# loam-ai
A command-line interface (CLI) tool for interacting with AWS Bedrock foundation models and inference profiles. LoamAI provides a streamlined way to invoke AI models, generate embeddings, and manage conversations through AWS Bedrock.
## Features
- List available foundation models and inference profiles
- Generate text and image embeddings
- Stream model responses for real-time output
- Support for conversation-based model interactions
- Manage multiple AWS profiles and regions
- Rich terminal output formatting
## Installation
Requires Python 3.10 or higher.
```bash
pip install loam-ai
```
## Configuration
### AWS SSO Login
If you're using AWS SSO, first configure your AWS profile and log in:
```bash
export AWS_PROFILE=your-sso-profile
aws sso login
```
After successful login, you can run loam-ai commands using your SSO credentials.
## Usage
### List Available Models
```bash
loam list-models
```
Filter by provider or output type:
```bash
loam list-models --provider anthropic
loam list-models --output TEXT
```
### Check Session Information
```bash
loam session
```
### Generate Embeddings
Generate text embeddings:
```bash
loam generate-embeddings \
--model-id amazon.titan-embed-text-v2:0 \
--input-file texts.txt
```
Generate image embeddings:
```bash
loam generate-embeddings \
--model-id amazon.titan-embed-image-v1 \
--image image.jpg \
--texts "Image description"
```
### Invoke Models
Simple text generation:
```bash
loam invoke \
-m amazon.nova-lite-v1:0 \
-p "What are the benefits of renewable energy?"
```
### Conversation Mode
Use conversation mode for chat-based interactions:
```bash
loam converse \
--model-id "anthropic.claude-3-sonnet-20240229-v1:0" \
--messages-file conversation.json
```
Example messages file format:
```json
[
{
"role": "user",
"content": [{ "text": "What is the capital of France?" }]
}
]
```
### List Inference Profiles
```bash
loam list-inference-profiles
```
## Command Options
### Global Options
- `--profile`: AWS profile name
- `--region`: AWS region
- `--debug`: Enable debug output
### Model Invocation Options
- `--temperature`: Control response randomness (0-1)
- `--max-tokens`: Maximum response length
- `--top-p`: Control response diversity (0-1)
## Error Handling
LoamAI provides clear error messages with rich terminal formatting. Common issues include:
- Invalid AWS credentials
- Unsupported model configurations
- Rate limiting
- Input validation errors
## Development
Built with:
- [Click](https://click.palletsprojects.com/) for CLI interface
- [Rich](https://rich.readthedocs.io/) for terminal formatting
- [boto3](https://boto3.amazonaws.com/v1/documentation/api/latest/index.html) for AWS SDK
## License
MIT License - See LICENSE file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "loam-ai",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "ai, aws, bedrock, cli, machine-learning",
"author": "Brendan Quinn",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/be/24/76c311de87909204d11915f79b73b67fa767f5f92a23ae7c859877740320/loam_ai-0.1.0.tar.gz",
"platform": null,
"description": "# loam-ai\n\nA command-line interface (CLI) tool for interacting with AWS Bedrock foundation models and inference profiles. LoamAI provides a streamlined way to invoke AI models, generate embeddings, and manage conversations through AWS Bedrock.\n\n## Features\n\n- List available foundation models and inference profiles\n- Generate text and image embeddings\n- Stream model responses for real-time output\n- Support for conversation-based model interactions\n- Manage multiple AWS profiles and regions\n- Rich terminal output formatting\n\n## Installation\n\nRequires Python 3.10 or higher.\n\n```bash\npip install loam-ai\n```\n\n## Configuration\n\n### AWS SSO Login\n\nIf you're using AWS SSO, first configure your AWS profile and log in:\n\n```bash\nexport AWS_PROFILE=your-sso-profile\naws sso login\n```\n\nAfter successful login, you can run loam-ai commands using your SSO credentials.