harshalmore31
1 month ago
parent
4cf5487cb0
commit
1bf5c3d08e
@ -1,119 +0,0 @@
|
||||
# Swarms 5.8.1 Feature Documentation
|
||||
|
||||
## 1. Enhanced Command Line Interface (CLI)
|
||||
|
||||
### 1.1 Integrated Onboarding Process
|
||||
|
||||
```bash
|
||||
$ swarms onboarding
|
||||
```
|
||||
|
||||
### 1.2 Run Agents Command
|
||||
|
||||
```bash
|
||||
$ swarms run-agents --yaml-file agents.yaml
|
||||
```
|
||||
|
||||
This command allows users to execute multiple agents defined in a YAML file. Here's the process:
|
||||
|
||||
1. The command reads the specified YAML file (`agents.yaml` in this case).
|
||||
2. It parses the YAML content, extracting the configuration for each agent.
|
||||
3. For each agent defined in the YAML:
|
||||
- It creates an instance of the agent with the specified parameters.
|
||||
- It sets up the agent's environment (model, temperature, max tokens, etc.).
|
||||
- It assigns the given task to the agent.
|
||||
- It executes the agent, respecting parameters like `max_loops`, `autosave`, and `verbose`.
|
||||
4. The results from all agents are collected and presented to the user.
|
||||
|
||||
The YAML file structure allows users to define multiple agents with different configurations, making it easy to run complex, multi-agent tasks from the command line.
|
||||
|
||||
### 1.3 Generate Prompt Feature
|
||||
|
||||
```bash
|
||||
$ swarms generate-prompt --prompt "Create a marketing strategy for a new product launch"
|
||||
```
|
||||
|
||||
This feature leverages Swarms' language model to generate expanded or refined prompts:
|
||||
|
||||
1. The command takes the user's input prompt as a starting point.
|
||||
2. It likely sends this prompt to a pre-configured language model (possibly GPT-4 or a similar model).
|
||||
3. The model then generates an expanded or more detailed version of the prompt.
|
||||
4. The generated prompt is returned to the user, possibly with options to further refine or save it.
|
||||
|
||||
This feature can help users create more effective prompts for their agents or other AI tasks.
|
||||
|
||||
## 2. New Prompt Management System
|
||||
|
||||
### 2.1 Prompt Class
|
||||
|
||||
The new `Prompt` class provides a robust system for managing and versioning prompts:
|
||||
|
||||
```python
|
||||
from swarms import Prompt
|
||||
|
||||
marketing_prompt = Prompt(content="Initial marketing strategy draft", autosave=True)
|
||||
|
||||
print(marketing_prompt.get_prompt())
|
||||
```
|
||||
|
||||
Key features of the `Prompt` class:
|
||||
|
||||
1. **Initialization**: The class is initialized with initial content and an `autosave` option.
|
||||
|
||||
2. **Editing**:
|
||||
```python
|
||||
marketing_prompt.edit_prompt("Updated marketing strategy with social media focus")
|
||||
```
|
||||
This method updates the prompt content and, if `autosave` is True, automatically saves the new version.
|
||||
|
||||
3. **Retrieval**:
|
||||
```python
|
||||
current_content = marketing_prompt.get_prompt()
|
||||
```
|
||||
This method returns the current content of the prompt.
|
||||
|
||||
4. **Version History**:
|
||||
```python
|
||||
print(f"Edit history: {marketing_prompt.edit_history}")
|
||||
```
|
||||
The class maintains a history of edits, allowing users to track changes over time.
|
||||
|
||||
5. **Rollback**:
|
||||
```python
|
||||
marketing_prompt.rollback(1)
|
||||
```
|
||||
This feature allows users to revert to a previous version of the prompt.
|
||||
|
||||
6. **Duplicate Prevention**:
|
||||
The class includes logic to prevent duplicate edits, raising a `ValueError` if an attempt is made to save the same content twice in a row.
|
||||
|
||||
This system provides a powerful way to manage prompts, especially for complex projects where prompt engineering and iteration are crucial.
|
||||
|
||||
## 3. Upcoming Features Preview
|
||||
|
||||
### 3.1 Enhanced Agent Execution Capabilities
|
||||
|
||||
The preview code demonstrates planned enhancements for agent execution:
|
||||
|
||||
```python
|
||||
from swarms import Agent, ExecutionEnvironment
|
||||
|
||||
my_agent = Agent(name="data_processor")
|
||||
|
||||
cpu_env = ExecutionEnvironment(type="cpu", cores=4)
|
||||
my_agent.run(environment=cpu_env)
|
||||
|
||||
gpu_env = ExecutionEnvironment(type="gpu", device_id=0)
|
||||
my_agent.run(environment=gpu_env)
|
||||
|
||||
fractional_env = ExecutionEnvironment(type="fractional", cpu_fraction=0.5, gpu_fraction=0.3)
|
||||
my_agent.run(environment=fractional_env)
|
||||
```
|
||||
|
||||
This upcoming feature will allow for more fine-grained control over the execution environment:
|
||||
|
||||
1. **CPU Execution**: Users can specify the number of CPU cores to use.
