Skip to content

Commit

Permalink
update ags documentation
Browse files Browse the repository at this point in the history
  • Loading branch information
victordibia committed Jan 11, 2025
1 parent 617bee8 commit 2be8255
Show file tree
Hide file tree
Showing 3 changed files with 88 additions and 39 deletions.
21 changes: 11 additions & 10 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
[![LinkedIn](https://img.shields.io/badge/LinkedIn-Company?style=flat&logo=linkedin&logoColor=white)](https://www.linkedin.com/company/105812540)
[![Discord](https://img.shields.io/badge/discord-chat-green?logo=discord)](https://aka.ms/autogen-discord)
[![Documentation](https://img.shields.io/badge/Documentation-AutoGen-blue?logo=read-the-docs)](https://microsoft.github.io/autogen/)

</div>

# AutoGen
Expand Down Expand Up @@ -74,13 +75,13 @@ asyncio.run(main())

The AutoGen ecosystem provides everything you need to create AI agents, especially multi-agent workflows -- framework, developer tools, and applications.

The *framework* uses a layered and extensible design. Layers have clearly divided responsibilities and build on top of layers below. This design enables you to use the framework at different levels of abstraction, from high-level APIs to low-level components.
The _framework_ uses a layered and extensible design. Layers have clearly divided responsibilities and build on top of layers below. This design enables you to use the framework at different levels of abstraction, from high-level APIs to low-level components.

- [Core API](./python/packages/autogen-core/) implements message passing, event-driven agents, and local and distributed runtime for flexibility and power. It also support cross-language support for .NET and Python.
- [AgentChat API](./python/packages/autogen-agentchat/) implements a simpler but opinionated API rapid for prototyping. This API is built on top of the Core API and is closest to what users of v0.2 are familiar with and supports familiar multi-agent patterns such as two-agent chat or group chats.
- [Extensions API](./python/packages/autogen-ext/) enables first- and third-party extensions continuously expanding framework capabilities. It support specific implementation of LLM clients (e.g., OpenAI, AzureOpenAI), and capabilities such as code execution.

The ecosystem also supports two essential *developer tools*:
The ecosystem also supports two essential _developer tools_:

<div align="center">
<img src="https://media.githubusercontent.com/media/microsoft/autogen/refs/heads/main/python/packages/autogen-studio/docs/ags_screen.png" alt="AutoGen Studio Screenshot" width="500">
Expand All @@ -97,17 +98,17 @@ With AutoGen you get to join and contribute to a thriving ecosystem. We host wee

