Skip to content

Commit

Permalink
Docs adjustments
Browse files Browse the repository at this point in the history
  • Loading branch information
VRSEN committed Feb 19, 2025
1 parent d831a9a commit e08b66c
Show file tree
Hide file tree
Showing 3 changed files with 16 additions and 24 deletions.
5 changes: 5 additions & 0 deletions docs/core-framework/tools/custom-tools/step-by-step-guide.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -134,3 +134,8 @@ if __name__ == "__main__":
calc = Calculator(expression="2 + 2 * 3")
print(calc.run()) # Output should be '8'
```

## Next Steps

- Checkout [Best Practices & Tips](/core-framework/tools/custom-tools/best-practices)
- Learn why [PyDantic is all you need](/core-framework/tools/custom-tools/pydantic-is-all-you-need)
29 changes: 8 additions & 21 deletions docs/faq.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -26,11 +26,11 @@ load_dotenv()


<Accordion title="What's the difference between using .cursorrules (with Cursor IDE) and 'agency-swarm genesis'?" icon="scale-unbalanced">
There are two ways to create agents:
There are two ways to create agents with AI:

1. [**Genesis Agency**:](/welcome/getting-started/genesis-agency) A simple command-line tool that helps you create basic agents quickly. Great for getting started or simple use cases. Just run `agency-swarm genesis` and follow the prompts.
1. [**Genesis Agency**:](/welcome/getting-started/genesis-agency) A simple command-line tool that helps you create basic agent structures. Great for getting started or simple use cases. Just run `agency-swarm genesis` and follow the prompts.

2. [**Cursor AI Code Editor**](/welcome/getting-started/cursor-ide): Use the `.cursorrules` file in Cursor IDE to create agents. This is the best option for both beginners and experienced developers since it provides a more streamlined development experience.
2. [**Cursor AI Code Editor**](/welcome/getting-started/cursor-ide): Use the `.cursorrules` file in Cursor IDE to create agents. This is the best option for both beginners and experienced developers since it gives you more control over the agent creation process.
</Accordion>


Expand All @@ -40,7 +40,7 @@ Yes—you can use open source models for simple, non–mission-critical tasks (u


<Accordion title="How do I save and continue conversations?" icon="messages">
To persist threads between application restarts, implement thread callbacks that save and load thread IDs. For example, define your callback functions:
To persist threads between application restarts, implement thread callbacks that save and load thread IDs from a local file. For example, define your callback functions:
```python
import os
import json
Expand All @@ -58,6 +58,8 @@ def save_threads(new_threads, chat_id):

Then, pass these callbacks during your agency initialization to resume conversations:
```python
from agency_swarm.agency.genesis import GenesisAgency

agency = GenesisAgency(
...
threads_callbacks={
Expand All @@ -67,27 +69,12 @@ agency = GenesisAgency(
)
```

This setup preserves your conversation context between runs. For more details, refer to our [Deployment to Production](/additional-features/deployment-to-production) guide.
This setup preserves your conversation context between runs.
</Accordion>


<Accordion title="How do I manage multiple users with Agency Swarm?" icon="users">
To support multiple users/chats, instantiate a separate agency per user. Ensure to check out our [Deployment to Production](/additional-features/deployment-to-production) guide for more information.
</Accordion>


<Accordion title="What is the agency_chart parameter?" icon="diagram-project">
The `agency_chart` defines your agents and their communication flows. For example:

```python
agency_chart = [
ceo, # Main user-facing agent
[ceo, developer], # CEO can delegate tasks to the Developer
[ceo, analyst] # CEO can consult with the Analyst
]
```

This structure controls which agents can talk to each other. For more details, refer to our [Communication Flows](/core-framework/agencies/communication-flows) guide.
To support multiple users/chats, you need to load and save thread IDs in your database accordingly. Each chat/user should have unique thread IDs. Ensure to check out our [Deployment to Production](/additional-features/deployment-to-production) guide for more information.
</Accordion>


Expand Down
6 changes: 3 additions & 3 deletions docs/welcome/installation.mdx
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
title: "Installation"
description: "Install Agency in just 2 simple steps."
description: "Install Agency Swarm in just 2 simple steps."
icon: "box"
---

Expand Down Expand Up @@ -34,14 +34,14 @@ icon: "box"
```

</Accordion>
<Accordion title="Step 2: Install the agency package" defaultOpen={true}>
<Accordion title="Step 2: Install the agency swarm package" defaultOpen={true}>

Simply run the following command:

<Note>Make sure you are in the virtual environment before installing the package.</Note>

```bash
pip install agency
pip install agency-swarm
```

</Accordion>
Expand Down

0 comments on commit e08b66c

Please sign in to comment.