mirror of https://github.com/microsoft/autogen.git
Change references from agenext to autogen (#610)
This commit is contained in:
Jack Gerrits
GitHub
parent
8ea09318ce
commit
93e7127f1f
|
|
@ -8,7 +8,7 @@ dynamic = ["version"]
|
|||
authors = [
|
||||
{ name="Adam Fourney", email="adamfo@microsoft.com" },
|
||||
]
|
||||
description = "AGNext Benchmarking Tools"
|
||||
description = "AutoGen Benchmarking Tools"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.8, <3.13"
|
||||
classifiers = [
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
FROM python:3.11
|
||||
MAINTAINER AGNext
|
||||
MAINTAINER AutoGen
|
||||
|
||||
# Install packages
|
||||
# ffmpeg and exiftool are needed for mdconvert
|
||||
|
|
|
|||
|
|
@ -486,7 +486,7 @@ echo RUN.SH COMPLETE !#!#
|
|||
|
||||
if agnext_repo_base is None:
|
||||
raise ValueError(
|
||||
"Could not find AGNext repo base. Please set the environment variable AGNEXT_REPO_BASE to the correct value."
|
||||
"Could not find AutoGen repo base. Please set the environment variable AGNEXT_REPO_BASE to the correct value."
|
||||
)
|
||||
|
||||
agnext_repo_base = os.path.join(agnext_repo_base, "python")
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
## Building the AGNext Documentation
|
||||
## Building the AutoGen Documentation
|
||||
|
||||
AGNext documentation is based on the sphinx documentation system and uses the myst-parser to render markdown files. It uses the [pydata-sphinx-theme](https://pydata-sphinx-theme.readthedocs.io/en/latest/) to style the documentation.
|
||||
AutoGen documentation is based on the sphinx documentation system and uses the myst-parser to render markdown files. It uses the [pydata-sphinx-theme](https://pydata-sphinx-theme.readthedocs.io/en/latest/) to style the documentation.
|
||||
|
||||
### Prerequisites
|
||||
|
||||
|
|
|
|||
|
|
@ -63,7 +63,7 @@ myst_enable_extensions = [
|
|||
# -- Options for HTML output -------------------------------------------------
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
|
||||
|
||||
html_title = "AGNext"
|
||||
html_title = "AutoGen"
|
||||
|
||||
html_theme = "pydata_sphinx_theme"
|
||||
html_static_path = ["_static"]
|
||||
|
|
|
|||
|
|
@ -2,16 +2,16 @@
|
|||
myst:
|
||||
html_meta:
|
||||
"description lang=en": |
|
||||
Top-level documentation for AGNext, a framework for building multi-agent applications with AI agents.
|
||||
Top-level documentation for AutoGen, a framework for building multi-agent applications with AI agents.
|
||||
html_theme.sidebar_secondary.remove: false
|
||||
---
|
||||
|
||||
# AGNext
|
||||
# AutoGen
|
||||
|
||||
AGNext is a OSS framework for developing intelligent applications using AI Agents patterns.
|
||||
AutoGen is an OSS framework for developing intelligent applications using AI Agents patterns.
|
||||
It offers an easy way to quickly build event-driven, distributed, scalable, resilient AI agent systems. Agents are developed by using the [Actor model](https://en.wikipedia.org/wiki/Actor_model). You can build and run your agent system locally and easily move to a distributed system in the cloud when you are ready.
|
||||
|
||||
Key features of AGNext are summarized below.
|
||||
Key features of AutoGen are summarized below.
|
||||
|
||||
```{gallery-grid}
|
||||
:grid-columns: 1 2 2 3
|
||||
|
|
@ -31,7 +31,7 @@ Key features of AGNext are summarized below.
|
|||
```
|
||||
|
||||
<!--
|
||||
Key features of AGNext include:
|
||||
Key features of AutoGen include:
|
||||
|
||||
- Asynchronous messaging: Agents communicate with each other through asynchronous messages, enabling event-driven and request/response communication models.
|
||||
- Scalable & Distributed: Enable complex scenarios with networks of agents across org boundaries
|
||||
|
|
@ -40,7 +40,7 @@ Key features of AGNext include:
|
|||
- Observable, traceable & debuggable -->
|
||||
|
||||
```{seealso}
|
||||
To start quickly, read the [Quick Start](user-guide/guides/quickstart) guide and follow the tutorial sections. To learn about the core concepts of AGNext, begin with [Agent and Multi-Agent Application](user-guide/core-concepts/agent-and-multi-agent-application).
|
||||
To start quickly, read the [Quick Start](user-guide/guides/quickstart) guide and follow the tutorial sections. To learn about the core concepts of AutoGen, begin with [Agent and Multi-Agent Application](user-guide/core-concepts/agent-and-multi-agent-application).
|
||||
```
|
||||
|
||||
```{toctree}
|
||||
|
|
@ -52,7 +52,7 @@ user-guide/index
|
|||
|
||||
<!-- ## Community
|
||||
|
||||
Information about the community that leads, supports, and develops AGNext.
|
||||
Information about the community that leads, supports, and develops AutoGen.