|
||||
2. **GPU Execution**: Allows selection of a specific GPU device.
|
||||
3. **Fractionalized Execution**: Enables partial allocation of CPU and GPU resources.
|
||||
|
||||
These features will provide users with greater flexibility in resource allocation, potentially improving performance and allowing for more efficient use of available hardware.
|
||||
@ -1,59 +0,0 @@
|
||||
# Swarms 6.0.0 - Performance & Reliability Update 🚀
|
||||
|
||||
We're excited to announce the release of Swarms 6.0.0, bringing significant improvements to performance, reliability, and developer experience. This release focuses on streamlining core functionalities while enhancing the overall stability of the framework.
|
||||
|
||||
## 📦 Installation
|
||||
|
||||
```bash
|
||||
pip3 install -U swarms
|
||||
```
|
||||
|
||||
## 🌟 Highlights
|
||||
|
||||
### Agent Enhancements
|
||||
- **Improved RAG Performance**: Significant improvements to Retrieval-Augmented Generation capabilities
|
||||
- **Enhanced Prompt Generation**: Auto-generate prompt now incorporates name, description, and system prompt for more contextual interactions
|
||||
- **Streamlined Architecture**: Cleaned up unused code for better performance and maintainability
|
||||
- **Simplified State Management**: Consolidated state management methods into a single `load()` function
|
||||
|
||||
### Tools & Execution
|
||||
- **Optimized Environment Management**: Fixed multiple environment instantiation issue
|
||||
- Environments now initialize once during `__init__`
|
||||
- **New SwarmRouter Function**: Simplified routing mechanism
|
||||
- Returns consolidated string output from all agents
|
||||
- Improved coordination between swarm components
|
||||
|
||||
## 💪 Performance Improvements
|
||||
- Faster execution times
|
||||
- Reduced memory footprint
|
||||
- More reliable logging system
|
||||
- Lightweight and efficient codebase
|
||||
|
||||
## 🤝 Join Our Community
|
||||
|
||||
### We're Hiring!
|
||||
Join our growing team! We're currently looking for:
|
||||
- Agent Engineers
|
||||
- Developer Relations
|
||||
- Infrastructure Engineers
|
||||
- And more!
|
||||
|
||||
### Get Involved
|
||||
- ⭐ Star our repository
|
||||
- 🔄 Fork the project
|
||||
- 🛠 Submit pull requests
|
||||
- 🐛 Report issues
|
||||
- 💡 Share your ideas
|
||||
|
||||
### Contact & Support
|
||||
- 📧 Email: kye@swarms.world
|
||||
- 🔗 Issues: [GitHub Issues](https://github.com/kyegomez/swarms/issues)
|
||||
|
||||
## 🔜 What's Next?
|
||||
Have ideas for features, bug fixes, or improvements? We'd love to hear from you! Reach out through our GitHub issues or email us directly.
|
||||
|
||||
---
|
||||
|
||||
*Thank you to all our contributors and users who make Swarms better every day. Together, we're building the future of swarm intelligence.*
|
||||
|
||||
#SwarmAI #OpenSource #AI #MachineLearning
|
||||
@ -1,59 +0,0 @@
|
||||
# Swarms 6.0.0 - Performance & Reliability Update 🚀
|
||||
|
||||
We're excited to announce the release of Swarms 6.0.0, bringing significant improvements to performance, reliability, and developer experience. This release focuses on streamlining core functionalities while enhancing the overall stability of the framework.
|
||||
|
||||
## 📦 Installation
|
||||
|
||||
```bash
|
||||
pip3 install -U swarms
|
||||
```
|
||||
|
||||
## 🌟 Highlights
|
||||
|
||||
### Agent Enhancements
|
||||
- **Improved RAG Performance**: Significant improvements to Retrieval-Augmented Generation capabilities
|
||||
- **Enhanced Prompt Generation**: Auto-generate prompt now incorporates name, description, and system prompt for more contextual interactions
|
||||
- **Streamlined Architecture**: Cleaned up unused code for better performance and maintainability
|
||||
- **Simplified State Management**: Consolidated state management methods into a single `load()` function
|
||||
|
||||
### Tools & Execution
|
||||
- **Optimized Environment Management**: Fixed multiple environment instantiation issue
|
||||
- Environments now initialize once during `__init__`
|
||||
- **New SwarmRouter Function**: Simplified routing mechanism
|
||||
- Returns consolidated string output from all agents
|
||||
- Improved coordination between swarm components
|
||||
|
||||
## 💪 Performance Improvements
|
||||
- Faster execution times
|
||||
- Reduced memory footprint
|
||||
- More reliable logging system
|
||||
- Lightweight and efficient codebase
|
||||
|
||||
## 🤝 Join Our Community
|
||||
|
||||
### We're Hiring!
|
||||
Join our growing team! We're currently looking for:
|
||||
- Agent Engineers
|
||||
- Developer Relations
|
||||
- Infrastructure Engineers
|
||||
- And more!
