| Name | llm-nomic-api-embed JSON |
| Version |
0.3
JSON |
| download |
| home_page | None |
| Summary | Create embeddings using the Nomic API |
| upload_time | 2024-11-21 23:06:52 |
| maintainer | None |
| docs_url | None |
| author | Simon Willison |
| requires_python | None |
| license | Apache-2.0 |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# llm-nomic-api-embed
[](https://pypi.org/project/llm-nomic-api-embed/)
[](https://github.com/simonw/llm-nomic-api-embed/releases)
[](https://github.com/simonw/llm-nomic-api-embed/actions/workflows/test.yml)
[](https://github.com/simonw/llm-nomic-api-embed/blob/main/LICENSE)
Create embeddings using the Nomic API
## Installation
Install this plugin in the same environment as [LLM](https://llm.datasette.io/).
```bash
llm install llm-nomic-api-embed
```
## Usage
This plugin requires [a Nomic API key](https://atlas.nomic.ai/). These include a generous free allowance for their embedding API.
Configure the key like this:
```bash
llm keys set nomic
# Paste key here
```
You can then use the Nomic embedding models like this:
```bash
llm embed -m nomic-1.5 -c 'hello world'
```
This will return a 768 item floating point array as JSON.
See [the LLM embeddings documentation](https://llm.datasette.io/en/stable/embeddings/index.html) for more you can do with the tool.
## Models
Run `llm embed-models` for a full list. The Nomic models are:
```
nomic-embed-text-v1 (aliases: nomic-1)
nomic-embed-text-v1.5 (aliases: nomic-1.5)
nomic-embed-text-v1.5-512 (aliases: nomic-1.5-512)
nomic-embed-text-v1.5-256 (aliases: nomic-1.5-256)
nomic-embed-text-v1.5-128 (aliases: nomic-1.5-128)
nomic-embed-text-v1.5-64 (aliases: nomic-1.5-64)
nomic-embed-vision-v1
nomic-embed-vision-v1.5
nomic-embed-combined-v1
nomic-embed-combined-v1.5
```
Vision models can be used with image files using the `--binary` option, for example:
```bash
llm embed-multi images --files . '*.png' \
--binary --model nomic-embed-vision-v1.5
```
### Combined vision and text models
The `nomic-embed-combined-v1` and `nomic-embed-combined-v1.5` models are special - they will automatically use their respective text models for text inputs and their respective vision models for images.
This means you can use them to create a collection that mixes images and text, or you can create an image collection with them and then use text to find similar images.
Here's how do do that for a `photos/` directory full of JPEGs:
```bash
llm embed-multi --binary -m nomic-embed-combined-v1.5 \
-d photos.db photos --files photos/ '*.jpeg'
```
Then run similarity searches like this:
```bash
llm similar photos -d photos.db -c pelican
```
## Development
To set up this plugin locally, first checkout the code. Then create a new virtual environment:
```bash
cd llm-nomic-api-embed
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": null,
"name": "llm-nomic-api-embed",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": null,
"author": "Simon Willison",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/73/aa/a39f0dde114ad184c841ddfee26a2ab387b4cae162a5bc46a67ae1080391/llm_nomic_api_embed-0.3.tar.gz",
"platform": null,
"description": "# llm-nomic-api-embed\n\n[](https://pypi.org/project/llm-nomic-api-embed/)\n[](https://github.com/simonw/llm-nomic-api-embed/releases)\n[](https://github.com/simonw/llm-nomic-api-embed/actions/workflows/test.yml)\n[](https://github.com/simonw/llm-nomic-api-embed/blob/main/LICENSE)\n\nCreate embeddings using the Nomic API\n\n## Installation\n\nInstall this plugin in the same environment as [LLM](https://llm.datasette.io/).\n```bash\nllm install llm-nomic-api-embed\n```\n## Usage\n\nThis plugin requires [a Nomic API key](https://atlas.nomic.ai/). These include a generous free allowance for their embedding API.