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
|
|
@ -72,8 +72,3 @@ packages/index
|
|||
reference/index
|
||||
```
|
||||
|
||||
<!-- ````{toctree}
|
||||
:hidden:
|
||||
|
||||
Changelog <https://github.com/your-org/agnext/releases>
|
||||
``` -->
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
myst:
|
||||
html_meta:
|
||||
"description lang=en": |
|
||||
AGNext packages provide a set of functionality for building multi-agent applications with AI agents.
|
||||
AutoGen packages provide a set of functionality for building multi-agent applications with AI agents.
|
||||
---
|
||||
|
||||
<style>
|
||||
|
|
@ -23,7 +23,7 @@ myst:
|
|||
:::{card} {fas}`cube;pst-color-primary` AutoGen Core
|
||||
:class-title: card-title
|
||||
|
||||
Implements the core functionality of the AGNext framework, providing basic building blocks for creating multi-agent systems.
|
||||
Implements the core functionality of the AutoGen framework, providing basic building blocks for creating multi-agent systems.
|
||||
|
||||
```sh
|
||||
pip install autogen-core
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
myst:
|
||||
html_meta:
|
||||
"description lang=en": |
|
||||
AGNext is a community-driven project. Learn how to get involved, contribute, and connect with the community.
|
||||
AutoGen is a community-driven project. Learn how to get involved, contribute, and connect with the community.
|
||||
---
|
||||
|
||||
<style>
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@
|
|||
"and [Azure OpenAI Assistant](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/assistant)\n",
|
||||
"are server-side APIs for building\n",
|
||||
"agents.\n",
|
||||
"They can be used to build agents in AGNext. This cookbook demonstrates how to\n",
|
||||
"They can be used to build agents in AutoGen. This cookbook demonstrates how to\n",
|
||||
"to use OpenAI Assistant to create an agent that can run code and Q&A over document.\n",
|
||||
"\n",
|
||||
"## Message Protocol\n",
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Application Stack
|
||||
|
||||
AGNext is designed to be an unopinionated framework that can be used to build
|
||||
AutoGen core is designed to be an unopinionated framework that can be used to build
|
||||
a wide variety of multi-agent applications. It is not tied to any specific
|
||||
agent abstraction or multi-agent pattern.
|
||||
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
"source": [
|
||||
"# Agent and Agent Runtime\n",
|
||||
"\n",
|
||||
"In this and the following section, we focus on the core concepts of AGNext:\n",
|
||||
"In this and the following section, we focus on the core concepts of AutoGen:\n",
|
||||
"agents, agent runtime, messages, and communication.\n",
|
||||
"You will not find any AI models or tools here, just the foundational\n",
|
||||
"building blocks for building multi-agent applications."
|
||||
|
|
@ -16,12 +16,12 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"An agent in AGNext is an entity defined by the base class {py:class}`autogen_core.base.BaseAgent`.\n",
|
||||
"An agent in AutoGen is an entity defined by the base class {py:class}`autogen_core.base.BaseAgent`.\n",
|
||||
"It has a unique identifier of the type {py:class}`autogen_core.base.AgentId`,\n",
|
||||
"a metadata dictionary of the type {py:class}`autogen_core.base.AgentMetadata`,\n",
|
||||
"and method for handling messages {py:meth}`autogen_core.base.BaseAgent.on_message`.\n",
|
||||
"\n",
|
||||
"An agent runtime is the execution environment for agents in AGNext.\n",
|
||||
"An agent runtime is the execution environment for agents in AutoGen.\n",
|
||||
"Similar to the runtime environment of a programming language,\n",
|
||||
"an agent runtime provides the necessary infrastructure to facilitate communication\n",
|
||||
"between agents, manage agent lifecycles, enforce security boundaries, and support monitoring and\n",
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Logging
|
||||
|
||||
AGNext uses Python's built-in [`logging`](https://docs.python.org/3/library/logging.html) module.
