Add Mintlify docs

docs_new/advanced-topics/asynchronous-execution.mdx

@@ -0,0 +1,46 @@
+---
+title: "Asynchronous Execution"
+description: "Enhance the performance of your agency by running agents and tools asynchronously."
+icon: "bolt"
+---
+
+<Tip>
+Asynchronous execution allows agents and tools to operate concurrently, improving overall efficiency.
+</Tip>
+
+## Enabling Asynchronous Agents
+
+To enable asynchronous execution for agents, set the `async_mode` parameter to `"threading"` when initializing the agency.
+
+<CodeBlock title="Initialize Agency with Asynchronous Agents" language="python">
+agency = Agency(agents=[ceo], async_mode='threading')
+</CodeBlock>
+
+**Benefits**:
+
+- Agents operate independently without waiting for others to complete tasks.
+- Improved performance in multi-agent setups.
+
+## Enabling Asynchronous Tools
+
+To enable asynchronous execution for tools, set the `async_mode` parameter to `"tools_threading"`.
+
+<CodeBlock title="Initialize Agency with Asynchronous Tools" language="python">
+agency = Agency(agents=[ceo], async_mode='tools_threading')
+</CodeBlock>
+
+**Benefits**:
+
+- Tools execute concurrently, reducing latency for I/O-bound operations.
+- Enhanced responsiveness of agents utilizing tools.
+
+## Considerations
+
+<Warning>
+When using asynchronous execution, be mindful of concurrency issues.
+</Warning>
+
+- **Concurrency Control**: Ensure thread-safe operations to prevent race conditions. Use thread locks or other synchronization mechanisms if necessary.
+
+- **Resource Management**: Monitor system resources to avoid overconsumption due to multiple threads. Keep an eye on CPU and memory usage.
+

docs_new/advanced-topics/customizing-prompts-and-few-shot-learning.mdx

@@ -0,0 +1,71 @@
+---
+title: "Customizing Prompts and Few-Shot Learning"
+description: "Fine-tune agent behavior by customizing prompts and providing few-shot examples."
+icon: "magic"
+---
+
+Fine-tune agent behavior by customizing prompts and providing few-shot examples.
+
+<Info>
+Custom prompts and few-shot learning help your agents understand the desired response style and content, leading to more accurate and tailored outputs.
+</Info>
+
+## Custom Prompts
+
+### Modify Instructions
+
+Adjust the `instructions.md` file associated with your agent to change how it responds.
+
+<CodeBlock title="instructions.md" language="markdown">
+# Agent Instructions
+
+You are a friendly assistant that helps users with booking flights and hotels.
+</CodeBlock>
+
+### Dynamic Prompts
+
+Programmatically alter prompts based on context or user input.
+
+<CodeBlock title="Dynamic Prompt Example" language="python">
+base_instructions = "You are an assistant who provides technical support."
+
+additional_context = "Assist the user with troubleshooting network issues."
+
+agent = Agent(
+    name="SupportAgent",
+    prompt=f"{base_instructions}\n\n{additional_context}"
+)
+</CodeBlock>
+
+## Few-Shot Examples
+
+Few-shot examples provide sample interactions to guide agent responses.
+
+### Implementation
+
+<CodeBlock title="Providing Few-Shot Examples" language="python">
+```python
+examples = [
+    {"role": "user", "content": "Hi!"},
+    {"role": "assistant", "content": "Hello! How can I assist you today?"},
+    {"role": "user", "content": "I need help resetting my password."},
+    {"role": "assistant", "content": "Sure, I can help with that. Have you tried using the 'Forgot Password' feature?"}
+]
+
+agent = Agent(name="Helper", examples=examples)
+```
+</CodeBlock>
+
+<Note>
+These examples help the agent understand the expected conversation flow and response style.
+</Note>
+
+## Benefits
+
+<Check>
+
+- **Consistency**: Ensures agents produce consistent and predictable outputs aligned with your desired style.
+
+- **Adaptability**: Tailors agent responses to specific domains, improving user experience.
+
+</Check>

