# Swarms Deploy 🚀
[](https://discord.gg/agora-999382051935506503) [](https://www.youtube.com/@kyegomez3242) [](https://www.linkedin.com/in/kye-g-38759a207/) [](https://x.com/kyegomezb)
[](https://badge.fury.io/py/swarms-deploy)
[](https://opensource.org/licenses/MIT)
[](https://www.python.org/downloads/)
Production-grade API deployment framework for Swarms AI workflows. Easily deploy, scale, and manage your swarm-based applications with enterprise features.
## Features ✨
- 🔥 Fast API-based deployment framework
- 🤖 Support for synchronous and asynchronous swarm execution
- 🔄 Built-in load balancing and scaling
- 📊 Real-time monitoring and logging
- 🛡️ Enterprise-grade error handling
- 🎯 Priority-based task execution
- 📦 Simple deployment and configuration
- 🔌 Extensible plugin architecture
## Installation 📦
```bash
pip install -U swarms-deploy
```
## Quick Start 🚀
```python
import os
from dotenv import load_dotenv
from swarms import Agent, SequentialWorkflow
from swarm_models import OpenAIChat
from swarm_deploy import SwarmDeploy
load_dotenv()
# Get the OpenAI API key from the environment variable
api_key = os.getenv("GROQ_API_KEY")
# Model
model = OpenAIChat(
openai_api_base="https://api.groq.com/openai/v1",
openai_api_key=api_key,
model_name="llama-3.1-70b-versatile",
temperature=0.1,
)
# Initialize specialized agents
data_extractor_agent = Agent(
agent_name="Data-Extractor",
system_prompt=None,
llm=model,
max_loops=1,
autosave=True,
verbose=True,
dynamic_temperature_enabled=True,
saved_state_path="data_extractor_agent.json",
user_name="pe_firm",
retry_attempts=1,
context_length=200000,
output_type="string",
)
summarizer_agent = Agent(
agent_name="Document-Summarizer",
system_prompt=None,
llm=model,
max_loops=1,
autosave=True,
verbose=True,
dynamic_temperature_enabled=True,
saved_state_path="summarizer_agent.json",
user_name="pe_firm",
retry_attempts=1,
context_length=200000,
output_type="string",
)
financial_analyst_agent = Agent(
agent_name="Financial-Analyst",
system_prompt=None,
llm=model,
max_loops=1,
autosave=True,
verbose=True,
dynamic_temperature_enabled=True,
saved_state_path="financial_analyst_agent.json",
user_name="pe_firm",
retry_attempts=1,
context_length=200000,
output_type="string",
)
market_analyst_agent = Agent(
agent_name="Market-Analyst",
system_prompt=None,
llm=model,
max_loops=1,
autosave=True,
verbose=True,
dynamic_temperature_enabled=True,
saved_state_path="market_analyst_agent.json",
user_name="pe_firm",
retry_attempts=1,
context_length=200000,
output_type="string",
)
operational_analyst_agent = Agent(
agent_name="Operational-Analyst",
system_prompt=None,
llm=model,
max_loops=1,
autosave=True,
verbose=True,
dynamic_temperature_enabled=True,
saved_state_path="operational_analyst_agent.json",
user_name="pe_firm",
retry_attempts=1,
context_length=200000,
output_type="string",
)
# Initialize the SwarmRouter
router = SequentialWorkflow(
name="pe-document-analysis-swarm",
description="Analyze documents for private equity due diligence and investment decision-making",
max_loops=1,
agents=[
data_extractor_agent,
summarizer_agent,
financial_analyst_agent,
market_analyst_agent,
operational_analyst_agent,
],
output_type="all",
)
# Advanced usage with configuration
swarm = SwarmDeploy(
router,
max_workers=4,
# cache_backend="redis"
)
swarm.start(
host="0.0.0.0",
port=8000,
workers=4,
)
```
## Advanced Usage 🔧
### Configuration Options
```python
swarm = SwarmDeploy(
workflow,
max_workers=4,
cache_backend="redis",
ssl_config={
"keyfile": "path/to/key.pem",
"certfile": "path/to/cert.pem"
}
)
```