|
||||
AutoGen uses Python's built-in [`logging`](https://docs.python.org/3/library/logging.html) module.
|
||||
|
||||
There are two kinds of logging:
|
||||
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
"source": [
|
||||
"# Message and Communication\n",
|
||||
"\n",
|
||||
"An agent in AGNext can react to, send, and publish messages,\n",
|
||||
"An agent in AutoGen core can react to, send, and publish messages,\n",
|
||||
"and messages are the only means through which agents can communicate\n",
|
||||
"with each other."
|
||||
]
|
||||
|
|
@ -263,7 +263,7 @@
|
|||
"source": [
|
||||
"## Direct Messaging\n",
|
||||
"\n",
|
||||
"There are two types of communication in AGNext:\n",
|
||||
"There are two types of communication in AutoGen core:\n",
|
||||
"\n",
|
||||
"- **Direct Messaging**: sends a direct message to another agent.\n",
|
||||
"- **Broadcast**: publishes a message to a topic.\n",
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
"source": [
|
||||
"# Model Clients\n",
|
||||
"\n",
|
||||
"AGNext provides the {py:mod}`autogen_core.components.models` module with a suite of built-in\n",
|
||||
"AutoGen provides the {py:mod}`autogen_core.components.models` module with a suite of built-in\n",
|
||||
"model clients for using ChatCompletion API.\n",
|
||||
"All model clients implement the {py:class}`~autogen_core.components.models.ChatCompletionClient` protocol class."
|
||||
]
|
||||
|
|
|
|||
|
|
@ -13,6 +13,6 @@ For example, the [tool-equiped agent](./tools.ipynb#tool-equipped-agent) in
|
|||
the previous section employs a design pattern called ReAct,
|
||||
which involves an agent interacting with tools.
|
||||
|
||||
You can implement any multi-agent design pattern using AGNext agents.
|
||||
You can implement any multi-agent design pattern using AutoGen agents.
|
||||
In the next two sections, we will discuss two common design patterns:
|
||||
group chat for task decomposition, and reflection for robustness.
|
||||
|
|
@ -381,7 +381,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"AGNext also supports distributed agent runtime, which can host agents running on\n",
|
||||
"AutoGen also supports a distributed agent runtime, which can host agents running on\n",
|
||||
"different processes or machines, with different identities, languages and dependencies.\n",
|
||||
"\n",
|
||||
"To learn how to use agent runtime, communication, message handling, and subscription, please continue\n",
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@
|
|||
"For example, given a task to write code, the first LLM can generate a code snippet,\n",
|
||||
"and the second LLM can generate a critique of the code snippet.\n",
|
||||
"\n",
|
||||
"In the context of AGNext and agents, reflection can be implemented as a pair\n",
|
||||
"In the context of AutoGen and agents, reflection can be implemented as a pair\n",
|
||||
"of agents, where the first agent generates a message and the second agent\n",
|
||||
"generates a response to the message. The two agents continue to interact\n",
|
||||
"until they reach a stopping condition, such as a maximum number of iterations\n",
|
||||
|
|
@ -22,7 +22,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's implement a simple reflection design pattern using AGNext agents.\n",
|
||||
"Let's implement a simple reflection design pattern using AutoGen agents.\n",
|
||||
"There will be two agents: a coder agent and a reviewer agent, the coder agent\n",
|
||||
"will generate a code snippet, and the reviewer agent will generate a critique\n",
|
||||
"of the code snippet.\n",
|
||||
|
|
@ -259,7 +259,7 @@
|
|||
"- It stores message histories for different `CodeWritingTask` in a dictionary,\n",
|
||||
"so each task has its own history.\n",
|
||||
"- When making an LLM inference request using its model client, it transforms\n",
|
||||
"the message history into a list of {py:class}`agnext.components.models.LLMMessage` objects\n",
|
||||
"the message history into a list of {py:class}`autogen_core.components.models.LLMMessage` objects\n",
|
||||
"to pass to the model client.\n",
|
||||
"\n",
|
||||
"The reviewer agent subscribes to the `CodeReviewTask` message and publishes the `CodeReviewResult` message."
