3971e4dc24c0243c",
"sha256": "6b0a5ed0876193aad023a63a72a976daf4fb9250471d573c222a46c94cab819c"
},
"downloads": -1,
"filename": "llm-embed-onnx-0.1.tar.gz",
"has_sig": false,
"md5_digest": "4f5d51616f16ddaf3971e4dc24c0243c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 7122,
"upload_time": "2024-01-28T22:22:47",
"upload_time_iso_8601": "2024-01-28T22:22:47.857152Z",
"url": "https://files.pythonhosted.org/packages/3d/34/1d5c0f5ed5c34a0ee04468d3e149c827280e97c08013fe48669b5e3ed100/llm-embed-onnx-0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-01-28 22:22:47",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "simonw",
"github_project": "llm-embed-onnx",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "llm-embed-onnx"
}