<div align="center">

| | [![Python](https://img.shields.io/badge/AutoGen-Python-blue?logo=python&logoColor=white)](./python) | [![.NET](https://img.shields.io/badge/AutoGen-.NET-green?logo=.net&logoColor=white)](./dotnet) | [![Studio](https://img.shields.io/badge/AutoGen-Studio-purple?logo=visual-studio&logoColor=white)](./python/packages/autogen-studio) |
|----------------------|--------------------------------------------------------------------------------------------|-------------------|-------------------|
| Installation | [![Installation](https://img.shields.io/badge/Install-blue)](https://microsoft.github.io/autogen/dev/user-guide/agentchat-user-guide/installation.html) | * | [![Install](https://img.shields.io/badge/Install-purple)](https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/installation.html) |
| Quickstart | [![Quickstart](https://img.shields.io/badge/Quickstart-blue)](https://microsoft.github.io/autogen/dev/user-guide/agentchat-user-guide/quickstart.html#) | * | * |
| Tutorial | [![Tutorial](https://img.shields.io/badge/Tutorial-blue)](https://microsoft.github.io/autogen/dev/user-guide/agentchat-user-guide/tutorial/models.html) | *| * |
| API Reference | [![API](https://img.shields.io/badge/Docs-blue)](https://microsoft.github.io/autogen/dev/reference/index.html#) | * | [![API](https://img.shields.io/badge/Docs-purple)](https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/usage.html) |
| Packages | [![PyPi autogen-core](https://img.shields.io/badge/PyPi-autogen--core-blue?logo=pypi)](https://pypi.org/project/autogen-core/) <br> [![PyPi autogen-agentchat](https://img.shields.io/badge/PyPi-autogen--agentchat-blue?logo=pypi)](https://pypi.org/project/autogen-agentchat/) <br> [![PyPi autogen-ext](https://img.shields.io/badge/PyPi-autogen--ext-blue?logo=pypi)](https://pypi.org/project/autogen-ext/) | * | [![PyPi autogenstudio](https://img.shields.io/badge/PyPi-autogenstudio-purple?logo=pypi)](https://pypi.org/project/autogenstudio/) |
| | [![Python](https://img.shields.io/badge/AutoGen-Python-blue?logo=python&logoColor=white)](./python) | [![.NET](https://img.shields.io/badge/AutoGen-.NET-green?logo=.net&logoColor=white)](./dotnet) | [![Studio](https://img.shields.io/badge/AutoGen-Studio-purple?logo=visual-studio&logoColor=white)](./python/packages/autogen-studio) |
| ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Installation | [![Installation](https://img.shields.io/badge/Install-blue)](https://microsoft.github.io/autogen/dev/user-guide/agentchat-user-guide/installation.html) | \* | [![Install](https://img.shields.io/badge/Install-purple)](https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/installation.html) |
| Quickstart | [![Quickstart](https://img.shields.io/badge/Quickstart-blue)](https://microsoft.github.io/autogen/dev/user-guide/agentchat-user-guide/quickstart.html#) | \* | [![Usage](https://img.shields.io/badge/Quickstart-blue)](https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/usage.html#) |
| Tutorial | [![Tutorial](https://img.shields.io/badge/Tutorial-blue)](https://microsoft.github.io/autogen/dev/user-guide/agentchat-user-guide/tutorial/models.html) | \* | [![Usage](https://img.shields.io/badge/Quickstart-blue)](https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/usage.html#) |
| API Reference | [![API](https://img.shields.io/badge/Docs-blue)](https://microsoft.github.io/autogen/dev/reference/index.html#) | \* | [![API](https://img.shields.io/badge/Docs-purple)](https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/usage.html) |
| Packages | [![PyPi autogen-core](https://img.shields.io/badge/PyPi-autogen--core-blue?logo=pypi)](https://pypi.org/project/autogen-core/) <br> [![PyPi autogen-agentchat](https://img.shields.io/badge/PyPi-autogen--agentchat-blue?logo=pypi)](https://pypi.org/project/autogen-agentchat/) <br> [![PyPi autogen-ext](https://img.shields.io/badge/PyPi-autogen--ext-blue?logo=pypi)](https://pypi.org/project/autogen-ext/) | \* | [![PyPi autogenstudio](https://img.shields.io/badge/PyPi-autogenstudio-purple?logo=pypi)](https://pypi.org/project/autogenstudio/) |

</div>

**Releasing soon*
\*_Releasing soon_

Interested in contributing? See [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines on how to get started. We welcome contributions of all kinds, including bug fixes, new features, and documentation improvements. Join our community and help us make AutoGen better!

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -9,9 +9,9 @@ myst:

There are two ways to install AutoGen Studio - from PyPi or from source. We **recommend installing from PyPi** unless you plan to modify the source code.

## 1. Create a Virtual Environment (optional)
## Create a Virtual Environment (Recommended)

When installing AgentChat locally, we recommend using a virtual environment for the installation. This will ensure that the dependencies for AgentChat are isolated from the rest of your system.
We recommend using a virtual environment as this will ensure that the dependencies for AutoGen Studio are isolated from the rest of your system.

``````{tab-set}
Expand Down Expand Up @@ -59,7 +59,7 @@ conda deactivate

## Install Using pip (Recommended)

We recommend using a virtual environment (e.g., conda) to avoid conflicts with existing Python packages. With Python 3.10 or newer active in your virtual environment, use pip to install AutoGen Studio:
You can install AutoGen Studio using pip, the Python package manager.