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Open Telemetry
|
||||
|
||||
AGNext has native support for [open telemetry](https://opentelemetry.io/). This allows you to collect telemetry data from your application and send it to a telemetry backend of your choosing.
|
||||
AutoGen has native support for [open telemetry](https://opentelemetry.io/). This allows you to collect telemetry data from your application and send it to a telemetry backend of your choosing.
|
||||
|
||||
These are the components that are currently instrumented:
|
||||
- Runtime (Single Threaded Agent Runtime, Worker Agent Runtime)
|
||||
|
|
@ -12,7 +12,7 @@ To instrument your application, you will need an sdk and an exporter. You may al
|
|||
pip install opentelemetry-sdk
|
||||
```
|
||||
|
||||
Depending on your open telemetry collector, you can use grpc or http to export your telemetry.
|
||||
Depending on your open telemetry collector, you can use grpc or http to export your telemetry.
|
||||
|
||||
```bash
|
||||
# Pick one of the following
|
||||
|
|
@ -35,7 +35,7 @@ def configure_oltp_tracing(endpoint: str = None) -> trace.TracerProvider:
|
|||
processor = BatchSpanProcessor(OTLPSpanExporter())
|
||||
tracer_provider.add_span_processor(processor)
|
||||
trace.set_tracer_provider(tracer_provider)
|
||||
|
||||
|
||||
return tracer_provider
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@
|
|||
"In the context of AI agents, tools are designed to be executed by agents in\n",
|
||||
"response to model-generated function calls.\n",
|
||||
"\n",
|
||||
"AGNext provides the {py:mod}`autogen_core.components.tools` module with a suite of built-in\n",
|
||||
"AutoGen provides the {py:mod}`autogen_core.components.tools` module with a suite of built-in\n",
|
||||
"tools and utilities for creating and running custom tools."
|
||||
]
|
||||
},
|
||||
|
|
|
|||
|
|
@ -2,12 +2,12 @@
|
|||
myst:
|
||||
html_meta:
|
||||
"description lang=en": |
|
||||
User Guide for AGNext, a framework for building multi-agent applications with AI agents.
|
||||
User Guide for AutoGen, a framework for building multi-agent applications with AI agents.
|
||||
---
|
||||
|
||||
# User Guide
|
||||
|
||||
AGNext is a flexible framework for building multi-agent systems. Begin with the [installation](guides/installation.md) guide to set up the framework on your machine. Then, follow the [quickstart](guides/quickstart) guide to get started with building your first multi-agent application.
|
||||
AutoGen is a flexible framework for building multi-agent systems. Begin with the [installation](guides/installation.md) guide to set up the framework on your machine. Then, follow the [quickstart](guides/quickstart) guide to get started with building your first multi-agent application.
|
||||
|
||||
```{danger}
|
||||
This project and documentation is a work in progress. If you have any questions or need help, please reach out to us on GitHub.
|
||||
|
|
|
|||
|
|
@ -1,18 +1,18 @@
|
|||
# Examples
|
||||
|
||||
This directory contains examples and demos of how to use AGNext.
|
||||
This directory contains examples and demos of how to use AutoGen core.
|
||||
|
||||
- `common`: Contains common implementations and utilities used by the examples.
|
||||
- `core`: Contains examples that illustrate the core concepts of AGNext.
|
||||
- `tool-use`: Contains examples that illustrate tool use in AGNext.
|
||||
- `patterns`: Contains examples that illustrate how multi-agent patterns can be implemented in AGNext.
|
||||
- `demos`: Contains interactive demos that showcase applications that can be built using AGNext.
|
||||
- `core`: Contains examples that illustrate the core concepts of AutoGen core.
|
||||
- `tool-use`: Contains examples that illustrate tool use in AutoGen core.
|
||||
- `patterns`: Contains examples that illustrate how multi-agent patterns can be implemented in AutoGen core.
|
||||
- `demos`: Contains interactive demos that showcase applications that can be built using AutoGen core.
|
||||
|
||||
See [Running the examples](#running-the-examples) for instructions on how to run the examples.
|
||||
|
||||
## Core examples
|
||||
|
||||
We provide examples to illustrate the core concepts of AGNext: agents, runtime, and message passing.
|
||||
We provide examples to illustrate the core concepts of AutoGen core: agents, runtime, and message passing.
|
||||
|
||||
- [`one_agent_direct.py`](core/one_agent_direct.py): A simple example of how to create a single agent powered by ChatCompletion model client. Communicate with the agent using direct communication.
|
||||
- [`inner_outer_direct.py`](core/inner_outer_direct.py): A simple example of how to create an agent that calls an inner agent using direct communication.
