mirror of
https://github.com/microsoft/autogen.git
synced 2026-02-11 12:54:59 -05:00
update dev8 (#4417)
This commit is contained in:
Eric Zhu
@@ -61,7 +61,7 @@ AgentChat </div>
|
||||
High-level API that includes preset agents and teams for building multi-agent systems.
|
||||
|
||||
```sh
|
||||
pip install 'autogen-agentchat==0.4.0.dev7'
|
||||
pip install 'autogen-agentchat==0.4.0.dev8'
|
||||
```
|
||||
|
||||
💡 *Start here if you are looking for an API similar to AutoGen 0.2*
|
||||
@@ -82,7 +82,7 @@ Get Started
|
||||
Provides building blocks for creating asynchronous, event driven multi-agent systems.
|
||||
|
||||
```sh
|
||||
pip install 'autogen-core==0.4.0.dev7'
|
||||
pip install 'autogen-core==0.4.0.dev8'
|
||||
```
|
||||
|
||||
+++
|
||||
|
||||
@@ -31,10 +31,10 @@ myst:
|
||||
Library that is at a similar level of abstraction as AutoGen 0.2, including default agents and group chat.
|
||||
|
||||
```sh
|
||||
pip install 'autogen-agentchat==0.4.0.dev7'
|
||||
pip install 'autogen-agentchat==0.4.0.dev8'
|
||||
```
|
||||
|
||||
[{fas}`circle-info;pst-color-primary` User Guide](/user-guide/agentchat-user-guide/index.md) | [{fas}`file-code;pst-color-primary` API Reference](/reference/python/autogen_agentchat/autogen_agentchat.rst) | [{fab}`python;pst-color-primary` PyPI](https://pypi.org/project/autogen-agentchat/0.4.0.dev7/) | [{fab}`github;pst-color-primary` Source](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-agentchat)
|
||||
[{fas}`circle-info;pst-color-primary` User Guide](/user-guide/agentchat-user-guide/index.md) | [{fas}`file-code;pst-color-primary` API Reference](/reference/python/autogen_agentchat/autogen_agentchat.rst) | [{fab}`python;pst-color-primary` PyPI](https://pypi.org/project/autogen-agentchat/0.4.0.dev8/) | [{fab}`github;pst-color-primary` Source](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-agentchat)
|
||||
:::
|
||||
|
||||
(pkg-info-autogen-core)=
|
||||
@@ -46,10 +46,10 @@ pip install 'autogen-agentchat==0.4.0.dev7'
|
||||
Implements the core functionality of the AutoGen framework, providing basic building blocks for creating multi-agent systems.
|
||||
|
||||
```sh
|
||||
pip install 'autogen-core==0.4.0.dev7'
|
||||
pip install 'autogen-core==0.4.0.dev8'
|
||||
```
|
||||
|
||||
[{fas}`circle-info;pst-color-primary` User Guide](/user-guide/core-user-guide/index.md) | [{fas}`file-code;pst-color-primary` API Reference](/reference/python/autogen_core/autogen_core.rst) | [{fab}`python;pst-color-primary` PyPI](https://pypi.org/project/autogen-core/0.4.0.dev7/) | [{fab}`github;pst-color-primary` Source](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-core)
|
||||
[{fas}`circle-info;pst-color-primary` User Guide](/user-guide/core-user-guide/index.md) | [{fas}`file-code;pst-color-primary` API Reference](/reference/python/autogen_core/autogen_core.rst) | [{fab}`python;pst-color-primary` PyPI](https://pypi.org/project/autogen-core/0.4.0.dev8/) | [{fab}`github;pst-color-primary` Source](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-core)
|
||||
:::
|
||||
|
||||
(pkg-info-autogen-ext)=
|
||||
@@ -61,7 +61,7 @@ pip install 'autogen-core==0.4.0.dev7'
|
||||
Implementations of core components that interface with external services, or use extra dependencies. For example, Docker based code execution.