\n\nConfigure the key like this:\n```bash\nllm keys set nomic\n# Paste key here\n```\nYou can then use the Nomic embedding models like this:\n```bash\nllm embed -m nomic-1.5 -c 'hello world'\n```\nThis will return a 768 item floating point array as JSON.\n\nSee [the LLM embeddings documentation](https://llm.datasette.io/en/stable/embeddings/index.html) for more you can do with the tool.\n\n## Models\n\nRun `llm embed-models` for a full list. The Nomic models are:\n\n```\nnomic-embed-text-v1 (aliases: nomic-1)\nnomic-embed-text-v1.5 (aliases: nomic-1.5)\nnomic-embed-text-v1.5-512 (aliases: nomic-1.5-512)\nnomic-embed-text-v1.5-256 (aliases: nomic-1.5-256)\nnomic-embed-text-v1.5-128 (aliases: nomic-1.5-128)\nnomic-embed-text-v1.5-64 (aliases: nomic-1.5-64)\nnomic-embed-vision-v1\nnomic-embed-vision-v1.5\nnomic-embed-combined-v1\nnomic-embed-combined-v1.5\n```\nVision models can be used with image files using the `--binary` option, for example:\n\n```bash\nllm embed-multi images --files . '*.png' \\\n --binary --model nomic-embed-vision-v1.5\n```\n\n### Combined vision and text models\n\nThe `nomic-embed-combined-v1` and `nomic-embed-combined-v1.5` models are special - they will automatically use their respective text models for text inputs and their respective vision models for images.\n\nThis means you can use them to create a collection that mixes images and text, or you can create an image collection with them and then use text to find similar images.\n\nHere's how do do that for a `photos/` directory full of JPEGs:\n\n```bash\nllm embed-multi --binary -m nomic-embed-combined-v1.5 \\\n -d photos.db photos --files photos/ '*.jpeg'\n```\nThen run similarity searches like this:\n```bash\nllm similar photos -d photos.db -c pelican\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-nomic-api-embed\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": "Create embeddings using the Nomic API",
"version": "0.3",
"project_urls": {
"CI": "https://github.com/simonw/llm-nomic-api-embed/actions",
"Changelog": "https://github.com/simonw/llm-nomic-api-embed/releases",
"Homepage": "https://github.com/simonw/llm-nomic-api-embed",
"Issues": "https://github.com/simonw/llm-nomic-api-embed/issues"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "2af6309ac014bc8812956d5275941a73a29d33ed4fb2385183bd954a1dcacbe9",
"md5": "82844411a3cb0472e0915183a025acbf",
"sha256": "c7046739761cfb4058e3fcc19acf56612ff71631dde5cd774377ba298495a05f"
},
"downloads": -1,
"filename": "llm_nomic_api_embed-0.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "82844411a3cb0472e0915183a025acbf",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 8057,
"upload_time": "2024-11-21T23:06:51",
"upload_time_iso_8601": "2024-11-21T23:06:51.118641Z",
"url": "https://files.pythonhosted.org/packages/2a/f6/309ac014bc8812956d5275941a73a29d33ed4fb2385183bd954a1dcacbe9/llm_nomic_api_embed-0.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "73aaa39f0dde114ad184c841ddfee26a2ab387b4cae162a5bc46a67ae1080391",
"md5": "c5ad1986fb24a589265d28084c212634",
"sha256": "96729b3fbcfbc925b62208d55d38ca7850063cb96a81911ee0a73b21aff8699b"
},
"downloads": -1,
"filename": "llm_nomic_api_embed-0.3.tar.gz",
"has_sig": false,
"md5_digest": "c5ad1986fb24a589265d28084c212634",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 8257,
"upload_time": "2024-11-21T23:06:52",
"upload_time_iso_8601": "2024-11-21T23:06:52.160082Z",
"url": "https://files.pythonhosted.org/packages/73/aa/a39f0dde114ad184c841ddfee26a2ab387b4cae162a5bc46a67ae1080391/llm_nomic_api_embed-0.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-21 23:06:52",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "simonw",
"github_project": "llm-nomic-api-embed",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "llm-nomic-api-embed"
}