|
||||
|
|
@ -20,7 +20,7 @@ We provide examples to illustrate the core concepts of AGNext: agents, runtime,
|
|||
|
||||
## Tool use examples
|
||||
|
||||
We provide examples to illustrate how to use tools in AGNext:
|
||||
We provide examples to illustrate how to use tools in AutoGen core:
|
||||
|
||||
- [`coding_direct.py`](tool-use/coding_direct.py): a code execution example with one agent that calls and executes tools to demonstrate tool use and reflection on tool use. This example uses direct communication.
|
||||
- [`coding_pub_sub.py`](tool-use/coding_pub_sub.py): a code execution example with two agents, one for calling tool and one for executing the tool, to demonstrate tool use and reflection on tool use. This example uses broadcast communication.
|
||||
|
|
@ -29,7 +29,7 @@ We provide examples to illustrate how to use tools in AGNext:
|
|||
|
||||
## Pattern examples
|
||||
|
||||
We provide examples to illustrate how multi-agent patterns can be implemented in AGNext:
|
||||
We provide examples to illustrate how multi-agent patterns can be implemented in AutoGen core:
|
||||
|
||||
- [`coder_executor.py`](patterns/coder_executor.py): An example of how to create a coder-executor reflection pattern. This example creates a plot of stock prices using the Yahoo Finance API.
|
||||
- [`coder_reviewer.py`](patterns/coder_reviewer.py): An example of how to create a coder-reviewer reflection pattern.
|
||||
|
|
@ -39,7 +39,7 @@ We provide examples to illustrate how multi-agent patterns can be implemented in
|
|||
|
||||
## Demos
|
||||
|
||||
We provide interactive demos that showcase applications that can be built using AGNext:
|
||||
We provide interactive demos that showcase applications that can be built using AutoGen core:
|
||||
|
||||
- [`assistant.py`](demos/assistant.py): a demonstration of how to use the OpenAI Assistant API to create
|
||||
a ChatGPT agent.
|
||||
|
|
@ -63,7 +63,7 @@ We provide examples on how to integrate other agents with the platform:
|
|||
|
||||
### Prerequisites
|
||||
|
||||
First, you need a shell with AGNext and required dependencies installed.
|
||||
First, you need a shell with AutoGen core and required dependencies installed.
|
||||
|
||||
### Using Azure OpenAI API
|
||||
|
||||
|
|
@ -75,7 +75,7 @@ export AZURE_OPENAI_API_ENDPOINT=your_azure_openai_endpoint
|
|||
export AZURE_OPENAI_API_VERSION=your_azure_openai_api_version
|
||||
```
|
||||
|
||||
By default, we use Azure Active Directory (AAD) for authentication.
|
||||
By default, we use Azure Active Directory (AAD) for authentication.
|
||||
You need to run `az login` first to authenticate with Azure.
|
||||
You can also
|
||||
use API key authentication by setting the following environment variables:
|
||||
|
|
|
|||
|
|
@ -318,7 +318,7 @@ if __name__ == "__main__":
|
|||
# import logging
|
||||
|
||||
# logging.basicConfig(level=logging.WARNING)
|
||||
# logging.getLogger("agnext").setLevel(logging.DEBUG)
|
||||
# logging.getLogger("autogen_core").setLevel(logging.DEBUG)
|
||||
|
||||
# if os.path.exists("state.json"):
|
||||
# os.remove("state.json")
|
||||
|
|
|
|||
|
|
@ -160,7 +160,7 @@ Team One agents can emit several log events that can be consumed by a log handle
|
|||
- OrchestrationEvent : emitted by a an [Orchestrator](src/team_one/agents/base_orchestrator.py) agent.
|
||||
- WebSurferEvent : emitted by a [WebSurfer](src/team_one/agents/multimodal_web_surfer/multimodal_web_surfer.py) agent.
|
||||
|
||||
In addition, developers can also handle and process logs generated from the AGNext core library (e.g., LLMCallEvent etc). See the example log handler in [utils.py](src/team_one/utils.py) on how this can be implemented. By default, the logs are written to a file named `log.jsonl` which can be configured as a parameter to the defined log handler. These logs can be parsed to retrieved data agent actions.
|
||||
In addition, developers can also handle and process logs generated from the AutoGen core library (e.g., LLMCallEvent etc). See the example log handler in [utils.py](src/team_one/utils.py) on how this can be implemented. By default, the logs are written to a file named `log.jsonl` which can be configured as a parameter to the defined log handler. These logs can be parsed to retrieved data agent actions.
|
||||
|
||||
|
||||
# Setup
|
||||
|
|
|
|||
Loading…
Reference in New Issue