# Action Collective
A framework for dynamic action generation and reuse with LLMs.
## Installation
```bash
pip install action-collective
```
## Quick Start
```python
from action_collective import ActionClient
client = ActionClient(
openai_api_key=os.getenv("OPENAI_API_KEY"),
backend_url=os.getenv("BACKEND_URL", "http://70.179.0.242:11000"),
verbose=True,
)
prompt = """Please perform the matrix multiplication of A x B and return the result, here are the variables:
A = [[1, 2, 3, 4, 5],
[6, 7, 7, 9, 10],
[11, 12, 13, 14, 15],
[16, 17, 7, 19, 20],
[21, 22, 23, 24, 25]]
B = [[1, 2, 3, 4, 5],
[6, 7, 8, 9, 10],
[11, 12, 7, 14, 15],
[16, 17, 18, 19, 20],
[21, 22, 23, 24, 25]]"""
chat_history = [{"role": "user", "content": prompt}]
result = await client.execute(chat_history=chat_history)
print("\n\nresult:\n", json.dumps(result, indent=4), "\n\n")
matrix = [
[215, 230, 227, 260, 275],
[479, 518, 515, 596, 635],
[765, 830, 817, 960, 1025],
[919, 998, 1035, 1156, 1235],
[1315, 1430, 1407, 1660, 1775],
]
# validate that each of the number inside matrix exist in the result string
assert result is not None
for row in matrix:
for number in row:
assert str(number) in result[-1]["content"]
print("\n\nPASSED\n\n")
```
## Features
- Dynamic action generation
- Action reuse through vector similarity
- Automatic validation and testing
- Easy integration with OpenAI models
## Documentation
For full documentation, visit our [GitHub repository](https://github.com/yourusername/ActionCollective).
Raw data
{
"_id": null,
"home_page": "https://github.com/CakeCrusher/ActionCollective",
"name": "action-collective",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "llm, ai, actions, tools",
"author": "Sebastian Sosa",
"author_email": "1sebastian1sosa1@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/4e/c4/174b35114e527d31343e58fb36ea93f1054a21ea36ffa72925f5cca05e2a/action_collective-0.0.4.tar.gz",
"platform": null,
"description": "# Action Collective\n\nA framework for dynamic action generation and reuse with LLMs.\n\n## Installation\n\n```bash\npip install action-collective\n```\n\n## Quick Start\n\n```python\nfrom action_collective import ActionClient\n\nclient = ActionClient(\n openai_api_key=os.getenv(\"OPENAI_API_KEY\"),\n backend_url=os.getenv(\"BACKEND_URL\", \"http://70.179.0.242:11000\"),\n verbose=True,\n)\nprompt = \"\"\"Please perform the matrix multiplication of A x B and return the result, here are the variables:\nA = [[1, 2, 3, 4, 5],\n [6, 7, 7, 9, 10],\n [11, 12, 13, 14, 15],\n [16, 17, 7, 19, 20],\n [21, 22, 23, 24, 25]]\nB = [[1, 2, 3, 4, 5],\n [6, 7, 8, 9, 10],\n [11, 12, 7, 14, 15],\n [16, 17, 18, 19, 20],\n [21, 22, 23, 24, 25]]\"\"\"\n\nchat_history = [{\"role\": \"user\", \"content\": prompt}]\n\nresult = await client.execute(chat_history=chat_history)\nprint(\"\\n\\nresult:\\n\", json.dumps(result, indent=4), \"\\n\\n\")\nmatrix = [\n [215, 230, 227, 260, 275],\n [479, 518, 515, 596, 635],\n [765, 830, 817, 960, 1025],\n [919, 998, 1035, 1156, 1235],\n [1315, 1430, 1407, 1660, 1775],\n]\n# validate that each of the number inside matrix exist in the result string\nassert result is not None\nfor row in matrix:\n for number in row:\n assert str(number) in result[-1][\"content\"]\nprint(\"\\n\\nPASSED\\n\\n\")\n```\n\n## Features\n\n- Dynamic action generation\n- Action reuse through vector similarity\n- Automatic validation and testing\n- Easy integration with OpenAI models\n\n## Documentation\n\nFor full documentation, visit our [GitHub repository](https://github.com/yourusername/ActionCollective).",
"bugtrack_url": null,
"license": "MIT",
"summary": "A framework for dynamic action generation and reuse with LLMs",
"version": "0.0.4",
"project_urls": {
"Documentation": "https://github.com/CakeCrusher/ActionCollective",
"Homepage": "https://github.com/CakeCrusher/ActionCollective",
"Repository": "https://github.com/CakeCrusher/ActionCollective"
},
"split_keywords": [
"llm",
" ai",
" actions",
" tools"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "e09207dfc14adc5596f882d50d5e27b6c07047f97232d4270095865fbbe47bb4",
"md5": "1eea99e11fdb6070f797854531cd4a28",
"sha256": "c608974cb514a451c3ac7940fd5304b49b6675b8dc68f05f22bf58f130884608"
},
"downloads": -1,
"filename": "action_collective-0.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "1eea99e11fdb6070f797854531cd4a28",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 7748,
"upload_time": "2024-12-18T04:31:51",
"upload_time_iso_8601": "2024-12-18T04:31:51.387735Z",
"url": "https://files.pythonhosted.org/packages/e0/92/07dfc14adc5596f882d50d5e27b6c07047f97232d4270095865fbbe47bb4/action_collective-0.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "4ec4174b35114e527d31343e58fb36ea93f1054a21ea36ffa72925f5cca05e2a",
"md5": "b0dfdbe951aac967305f7cd8f9f132bd",
"sha256": "6263a4e216fddbb11d2787faa7aca362677938c2e9da7c35bedd08be376eb640"
},
"downloads": -1,
"filename": "action_collective-0.0.4.tar.gz",
"has_sig": false,
"md5_digest": "b0dfdbe951aac967305f7cd8f9f132bd",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 6038,
"upload_time": "2024-12-18T04:31:53",
"upload_time_iso_8601": "2024-12-18T04:31:53.802020Z",
"url": "https://files.pythonhosted.org/packages/4e/c4/174b35114e527d31343e58fb36ea93f1054a21ea36ffa72925f5cca05e2a/action_collective-0.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-18 04:31:53",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "CakeCrusher",
"github_project": "ActionCollective",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "action-collective"
}
JSON
