| Name | llm-bedrock JSON |
| Version |
0.4
JSON |
| download |
| home_page | None |
| Summary | Run prompts against models hosted on AWS Bedrock |
| upload_time | 2024-12-04 15:40:10 |
| maintainer | None |
| 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-bedrock
[](https://pypi.org/project/llm-bedrock/)
[](https://github.com/simonw/llm-bedrock/releases)
[](https://github.com/simonw/llm-bedrock/actions/workflows/test.yml)
[](https://github.com/simonw/llm-bedrock/blob/main/LICENSE)
Run prompts against models hosted on AWS Bedrock
## Installation
Install this plugin in the same environment as [LLM](https://llm.datasette.io/).
```bash
llm install llm-bedrock
```
### Credentials
You'll need an access key and a secret key to use this plugin, with permission granted to access the Bedrock Nova models.
If you have already configured the AWS CLI on your machine you may be able to skip this step, as the plugin will automatically use the credentials from the CLI.
You still need to request access to the Bedrock models [in the AWS console](https://us-west-2.console.aws.amazon.com/bedrock/home?region=us-west-2#/), which should be provisioned automatically within seconds of you filing the request.
If you want to use the plugin with dedicated IAM credentials (an access key and a secret key) follow these [step by step instructions](https://ndurner.github.io/amazon-nova) by Nils Durner.
Combine those into a `access_key:secret_key` format (joined by a colon) and paste that into:
```bash
llm keys set bedrock
# paste access_key:secret_key here
```
## Usage
Run `llm models` to see the list of models. The [Amazon Nova](https://aws.amazon.com/blogs/aws/introducing-amazon-nova-frontier-intelligence-and-industry-leading-price-performance/) models are:
- `us.amazon.nova-micro-v1:0` (alias: `nova-micro`) - cheapest and fastest, text only
- `us.amazon.nova-lite-v1:0` (alias: `nova-lite`) - can handle text, images and PDFs
- `us.amazon.nova-pro-v1:0` (alias: `nova-pro`) - can handle text, images and PDFs, best and most expensive
Run a prompt like this:
```bash
llm -m nova-pro 'a happy poem about a pelican with a secret'
```
Images and videos and PDFs can be provided using the `-a` option, which takes a file path or a URL:
```bash
llm -m nova-lite 'describe this image' -a https://static.simonwillison.net/static/2024/pelicans.jpg
```
## Development
To set up this plugin locally, first checkout the code. Then create a new virtual environment:
```bash
cd llm-bedrock
python -m venv venv
source venv/bin/activate
```
Now install the dependencies and test dependencies:
```bash
llm install -e '.[test]'
```
To run the tests:
```bash
python -m pytest
```
To regenerate the captured HTTP responses:
```bash
PYTEST_BEDROCK_API_KEY="$(llm keys get bedrock)" python -m pytest --record-mode all
```
Raw data
{
"_id": null,
"home_page": null,
"name": "llm-bedrock",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": null,
"author": "Simon Willison",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/c8/21/d184dd8e094fff1490067b97dac1b9b0e87ec83ccb677086fa0ae696acbd/llm_bedrock-0.4.tar.gz",
"platform": null,
"description": "# llm-bedrock\n\n[](https://pypi.org/project/llm-bedrock/)\n[](https://github.com/simonw/llm-bedrock/releases)\n[](https://github.com/simonw/llm-bedrock/actions/workflows/test.yml)\n[](https://github.com/simonw/llm-bedrock/blob/main/LICENSE)\n\nRun prompts against models hosted on AWS Bedrock\n\n## Installation\n\nInstall this plugin in the same environment as [LLM](https://llm.datasette.io/).\n```bash\nllm install llm-bedrock\n```\n\n### Credentials\n\nYou'll need an access key and a secret key to use this plugin, with permission granted to access the Bedrock Nova models.