```bash
pip install -U autogenstudio
Expand Down Expand Up @@ -110,7 +110,7 @@ AutoGen Studio also takes several parameters to customize the application:
- `--host <host>` argument to specify the host address. By default, it is set to `localhost`.
- `--appdir <appdir>` argument to specify the directory where the app files (e.g., database and generated user files) are stored. By default, it is set to the a `.autogenstudio` directory in the user's home directory.
- `--port <port>` argument to specify the port number. By default, it is set to `8080`.
- `--upgrade-database` argument to upgrade the database schema (assuming there are changes in the version you are installing). By default, it is set to `False`.
- `--upgrade-database` argument to force-upgrade it's internal database schema (assuming there are changes in the version you are installing). By default, it is set to `False`.
- `--reload` argument to enable auto-reloading of the server when changes are made to the code. By default, it is set to `False`.
- `--database-uri` argument to specify the database URI. Example values include `sqlite:///database.sqlite` for SQLite and `postgresql+psycopg://user:password@localhost/dbname` for PostgreSQL. If this is not specified, the database URI defaults to a `autogen.db` file in the `--appdir` directory.

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -7,55 +7,103 @@ myst:

# Usage

The expected usage behavior is that developers use the provided Team Builder interface to to define teams - create agents, attach tools and models to agents, and define termination conditions. Once the team is defined, users can run the team in the Playground to interact with the team to accomplish tasks.
AutoGen Studio provides a Team Builder interface where developers can define multiple components and behaviors. Users can create teams, add agents to teams, attach tools and models to agents, and define team termination conditions.
After defining a team, users can test it in the Playground view to accomplish various tasks through direct interaction.

![AutoGen Studio](https://media.githubusercontent.com/media/microsoft/autogen/refs/heads/main/python/packages/autogen-studio/docs/ags_screen.png)

## Declarative Specification of Componenents

AutoGen Studio uses a declarative specification system to build its GUI components. At runtime, the AGS API loads these specifications into AutoGen AgentChat objects to address tasks.

Here's an example of a declarative team specification:

```json
{
"version": "1.0.0",
"component_type": "team",
"name": "sample_team",
"participants": [
{
"component_type": "agent",
"name": "assistant_agent",
"agent_type": "AssistantAgent",
"system_message": "You are a helpful assistant. Solve tasks carefully. When done respond with TERMINATE",
"model_client": {
"component_type": "model",
"model": "gpt-4o-2024-08-06",
"model_type": "OpenAIChatCompletionClient"
},
"tools": []
}
],
"team_type": "RoundRobinGroupChat",
"termination_condition": {
"component_type": "termination",
"termination_type": "MaxMessageTermination",
"max_messages": 3
}
}
```

This example shows a team with a single agent, using the `RoundRobinGroupChat` type and a `MaxMessageTermination` condition limited to 3 messages.

```{note}
Work is currently in progress to make the entire AgentChat API [declarative](/user-guide/core-user-guide/framework/component-config.html). This will allow all agentchat components to be `dumped` into the same declarative specification format used by AGS.
```

## Building an Agent Team

<div style="padding:58.13% 0 0 0;position:relative; border-radius:5px; border-bottom:10px"><iframe src="https://player.vimeo.com/video/1043133833?badge=0&amp;autopause=0&amp;player_id=0&amp;app_id=58479" frameborder="0" allow="autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media" style="position:absolute;top:0;left:0;width:100%;height:100%;" title="AutoGen Studio v0.4x - Drag and Drop Interface"></iframe></div><script src="https://player.vimeo.com/api/player.js"></script>

