| Name | llm-anyscale-endpoints JSON |
| Version |
0.6
JSON |
| download |
| home_page | None |
| Summary | LLM plugin for models hosted by Anyscale Endpoints |
| upload_time | 2024-04-21 23:36:08 |
| 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-anyscale-endpoints
[](https://pypi.org/project/llm-anyscale-endpoints/)
[](https://github.com/simonw/llm-anyscale-endpoints/releases)
[](https://github.com/simonw/llm-anyscale-endpoints/actions?query=workflow%3ATest)
[](https://github.com/simonw/llm-anyscale-endpoints/blob/main/LICENSE)
[LLM](https://llm.datasette.io/) plugin for models hosted by [Anyscale Endpoints](https://app.endpoints.anyscale.com/)
## Installation
First, [install the LLM command-line utility](https://llm.datasette.io/en/stable/setup.html).
Now install this plugin in the same environment as LLM.
```bash
llm install llm-anyscale-endpoints
```
## Configuration
You will need an API key from Anyscale Endpoints. You can [obtain one here](https://app.endpoints.anyscale.com/).
You can set that as an environment variable called `LLM_ANYSCALE_ENDPOINTS_KEY`, or add it to the `llm` set of saved keys using:
```bash
llm keys set anyscale-endpoints
```
```
Enter key: <paste key here>
```
## Usage
To list available models, run:
```bash
llm models list
```
You should see a list that looks something like this:
```
AnyscaleEndpoints: meta-llama/Llama-2-7b-chat-hf
AnyscaleEndpoints: meta-llama/Llama-2-13b-chat-hf
AnyscaleEndpoints: mistralai/Mixtral-8x7B-Instruct-v0.1
AnyscaleEndpoints: mistralai/Mistral-7B-Instruct-v0.1
AnyscaleEndpoints: meta-llama/Llama-2-70b-chat-hf
AnyscaleEndpoints: codellama/CodeLlama-70b-Instruct-hf
AnyscaleEndpoints: mistralai/Mixtral-8x22B-Instruct-v0.1
AnyscaleEndpoints: mlabonne/NeuralHermes-2.5-Mistral-7B
AnyscaleEndpoints: google/gemma-7b-it
```
To run a prompt against a model, pass its full model ID to the `-m` option, like this:
```bash
llm -m mistralai/Mixtral-8x22B-Instruct-v0.1 \
'Five strident names for a pet walrus' \
--system 'You love coming up with creative names for pets'
```
You can set a shorter alias for a model using the `llm aliases` command like so:
```bash
llm aliases set mix22b mistralai/Mixtral-8x22B-Instruct-v0.1
```
Now you can prompt Mixtral-8x22B-Instruct-v0.1 using the alias `mix22b`:
```bash
cat llm_anyscale_endpoints.py | \
llm -m mix22b -s 'explain this code'
```
You can refresh the list of models by running:
```bash
llm anyscale-endpoints refresh
```
This will fetch the latest list of models from Anyscale Endpoints and story it in a local cache file.
## Development
To set up this plugin locally, first checkout the code. Then create a new virtual environment:
```bash
cd llm-anyscale-endpoints
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": null,
"name": "llm-anyscale-endpoints",
"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/9d/33/48b9458838b148674f2abb4d847ea917939e8c9abe162ff2216f2513f893/llm_anyscale_endpoints-0.6.tar.gz",
"platform": null,
"description": "# llm-anyscale-endpoints\n\n[](https://pypi.org/project/llm-anyscale-endpoints/)\n[](https://github.com/simonw/llm-anyscale-endpoints/releases)\n[](https://github.com/simonw/llm-anyscale-endpoints/actions?query=workflow%3ATest)\n[](https://github.com/simonw/llm-anyscale-endpoints/blob/main/LICENSE)\n\n[LLM](https://llm.datasette.io/) plugin for models hosted by [Anyscale Endpoints](https://app.endpoints.anyscale.com/)\n\n## Installation\n\nFirst, [install the LLM command-line utility](https://llm.datasette.io/en/stable/setup.html).\n\nNow install this plugin in the same environment as LLM.\n```bash\nllm install llm-anyscale-endpoints\n```\n## Configuration\n\nYou will need an API key from Anyscale Endpoints. You can [obtain one here](https://app.endpoints.anyscale.com/).