\n\nIf you have already configured the AWS CLI on your machine you may be able to skip this step, as the plugin will automatically use the credentials from the CLI.\n\nYou still need to request access to the Bedrock models [in the AWS console](https://us-west-2.console.aws.amazon.com/bedrock/home?region=us-west-2#/), which should be provisioned automatically within seconds of you filing the request.\n\nIf you want to use the plugin with dedicated IAM credentials (an access key and a secret key) follow these [step by step instructions](https://ndurner.github.io/amazon-nova) by Nils Durner.\n\nCombine those into a `access_key:secret_key` format (joined by a colon) and paste that into:\n\n```bash\nllm keys set bedrock\n# paste access_key:secret_key here\n```\n\n## Usage\n\nRun `llm models` to see the list of models. The [Amazon Nova](https://aws.amazon.com/blogs/aws/introducing-amazon-nova-frontier-intelligence-and-industry-leading-price-performance/) models are:\n\n- `us.amazon.nova-micro-v1:0` (alias: `nova-micro`) - cheapest and fastest, text only\n- `us.amazon.nova-lite-v1:0` (alias: `nova-lite`) - can handle text, images and PDFs\n- `us.amazon.nova-pro-v1:0` (alias: `nova-pro`) - can handle text, images and PDFs, best and most expensive\n\nRun a prompt like this:\n\n```bash\nllm -m nova-pro 'a happy poem about a pelican with a secret'\n```\nImages and videos and PDFs can be provided using the `-a` option, which takes a file path or a URL:\n\n```bash\nllm -m nova-lite 'describe this image' -a https://static.simonwillison.net/static/2024/pelicans.jpg\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-bedrock\npython -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\npython -m pytest\n```\nTo regenerate the captured HTTP responses:\n```bash\nPYTEST_BEDROCK_API_KEY=\"$(llm keys get bedrock)\" python -m pytest --record-mode all\n```\n\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Run prompts against models hosted on AWS Bedrock",
"version": "0.4",
"project_urls": {
"CI": "https://github.com/simonw/llm-bedrock/actions",
"Changelog": "https://github.com/simonw/llm-bedrock/releases",
"Homepage": "https://github.com/simonw/llm-bedrock",
"Issues": "https://github.com/simonw/llm-bedrock/issues"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "d995b14378bf770b54c765d2c0538150f577e8c94f045e1fed6c230d91cd38b3",
"md5": "bb9d2ad88a8fd45b35a9522165a0ad30",
"sha256": "128d56b73308f862fea89e727dc18d762f1a6d52a02215d9d45bb79c9c8022a0"
},
"downloads": -1,
"filename": "llm_bedrock-0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "bb9d2ad88a8fd45b35a9522165a0ad30",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 8538,
"upload_time": "2024-12-04T15:40:08",
"upload_time_iso_8601": "2024-12-04T15:40:08.778154Z",
"url": "https://files.pythonhosted.org/packages/d9/95/b14378bf770b54c765d2c0538150f577e8c94f045e1fed6c230d91cd38b3/llm_bedrock-0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "c821d184dd8e094fff1490067b97dac1b9b0e87ec83ccb677086fa0ae696acbd",
"md5": "b04a77eff0be98a70a22710f2987ed95",
"sha256": "ba46b3199adbf1fa153b69d3f48578079156de4d5b74552931922eba94bf2571"
},
"downloads": -1,
"filename": "llm_bedrock-0.4.tar.gz",
"has_sig": false,
"md5_digest": "b04a77eff0be98a70a22710f2987ed95",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 8456,
"upload_time": "2024-12-04T15:40:10",
"upload_time_iso_8601": "2024-12-04T15:40:10.542817Z",
"url": "https://files.pythonhosted.org/packages/c8/21/d184dd8e094fff1490067b97dac1b9b0e87ec83ccb677086fa0ae696acbd/llm_bedrock-0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-04 15:40:10",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "simonw",
"github_project": "llm-bedrock",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "llm-bedrock"
}