## API Reference 📚
### SwarmInput Model
```python
class SwarmInput(BaseModel):
task: str # Task description
img: Optional[str] # Optional image input
priority: int # Task priority (0-10)
```
### API Endpoints
- **POST** `/v1/swarms/completions/{callable_name}`
- Execute a task with the specified swarm
- Returns: SwarmOutput or SwarmBatchOutput
### Example Request
```bash
curl -X POST "http://localhost:8000/v1/swarms/completions/document-analysis" \
-H "Content-Type: application/json" \
-d '{"task": "Analyze financial report", "priority": 5}'
```
## Monitoring and Logging 📊
SwarmDeploy provides built-in monitoring capabilities:
- Real-time task execution stats
- Error tracking and reporting
- Performance metrics
- Task history and audit logs
## Error Handling 🛡️
The system includes comprehensive error handling:
```python
try:
result = await swarm.run(task)
except Exception as e:
error_output = SwarmOutput(
id=str(uuid.uuid4()),
status="error",
execution_time=time.time() - start_time,
result=None,
error=str(e)
)
```
## Best Practices 🎯
1. Always set appropriate task priorities
2. Implement proper error handling
3. Use clustering for high-availability
4. Monitor system performance
5. Regular maintenance and updates
## Contributing 🤝
Contributions are welcome! Please read our [Contributing Guidelines](CONTRIBUTING.md) for details on our code of conduct and the process for submitting pull requests.
## Support 💬
- Email: kye@swarms.world
- Discord: [Join our community](https://swarms.world/swarms)
- Documentation: [https://docs.swarms.world](https://docs.swarms.world)
## License 📄
MIT License - see the [LICENSE](LICENSE) file for details.
---
Powered by [swarms.ai](https://swarms.ai) 🚀
For enterprise support and custom solutions, contact kye@swarms.world
Raw data
{
"_id": null,
"home_page": "https://github.com/The-Swarm-Corporation/SwarmDeploy",
"name": "swarm-deploy",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": "artificial intelligence, deep learning, optimizers, Prompt Engineering",
"author": "Kye Gomez",
"author_email": "kye@apac.ai",
"download_url": "https://files.pythonhosted.org/packages/c4/03/c0fcf270e492c1db27f5e7565baa09bac30cc310eac5075e05693f672f74/swarm_deploy-0.0.4.tar.gz",
"platform": null,
"description": "# Swarms Deploy \ud83d\ude80\n\n[](https://discord.gg/agora-999382051935506503) [](https://www.youtube.com/@kyegomez3242) [](https://www.linkedin.com/in/kye-g-38759a207/) [](https://x.com/kyegomezb)\n\n\n[](https://badge.fury.io/py/swarms-deploy)\n[](https://opensource.org/licenses/MIT)\n[](https://www.python.org/downloads/)\n\nProduction-grade API deployment framework for Swarms AI workflows. Easily deploy, scale, and manage your swarm-based applications with enterprise features.\n\n## Features \u2728\n\n- \ud83d\udd25 Fast API-based deployment framework\n- \ud83e\udd16 Support for synchronous and asynchronous swarm execution\n- \ud83d\udd04 Built-in load balancing and scaling\n- \ud83d\udcca Real-time monitoring and logging\n- \ud83d\udee1\ufe0f Enterprise-grade error handling\n- \ud83c\udfaf Priority-based task execution\n- \ud83d\udce6 Simple deployment and configuration\n- \ud83d\udd0c Extensible plugin architecture\n\n## Installation \ud83d\udce6\n\n```bash\npip install -U swarms-deploy\n```\n\n## Quick Start \ud83d\ude80\n\n```python\nimport os\nfrom dotenv import load_dotenv\nfrom swarms import Agent, SequentialWorkflow\nfrom swarm_models import OpenAIChat\nfrom swarm_deploy import SwarmDeploy\n\nload_dotenv()\n\n# Get the OpenAI API key from the environment variable\napi_key = os.getenv(\"GROQ_API_KEY\")\n\n# Model\nmodel = OpenAIChat(\n openai_api_base=\"https://api.groq.com/openai/v1\",\n openai_api_key=api_key,\n model_name=\"llama-3.1-70b-versatile\",\n temperature=0.1,\n)\n\n\n# Initialize specialized agents\ndata_extractor_agent = Agent(\n agent_name=\"Data-Extractor\",\n system_prompt=None,\n llm=model,\n max_loops=1,\n autosave=True,\n verbose=True,\n dynamic_temperature_enabled=True,\n saved_state_path=\"data_extractor_agent.json\",\n user_name=\"pe_firm\",\n retry_attempts=1,\n context_length=200000,\n output_type=\"string\",\n)\n\nsummarizer_agent = Agent(\n agent_name=\"Document-Summarizer\",\n system_prompt=None,\n llm=model,\n max_loops=1,\n autosave=True,\n verbose=True,\n dynamic_temperature_enabled=True,\n saved_state_path=\"summarizer_agent.json\",\n user_name=\"pe_firm\",\n retry_attempts=1,\n context_length=200000,\n output_type=\"string\",\n)\n\nfinancial_analyst_agent = Agent(\n agent_name=\"Financial-Analyst\",\n system_prompt=None,\n llm=model,\n max_loops=1,\n autosave=True,\n verbose=True,\n dynamic_temperature_enabled=True,\n saved_state_path=\"financial_analyst_agent.json\",\n user_name=\"pe_firm\",\n retry_attempts=1,\n context_length=200000,\n output_type=\"string\",\n)\n\nmarket_analyst_agent = Agent(\n agent_name=\"Market-Analyst\",\n system_prompt=None,\n llm=model,\n max_loops=1,\n autosave=True,\n verbose=True,\n dynamic_temperature_enabled=True,\n saved_state_path=\"market_analyst_agent.json\",\n user_name=\"pe_firm\",\n retry_attempts=1,\n context_length=200000,\n output_type=\"string\",\n)\n\noperational_analyst_agent = Agent(\n agent_name=\"Operational-Analyst\",\n system_prompt=None,\n llm=model,\n max_loops=1,\n autosave=True,\n verbose=True,\n dynamic_temperature_enabled=True,\n saved_state_path=\"operational_analyst_agent.json\",\n user_name=\"pe_firm\",\n retry_attempts=1,\n context_length=200000,\n output_type=\"string\",\n)\n\n# Initialize the SwarmRouter\nrouter = SequentialWorkflow(\n name=\"pe-document-analysis-swarm\",\n description=\"Analyze documents for private equity due diligence and investment decision-making\",\n max_loops=1,\n agents=[\n data_extractor_agent,\n summarizer_agent,\n financial_analyst_agent,\n market_analyst_agent,\n operational_analyst_agent,\n ],\n output_type=\"all\",\n)\n\n# Advanced usage with configuration\nswarm = SwarmDeploy(\n router,\n max_workers=4,\n # cache_backend=\"redis\"\n)\nswarm.start(\n host=\"0.0.0.0\",\n port=8000,\n workers=4,\n)\n\n```\n\n## Advanced Usage \ud83d\udd27\n\n### Configuration Options\n\n```python\nswarm = SwarmDeploy(\n workflow,\n max_workers=4,\n cache_backend=\"redis\",\n ssl_config={\n \"keyfile\": \"path/to/key.pem\",\n \"certfile\": \"path/to/cert.pem\"\n }\n)\n```\n\n\n\n## API Reference \ud83d\udcda\n\n### SwarmInput Model\n\n```python\nclass SwarmInput(BaseModel):\n task: str # Task description\n img: Optional[str] # Optional image input\n priority: int # Task priority (0-10)\n```\n\n### API Endpoints\n\n- **POST** `/v1/swarms/completions/{callable_name}`\n - Execute a task with the specified swarm\n - Returns: SwarmOutput or SwarmBatchOutput\n\n### Example Request\n\n```bash\ncurl -X POST \"http://localhost:8000/v1/swarms/completions/document-analysis\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"task\": \"Analyze financial report\", \"priority\": 5}'\n```\n\n## Monitoring and Logging \ud83d\udcca\n\nSwarmDeploy provides built-in monitoring capabilities:\n\n- Real-time task execution stats\n- Error tracking and reporting\n- Performance metrics\n- Task history and audit logs\n\n## Error Handling \ud83d\udee1\ufe0f\n\nThe system includes comprehensive error handling:\n\n```python\ntry:\n result = await swarm.run(task)\nexcept Exception as e:\n error_output = SwarmOutput(\n id=str(uuid.uuid4()),\n status=\"error\",\n execution_time=time.time() - start_time,\n result=None,\n error=str(e)\n )\n```\n\n## Best Practices \ud83c\udfaf\n\n1. Always set appropriate task priorities\n2. Implement proper error handling\n3. Use clustering for high-availability\n4. Monitor system performance\n5. Regular maintenance and updates\n\n## Contributing \ud83e\udd1d\n\nContributions are welcome! Please read our [Contributing Guidelines](CONTRIBUTING.md) for details on our code of conduct and the process for submitting pull requests.\n\n## Support \ud83d\udcac\n\n- Email: kye@swarms.world\n- Discord: [Join our community](https://swarms.world/swarms)\n- Documentation: [https://docs.swarms.world](https://docs.swarms.world)\n\n## License \ud83d\udcc4\n\nMIT License - see the [LICENSE](LICENSE) file for details.\n\n---\n\nPowered by [swarms.ai](https://swarms.ai) \ud83d\ude80\n\nFor enterprise support and custom solutions, contact kye@swarms.world",
"bugtrack_url": null,
"license": "MIT",
"summary": "Swarm-Deploy - TGSC",
"version": "0.0.4",
"project_urls": {
"Documentation": "https://github.com/The-Swarm-Corporation/SwarmDeploy",
"Homepage": "https://github.com/The-Swarm-Corporation/SwarmDeploy",
"Repository": "https://github.com/The-Swarm-Corporation/SwarmDeploy"
},
"split_keywords": [
"artificial intelligence",
" deep learning",
" optimizers",
" prompt engineering"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "1eeed0ca4821ddcdf065bf2323f8dff3082d98c76baaf6c6d5c1d505db205ed7",
"md5": "9d0b291e82a39ec7e6c0fa0b3e839842",
"sha256": "2f1e36d3afcbd37e3c3e9ebea07fc435b670c88824dabdc76b6bf708bffcdab1"
},
"downloads": -1,
"filename": "swarm_deploy-0.0.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "9d0b291e82a39ec7e6c0fa0b3e839842",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 10854,
"upload_time": "2025-01-16T01:11:40",
"upload_time_iso_8601": "2025-01-16T01:11:40.790044Z",
"url": "https://files.pythonhosted.org/packages/1e/ee/d0ca4821ddcdf065bf2323f8dff3082d98c76baaf6c6d5c1d505db205ed7/swarm_deploy-0.0.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "c403c0fcf270e492c1db27f5e7565baa09bac30cc310eac5075e05693f672f74",
"md5": "1b5d8b2e6f8e8143eddd6f176c4b1e5e",
"sha256": "048ddb1d121b631462245f85e030146ec6fee5969319a24d51645357654f2b97"
},
"downloads": -1,
"filename": "swarm_deploy-0.0.4.tar.gz",
"has_sig": false,
"md5_digest": "1b5d8b2e6f8e8143eddd6f176c4b1e5e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 12348,
"upload_time": "2025-01-16T01:11:42",
"upload_time_iso_8601": "2025-01-16T01:11:42.945263Z",
"url": "https://files.pythonhosted.org/packages/c4/03/c0fcf270e492c1db27f5e7565baa09bac30cc310eac5075e05693f672f74/swarm_deploy-0.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-16 01:11:42",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "The-Swarm-Corporation",
"github_project": "SwarmDeploy",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "swarms",
"specs": []
},
{
"name": "asyncio",
"specs": []
},
{
"name": "uuid",
"specs": []
},
{
"name": "datetime",
"specs": []
},
{
"name": "typing",
"specs": []
},
{
"name": "orjson",
"specs": []
},
{
"name": "structlog",
"specs": []
},
{
"name": "aiocache",
"specs": []
},
{
"name": "fastapi",
"specs": []
},
{
"name": "prometheus_client",
"specs": []
},
{
"name": "pydantic",
"specs": []
},
{
"name": "rich",
"specs": []
}
],
"lcname": "swarm-deploy"
}
JSON