<br/>

AutoGen Studio is tied very closely with all of the component abstractions provided by AutoGen AgentChat. This includes - {py:class}`~autogen_agentchat.teams`, {py:class}`~autogen_agentchat.agents`, {py:class}`~autogen_core.models`, {py:class}`~autogen_core.tools`, termination {py:class}`~autogen_agentchat.conditions`.
AutoGen Studio integrates closely with all component abstractions provided by AutoGen AgentChat, including {py:class}`~autogen_agentchat.teams`, {py:class}`~autogen_agentchat.agents`, {py:class}`~autogen_core.models`, {py:class}`~autogen_core.tools`, and termination {py:class}`~autogen_agentchat.conditions`.

The Team Builder interface allows users to define components through either declarative specification or drag-and-drop functionality:

Team Builder Operations:

- Create a new team
- Edit Team JSON directly (toggle visual builder mode off) or
- Use the visual builder, drag-and-drop components from the library:
- Teams: Add agents and termination conditions
- Agents: Add models and tools
- Save team configurations

Users can define these components in the Team Builder interface either via a declarative specification or by dragging and dropping components from a component library.
Component Library Management:

- Create new galleries via Gallery -> New Gallery
- Edit gallery JSON as needed
- Set a **default** gallery (click pin icon in sidebar) to make components available in Team Builder

## Interactively Running Teams

AutoGen Studio Playground allows users to interactively test teams on tasks and review resulting artifacts (such as images, code, and text).
The AutoGen Studio Playground enables users to:

Users can also review the “inner monologue” of team as they address tasks, and view profiling information such as costs associated with the run (such as number of turns, number of tokens etc.), and agent actions (such as whether tools were called and the outcomes of code execution).
- Test teams on specific tasks
- Review generated artifacts (images, code, text)
- Monitor team "inner monologue" during task execution
- View performance metrics (turn count, token usage)
- Track agent actions (tool usage, code execution results)

## Importing and Reusing Team Configurations

AutoGen Studio provides a Gallery view which provides a built-in default gallery. A Gallery is simply is a collection of components - teams, agents, models tools etc. Furthermore, users can import components from 3rd party community sources either by providing a URL to a JSON Gallery spec or pasting in the gallery JSON. This allows users to reuse and share team configurations with others.
AutoGen Studio's Gallery view offers a default component collection and supports importing external configurations:

- Gallery -> New Gallery -> Import
- Set as default gallery (in side bar, by clicking pin icon)
- Reuse components in Team Builder. Team Builder -> Sidebar -> From Gallery
- Create/Import galleries through Gallery -> New Gallery -> Import
- Set default galleries via sidebar pin icon
- Access components in Team Builder through Sidebar -> From Gallery

### Using AutoGen Studio Teams in a Python Application
### Python Integration

An exported team can be easily integrated into any Python application using the `TeamManager` class with just two lines of code. Underneath, the `TeamManager` rehydrates the team specification into AutoGen AgentChat agents that are subsequently used to address tasks.
Team configurations can be integrated into Python applications using the `TeamManager` class:

```python

from autogenstudio.teammanager import TeamManager

tm = TeamManager()
result_stream = tm.run(task="What is the weather in New York?", team_config="team.json") # or wm.run_stream(..)

```

To export a team configuration, click on the export button in the Team Builder interface. This will generate a JSON file that can be used to rehydrate the team in a Python application.

<!-- ### Deploying AutoGen Studio Teams as APIs
The team can be launched as an API endpoint from the command line using the autogenstudio commandline tool.
```bash
autogenstudio serve --team=team.json --port=5000
result_stream = tm.run(task="What is the weather in New York?", team_config="team.json") # or wm.run_stream(..)
```

Similarly, the team launch command above can be wrapped into a Dockerfile that can be deployed on cloud services like Azure Container Apps or Azure Web Apps. -->
To export team configurations, use the export button in Team Builder to generate a JSON file for Python application use.

0 comments on commit 2be8255

Please sign in to comment.