|
||||
|
||||
### Get Involved
|
||||
- ⭐ Star our repository
|
||||
- 🔄 Fork the project
|
||||
- 🛠 Submit pull requests
|
||||
- 🐛 Report issues
|
||||
- 💡 Share your ideas
|
||||
|
||||
### Contact & Support
|
||||
- 📧 Email: kye@swarms.world
|
||||
- 🔗 Issues: [GitHub Issues](https://github.com/kyegomez/swarms/issues)
|
||||
|
||||
## 🔜 What's Next?
|
||||
Have ideas for features, bug fixes, or improvements? We'd love to hear from you! Reach out through our GitHub issues or email us directly.
|
||||
|
||||
---
|
||||
|
||||
*Thank you to all our contributors and users who make Swarms better every day. Together, we're building the future of swarm intelligence.*
|
||||
|
||||
#SwarmAI #OpenSource #AI #MachineLearning
|
||||
@ -1,90 +0,0 @@
|
||||
# 🚀 Swarms 5.9.2 Release Notes
|
||||
|
||||
|
||||
### 🎯 Major Features
|
||||
|
||||
#### Concurrent Agent Execution Suite
|
||||
We're excited to introduce a comprehensive suite of agent execution methods to supercharge your multi-agent workflows:
|
||||
|
||||
- `run_agents_concurrently`: Execute multiple agents in parallel with optimal resource utilization
|
||||
- `run_agents_concurrently_async`: Asynchronous execution for improved performance
|
||||
- `run_single_agent`: Streamlined single agent execution
|
||||
- `run_agents_concurrently_multiprocess`: Multi-process execution for CPU-intensive tasks
|
||||
- `run_agents_sequentially`: Sequential execution with controlled flow
|
||||
- `run_agents_with_different_tasks`: Assign different tasks to different agents
|
||||
- `run_agent_with_timeout`: Time-bounded agent execution
|
||||
- `run_agents_with_resource_monitoring`: Monitor and manage resource usage
|
||||
|
||||
### 📚 Documentation
|
||||
- Comprehensive documentation added for all new execution methods
|
||||
- Updated examples and usage patterns
|
||||
- Enhanced API reference
|
||||
|
||||
### 🛠️ Improvements
|
||||
- Tree swarm implementation fixes
|
||||
- Workspace directory now automatically set to `agent_workspace`
|
||||
- Improved error handling and stability
|
||||
|
||||
## Quick Start
|
||||
|
||||
```python
|
||||
from swarms import Agent, run_agents_concurrently, run_agents_with_timeout, run_agents_with_different_tasks
|
||||
|
||||
# Initialize multiple agents
|
||||
agents = [
|
||||
Agent(
|
||||
agent_name=f"Analysis-Agent-{i}",
|
||||
system_prompt="You are a financial analysis expert",
|
||||
llm=model,
|
||||
max_loops=1
|
||||
)
|
||||
for i in range(5)
|
||||
]
|
||||
|
||||
# Run agents concurrently
|
||||
task = "Analyze the impact of rising interest rates on tech stocks"
|
||||
outputs = run_agents_concurrently(agents, task)
|
||||
|
||||
# Example with timeout
|
||||
outputs_with_timeout = run_agents_with_timeout(
|
||||
agents=agents,
|
||||
task=task,
|
||||
timeout=30.0,
|
||||
batch_size=2
|
||||
)
|
||||
|
||||
# Run different tasks
|
||||
task_pairs = [
|
||||
(agents[0], "Analyze tech stocks"),
|
||||
(agents[1], "Analyze energy stocks"),
|
||||
(agents[2], "Analyze retail stocks")
|
||||
]
|
||||
different_outputs = run_agents_with_different_tasks(task_pairs)
|
||||
```
|
||||
|
||||
## Installation
|
||||
```bash
|
||||
pip3 install -U swarms
|
||||
```
|
||||
|
||||
## Coming Soon
|
||||
- 🌟 Auto Swarm Builder: Automatically construct and configure entire swarms from a single task specification (in development)
|
||||
- Auto Prompt Generator for thousands of agents (in development)
|
||||
|
||||
## Community
|
||||
We believe in the power of community-driven development. Help us make Swarms better!
|
||||
|
||||
- ⭐ Star our repository: https://github.com/kyegomez/swarms
|
||||
- 🔄 Fork the project and contribute your improvements
|
||||
- 🤝 Join our growing community of contributors
|
||||
|
||||
## Bug Fixes
|
||||
- Fixed Tree Swarm implementation issues
|
||||
- Resolved workspace directory configuration problems
|
||||
- General stability improvements
|
||||
|
||||
---
|
||||
|
||||
For detailed documentation and examples, visit our [GitHub repository](https://github.com/kyegomez/swarms).
|
||||
|
||||
Let's build the future of multi-agent systems together! 🚀
|
||||
Loading…
Reference in new issue