\n\nYou can set that as an environment variable called `LLM_ANYSCALE_ENDPOINTS_KEY`, or add it to the `llm` set of saved keys using:\n\n```bash\nllm keys set anyscale-endpoints\n```\n```\nEnter key: <paste key here>\n```\n\n## Usage\n\nTo list available models, run:\n```bash\nllm models list\n```\nYou should see a list that looks something like this:\n```\nAnyscaleEndpoints: meta-llama/Llama-2-7b-chat-hf\nAnyscaleEndpoints: meta-llama/Llama-2-13b-chat-hf\nAnyscaleEndpoints: mistralai/Mixtral-8x7B-Instruct-v0.1\nAnyscaleEndpoints: mistralai/Mistral-7B-Instruct-v0.1\nAnyscaleEndpoints: meta-llama/Llama-2-70b-chat-hf\nAnyscaleEndpoints: codellama/CodeLlama-70b-Instruct-hf\nAnyscaleEndpoints: mistralai/Mixtral-8x22B-Instruct-v0.1\nAnyscaleEndpoints: mlabonne/NeuralHermes-2.5-Mistral-7B\nAnyscaleEndpoints: google/gemma-7b-it\n```\nTo run a prompt against a model, pass its full model ID to the `-m` option, like this:\n```bash\nllm -m mistralai/Mixtral-8x22B-Instruct-v0.1 \\\n 'Five strident names for a pet walrus' \\\n --system 'You love coming up with creative names for pets'\n```\nYou can set a shorter alias for a model using the `llm aliases` command like so:\n```bash\nllm aliases set mix22b mistralai/Mixtral-8x22B-Instruct-v0.1\n```\nNow you can prompt Mixtral-8x22B-Instruct-v0.1 using the alias `mix22b`:\n```bash\ncat llm_anyscale_endpoints.py | \\\n llm -m mix22b -s 'explain this code'\n```\n\nYou can refresh the list of models by running:\n```bash\nllm anyscale-endpoints refresh\n```\nThis will fetch the latest list of models from Anyscale Endpoints and story it in a local cache file.\n\n## Development\n\nTo set up this plugin locally, first checkout the code. Then create a new virtual environment:\n```bash\ncd llm-anyscale-endpoints\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": "LLM plugin for models hosted by Anyscale Endpoints",
"version": "0.6",
"project_urls": {
"CI": "https://github.com/simonw/llm-anyscale-endpoints/actions",
"Changelog": "https://github.com/simonw/llm-anyscale-endpoints/releases",
"Homepage": "https://github.com/simonw/llm-anyscale-endpoints",
"Issues": "https://github.com/simonw/llm-anyscale-endpoints/issues"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "191c64aea5735fca6630d9c8b2e6181996e87a49329babc1c75cc015fd0f812b",
"md5": "a4a2e6062e4f4faeecf2d7a4dbde1d88",
"sha256": "12bb01ccd13d98153c584b57a5ac765b0f15996d236811ae4ee612e512a685b8"
},
"downloads": -1,
"filename": "llm_anyscale_endpoints-0.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a4a2e6062e4f4faeecf2d7a4dbde1d88",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 8058,
"upload_time": "2024-04-21T23:36:07",
"upload_time_iso_8601": "2024-04-21T23:36:07.441901Z",
"url": "https://files.pythonhosted.org/packages/19/1c/64aea5735fca6630d9c8b2e6181996e87a49329babc1c75cc015fd0f812b/llm_anyscale_endpoints-0.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "9d3348b9458838b148674f2abb4d847ea917939e8c9abe162ff2216f2513f893",
"md5": "4a548921405f366fa4d94b0558c21e33",
"sha256": "11c0c1ed42a6c16a25a92f4f756f122c39083af397f167e11b63151d060e1aa7"
},
"downloads": -1,
"filename": "llm_anyscale_endpoints-0.6.tar.gz",
"has_sig": false,
"md5_digest": "4a548921405f366fa4d94b0558c21e33",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 7739,
"upload_time": "2024-04-21T23:36:08",
"upload_time_iso_8601": "2024-04-21T23:36:08.556617Z",
"url": "https://files.pythonhosted.org/packages/9d/33/48b9458838b148674f2abb4d847ea917939e8c9abe162ff2216f2513f893/llm_anyscale_endpoints-0.6.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-21 23:36:08",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "simonw",
"github_project": "llm-anyscale-endpoints",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "llm-anyscale-endpoints"
}
