| Name | llm-clip JSON |
| Version |
0.1
JSON |
| download |
| home_page | |
| Summary | Generate embeddings for images and text using CLIP with LLM |
| upload_time | 2023-09-12 19:32:16 |
| maintainer | |
| docs_url | None |
| author | Simon Willison |
| requires_python | |
| license | Apache-2.0 |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# llm-clip
[](https://pypi.org/project/llm-clip/)
[](https://github.com/simonw/llm-clip/releases)
[](https://github.com/simonw/llm-clip/actions?query=workflow%3ATest)
[](https://github.com/simonw/llm-clip/blob/main/LICENSE)
[LLM](https://llm.datasette.io/) plugin for embedding images and text using [CLIP](https://openai.com/research/clip)
## Installation
Install this plugin in the same environment as LLM.
```bash
llm install llm-clip
```
## Usage
Once you have installed an embedding model you can use it to embed text like this:
```bash
llm embed -m clip -c 'Hello world'
```
Or an image like this:
```bash
llm embed -m clip --binary -i IMG_4801.jpeg
```
Embeddings are more useful if you store them in a database - see [the LLM documentation](https://llm.datasette.io/en/stable/embeddings/cli.html#storing-embeddings-in-sqlite) for details.
To embed every photograph in a folder and save them in a collection called "photos":
```bash
llm embed-multi photos -m clip --binary --files photos/ '*.jpg'
```
You can then search for photos of specific things like this:
```bash
llm similar photos -c 'bunny'
```
## Development
To set up this plugin locally, first checkout the code. Then create a new virtual environment:
```bash
cd llm-clip
python3 -m venv venv
source venv/bin/activate
```
Now install the dependencies and test dependencies:
```bash
pip install -e '.[test]'
```
To run the tests:
```bash
pytest
```
Raw data
{
"_id": null,
"home_page": "",
"name": "llm-clip",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "",
"author": "Simon Willison",
"author_email": "",
"download_url": "https://files.pythonhosted.org/packages/7b/ef/f16404d79cff379f3098ce95cbe205929a01dfa6b5946331fdfe7b0e4f53/llm-clip-0.1.tar.gz",
"platform": null,
"description": "# llm-clip\n\n[](https://pypi.org/project/llm-clip/)\n[](https://github.com/simonw/llm-clip/releases)\n[](https://github.com/simonw/llm-clip/actions?query=workflow%3ATest)\n[](https://github.com/simonw/llm-clip/blob/main/LICENSE)\n\n[LLM](https://llm.datasette.io/) plugin for embedding images and text using [CLIP](https://openai.com/research/clip)\n\n## Installation\n\nInstall this plugin in the same environment as LLM.\n```bash\nllm install llm-clip\n```\n\n## Usage\n\nOnce you have installed an embedding model you can use it to embed text like this:\n\n```bash\nllm embed -m clip -c 'Hello world'\n```\nOr an image like this:\n```bash\nllm embed -m clip --binary -i IMG_4801.jpeg\n```\n\nEmbeddings are more useful if you store them in a database - see [the LLM documentation](https://llm.datasette.io/en/stable/embeddings/cli.html#storing-embeddings-in-sqlite) for details.\n\nTo embed every photograph in a folder and save them in a collection called \"photos\":\n\n```bash\nllm embed-multi photos -m clip --binary --files photos/ '*.jpg'\n```\nYou can then search for photos of specific things like this:\n```bash\nllm similar photos -c 'bunny'\n```\n\n## Development\n\nTo set up this plugin locally, first checkout the code. Then create a new virtual environment:\n```bash\ncd llm-clip\npython3 -m venv venv\nsource venv/bin/activate\n```\nNow install the dependencies and test dependencies:\n```bash\npip install -e '.[test]'\n```\nTo run the tests:\n```bash\npytest\n```\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Generate embeddings for images and text using CLIP with LLM",
"version": "0.1",
"project_urls": {
"CI": "https://github.com/simonw/llm-clip/actions",
"Changelog": "https://github.com/simonw/llm-clip/releases",
"Homepage": "https://github.com/simonw/llm-clip",
"Issues": "https://github.com/simonw/llm-clip/issues"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "05512a9b1b753c8f127275ccbbc8ae3cc3bfd6af9882566542273583ad885369",
"md5": "1f4ccc53fcf89b56982dd3d022a99618",
"sha256": "31bca3c6dd3e4df192a805ff7d44eb788ccf6d4f1cb8b078f28adc8a2d547e1d"
},
"downloads": -1,
"filename": "llm_clip-0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "1f4ccc53fcf89b56982dd3d022a99618",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 6881,
"upload_time": "2023-09-12T19:32:14",
"upload_time_iso_8601": "2023-09-12T19:32:14.857283Z",
"url": "https://files.pythonhosted.org/packages/05/51/2a9b1b753c8f127275ccbbc8ae3cc3bfd6af9882566542273583ad885369/llm_clip-0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "7beff16404d79cff379f3098ce95cbe205929a01dfa6b5946331fdfe7b0e4f53",
"md5": "08fe3eba9fb2742adae33640264f0277",
"sha256": "fcd7efe71a55170b530c30dbf4088d8af80c72562dc85dbd6ec48324525dbb7e"
},
"downloads": -1,
"filename": "llm-clip-0.1.tar.gz",
"has_sig": false,
"md5_digest": "08fe3eba9fb2742adae33640264f0277",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 6608,
"upload_time": "2023-09-12T19:32:16",
"upload_time_iso_8601": "2023-09-12T19:32:16.339954Z",
"url": "https://files.pythonhosted.org/packages/7b/ef/f16404d79cff379f3098ce95cbe205929a01dfa6b5946331fdfe7b0e4f53/llm-clip-0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-09-12 19:32:16",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "simonw",
"github_project": "llm-clip",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "llm-clip"
}