docs_new/advanced-topics/open-source-models-support.mdx

@@ -0,0 +1,79 @@
+---
+title: "Open-Source Models Support"
+description: "Utilize open-source models to provide flexibility and control over your AI agents."
+icon: "code-fork"
+---
+
+While OpenAI models are recommended, Agency Swarm supports open-source models through projects that mimic the Assistants API.
+
+<Info>
+Utilizing open-source models allows for more flexibility and control over your AI agents.
+</Info>
+
+## Supported Projects
+
+<CardGroup>
+
+<Card title="Astra Assistants API" icon="rocket" iconType="solid" href="https://github.com/datastax/astra-assistants-api">
+Best option for running open-source models. Supports Assistants API V2.
+</Card>
+
+<Card title="Open Assistant API" icon="users" iconType="solid" href="https://github.com/MLT-OSS/open-assistant-api">
+Fully local and stable, supports Assistants API V1.
+</Card>
+
+</CardGroup>
+
+## Integration Steps
+
+<Steps>
+
+<Step title="Install Required Packages" icon="download" iconType="solid">
+Use pip to install necessary packages.
+
+<CodeBlock language="bash">
+pip install astra-assistants-api gradio
+</CodeBlock>
+</Step>
+
+<Step title="Set Up API Clients" icon="cogs" iconType="solid">
+Configure your API clients to use the open-source models.
+
+<CodeBlock language="python">
+from openai import OpenAI
+from astra_assistants import patch
+from agency_swarm import set_openai_client
+
+client = patch(OpenAI())
+set_openai_client(client)
+</CodeBlock>
+</Step>
+
+<Step title="Create Agents with Open-Source Models" icon="user-plus" iconType="solid">
+Instantiate your agents using the open-source models.
+
+<CodeBlock language="python">
+ceo = Agent(name="CEO", model='ollama/llama3')
+</CodeBlock>
+</Step>
+
+<Step title="Run the Agency" icon="play" iconType="solid">
+Start your agency with the configured agents.
+
+<CodeBlock language="python">
+agency = Agency([ceo])
+agency.run_demo()
+</CodeBlock>
+</Step>
+
+</Steps>
+
+## Limitations
+
+<Warning>
+Be aware of the limitations when using open-source models.
+</Warning>
+
+- **Function Calling**: Not supported by most open-source models.
+- **Retrieval-Augmented Generation**: Often limited; consider custom implementations.
+- **Code Interpreter**: Not supported in current open-source assistants.

docs_new/advanced-topics/production-readiness.mdx

@@ -0,0 +1,56 @@
+---
+title: "Production Readiness"
+description: "Prepare your agency for production by enhancing reliability, scalability, and security."
+icon: "check-circle-o"
+---
+
+<Info>
+Ensuring your agency is production-ready involves careful planning and implementation of best practices.
+</Info>
+
+## Key Considerations
+
+<AccordionGroup>
+
+<Accordion title="Robust Error Handling" icon="bug" iconType="solid">
+Implement comprehensive error handling within agents and tools to gracefully handle unexpected issues.
+
+<Tip>
+Use try-except blocks and logging to capture and manage exceptions.
+</Tip>
+</Accordion>
+
+<Accordion title="Security Measures" icon="shield-alt" iconType="solid">
+Secure API keys, enforce access controls, and sanitize inputs to protect against vulnerabilities.
+
+<Warning>
+Never hard-code API keys or sensitive information in your code.
+</Warning>
+</Accordion>
+
+<Accordion title="Monitoring and Logging" icon="eye" iconType="solid">
+Use monitoring tools to track performance and detect anomalies. Maintain logs for auditing and debugging.
+
+</Accordion>
+
+<Accordion title="Scalability" icon="arrows-alt" iconType="solid">
+Design for horizontal scaling to handle increased loads efficiently.
+
+<Tip>
+Consider using cloud services that support auto-scaling features.
+</Tip>
+</Accordion>
+
+</AccordionGroup>
+
+## Best Practices
+
+<Check>
+
+- **Testing**: Thoroughly test agents and tools under various conditions, including edge cases.
+
+- **Documentation**: Maintain clear documentation for maintenance and onboarding of new team members.
+
+- **Continuous Integration/Continuous Deployment (CI/CD)**: Set up pipelines for automated testing and deployment to streamline updates.
+
+</Check>

docs_new/api-reference/api-reference.mdx

@@ -0,0 +1,50 @@
+---
+title: "API Reference"
+description: "Gain a deeper understanding of the core classes and methods available in Agency Swarm."
+icon: "book"
+---
+
+## Agents
+
+<Frame caption="Agent Class Documentation">
+::: agency_swarm.agents.agent
+:::
+</Frame>
+
+## Agency
+
+<Frame caption="Agency Class Documentation">
+::: agency_swarm.agency.agency
+:::
+</Frame>
+
+## ToolFactory
+
+<Frame caption="ToolFactory Class Documentation">
+::: agency_swarm.tools.ToolFactory
+:::
+</Frame> 
+
+## Agents (Agent Class Methods)
+
+<Frame caption="Agent Class Methods Documentation">
+```python
+::: agency_swarm.agents.agent.Agent
+```
+</Frame>
+
+## Agency (Agency Class Methods)
+
+<Frame caption="Agency Class Methods Documentation">
+```python
+::: agency_swarm.agency.agency.Agency
+```
+</Frame>
+
+## ToolFactory (ToolFactory Class Methods)
+
+<Frame caption="ToolFactory Class Methods Documentation">
+```python
+::: agency_swarm.tools.ToolFactory
+```
+</Frame>