\n\n## Usage\n\n### List Available Models\n\n```bash\nloam list-models\n```\n\nFilter by provider or output type:\n\n```bash\nloam list-models --provider anthropic\nloam list-models --output TEXT\n```\n\n### Check Session Information\n\n```bash\nloam session\n```\n\n### Generate Embeddings\n\nGenerate text embeddings:\n\n```bash\nloam generate-embeddings \\\n --model-id amazon.titan-embed-text-v2:0 \\\n --input-file texts.txt\n```\n\nGenerate image embeddings:\n\n```bash\nloam generate-embeddings \\\n --model-id amazon.titan-embed-image-v1 \\\n --image image.jpg \\\n --texts \"Image description\"\n```\n\n### Invoke Models\n\nSimple text generation:\n\n```bash\nloam invoke \\\n -m amazon.nova-lite-v1:0 \\\n -p \"What are the benefits of renewable energy?\"\n```\n\n### Conversation Mode\n\nUse conversation mode for chat-based interactions:\n\n```bash\nloam converse \\\n --model-id \"anthropic.claude-3-sonnet-20240229-v1:0\" \\\n --messages-file conversation.json\n```\n\nExample messages file format:\n\n```json\n[\n {\n \"role\": \"user\",\n \"content\": [{ \"text\": \"What is the capital of France?\" }]\n }\n]\n```\n\n### List Inference Profiles\n\n```bash\nloam list-inference-profiles\n```\n\n## Command Options\n\n### Global Options\n\n- `--profile`: AWS profile name\n- `--region`: AWS region\n- `--debug`: Enable debug output\n\n### Model Invocation Options\n\n- `--temperature`: Control response randomness (0-1)\n- `--max-tokens`: Maximum response length\n- `--top-p`: Control response diversity (0-1)\n\n## Error Handling\n\nLoamAI provides clear error messages with rich terminal formatting. Common issues include:\n\n- Invalid AWS credentials\n- Unsupported model configurations\n- Rate limiting\n- Input validation errors\n\n## Development\n\nBuilt with:\n\n- [Click](https://click.palletsprojects.com/) for CLI interface\n- [Rich](https://rich.readthedocs.io/) for terminal formatting\n- [boto3](https://boto3.amazonaws.com/v1/documentation/api/latest/index.html) for AWS SDK\n\n## License\n\nMIT License - See LICENSE file for details.\n",
"bugtrack_url": null,
"license": null,
"summary": "CLI tool for AWS Bedrock model invocation",
"version": "0.1.0",
"project_urls": {
"Homepage": "https://github.com/nulib-labs/loam-ai",
"Issues": "https://github.com/nulib-labs/loam-ai/issues",
"Repository": "https://github.com/nulib-labs/loam-ai.git"
},
"split_keywords": [
"ai",
" aws",
" bedrock",
" cli",
" machine-learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "dc39f289ed07714b6182f07d3bc311c542d28544282e6a63e7cb6b1267d574e7",
"md5": "8fdeb6f9bd33c7c0f48097d36970a014",
"sha256": "44277ff93d32e75554a33c97a0fbfabb8b5d0d938f3daf2f320c5db72e70f7e5"
},
"downloads": -1,
"filename": "loam_ai-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8fdeb6f9bd33c7c0f48097d36970a014",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 12249,
"upload_time": "2025-01-17T04:29:09",
"upload_time_iso_8601": "2025-01-17T04:29:09.597392Z",
"url": "https://files.pythonhosted.org/packages/dc/39/f289ed07714b6182f07d3bc311c542d28544282e6a63e7cb6b1267d574e7/loam_ai-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "be2476c311de87909204d11915f79b73b67fa767f5f92a23ae7c859877740320",
"md5": "16040cf1df70568d222c4cb2142f4464",
"sha256": "fac8c5cf94cb303ba706e6d476442c426bc9f84916566281eed1b431b6bdeeff"
},
"downloads": -1,
"filename": "loam_ai-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "16040cf1df70568d222c4cb2142f4464",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 30778,
"upload_time": "2025-01-17T04:29:12",
"upload_time_iso_8601": "2025-01-17T04:29:12.060168Z",
"url": "https://files.pythonhosted.org/packages/be/24/76c311de87909204d11915f79b73b67fa767f5f92a23ae7c859877740320/loam_ai-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-17 04:29:12",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "nulib-labs",
"github_project": "loam-ai",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "loam-ai"
}
JSON