|
||||
|
||||
```sh
|
||||
pip install 'autogen-ext==0.4.0.dev7'
|
||||
pip install 'autogen-ext==0.4.0.dev8'
|
||||
```
|
||||
|
||||
Extras:
|
||||
@@ -71,7 +71,7 @@ Extras:
|
||||
- `docker` needed for {py:class}`~autogen_ext.code_executors.DockerCommandLineCodeExecutor`
|
||||
- `openai` needed for {py:class}`~autogen_ext.models.OpenAIChatCompletionClient`
|
||||
|
||||
[{fas}`circle-info;pst-color-primary` User Guide](/user-guide/extensions-user-guide/index.md) | [{fas}`file-code;pst-color-primary` API Reference](/reference/python/autogen_ext/autogen_ext.rst) | [{fab}`python;pst-color-primary` PyPI](https://pypi.org/project/autogen-ext/0.4.0.dev7/) | [{fab}`github;pst-color-primary` Source](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-ext)
|
||||
[{fas}`circle-info;pst-color-primary` User Guide](/user-guide/extensions-user-guide/index.md) | [{fas}`file-code;pst-color-primary` API Reference](/reference/python/autogen_ext/autogen_ext.rst) | [{fab}`python;pst-color-primary` PyPI](https://pypi.org/project/autogen-ext/0.4.0.dev8/) | [{fab}`github;pst-color-primary` Source](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-ext)
|
||||
:::
|
||||
|
||||
(pkg-info-autogen-magentic-one)=
|
||||
|
||||
@@ -61,7 +61,7 @@ Install the `autogen-agentchat` package using pip:
|
||||
|
||||
```bash
|
||||
|
||||
pip install 'autogen-agentchat==0.4.0.dev7'
|
||||
pip install 'autogen-agentchat==0.4.0.dev8'
|
||||
```
|
||||
|
||||
```{note}
|
||||
@@ -74,7 +74,7 @@ To use the OpenAI and Azure OpenAI models, you need to install the following
|
||||
extensions:
|
||||
|
||||
```bash
|
||||
pip install 'autogen-ext[openai]==0.4.0.dev7'
|
||||
pip install 'autogen-ext[openai]==0.4.0.dev8'
|
||||
```
|
||||
|
||||
## Install Docker for Code Execution
|
||||
|
||||
@@ -37,7 +37,7 @@
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pip install 'autogen-agentchat==0.4.0.dev7' 'autogen-ext[openai]==0.4.0.dev7'"
|
||||
"pip install 'autogen-agentchat==0.4.0.dev8' 'autogen-ext[openai]==0.4.0.dev8'"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@@ -1,187 +1,187 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Models\n",
|
||||
"\n",
|
||||
"In many cases, agents need access to model services such as OpenAI, Azure OpenAI, and local models.\n",
|
||||
"AgentChat utilizes model clients provided by the\n",
|
||||
"[`autogen-ext`](../../core-user-guide/framework/model-clients.ipynb) package."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## OpenAI\n",
|
||||
"\n",
|
||||
"To access OpenAI models, you need to install the `openai` extension to use the {py:class}`~autogen_ext.models.OpenAIChatCompletionClient`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "shellscript"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pip install 'autogen-ext[openai]==0.4.0.dev7'"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You will also need to obtain an [API key](https://platform.openai.com/account/api-keys) from OpenAI."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from autogen_ext.models import OpenAIChatCompletionClient\n",
|
||||
"\n",
|
||||
"opneai_model_client = OpenAIChatCompletionClient(\n",
|
||||
" model=\"gpt-4o-2024-08-06\",\n",
|
||||
" # api_key=\"sk-...\", # Optional if you have an OPENAI_API_KEY environment variable set.\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To test the model client, you can use the following code:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"CreateResult(finish_reason='stop', content='The capital of France is Paris.', usage=RequestUsage(prompt_tokens=15, completion_tokens=7), cached=False, logprobs=None)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from autogen_core.components.models import UserMessage\n",
|
||||
"\n",
|
||||
"result = await opneai_model_client.create([UserMessage(content=\"What is the capital of France?\", source=\"user\")])\n",
|
||||
"print(result)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"```{note}\n",
|
||||
"You can use this client with models hosted on OpenAI-compatible endpoints, however, we have not tested this functionality.\n",
|
||||
"See {py:class}`~autogen_ext.models.OpenAIChatCompletionClient` for more information.\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Azure OpenAI\n",
|
||||
"\n",
|
||||
"Install the `azure` and `openai` extensions to use the {py:class}`~autogen_ext.models.AzureOpenAIChatCompletionClient`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "shellscript"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pip install 'autogen-ext[openai,azure]==0.4.0.dev7'"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To use the client, you need to provide your deployment id, Azure Cognitive Services endpoint, api version, and model capabilities.\n",
|
||||
"For authentication, you can either provide an API key or an Azure Active Directory (AAD) token credential.\n",
|
||||
"\n",
|
||||
"The following code snippet shows how to use AAD authentication.\n",
|
||||
"The identity used must be assigned the [Cognitive Services OpenAI User](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/role-based-access-control#cognitive-services-openai-user) role."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from autogen_ext.models import AzureOpenAIChatCompletionClient\n",
|
||||
"from azure.identity import DefaultAzureCredential, get_bearer_token_provider\n",
|
||||
"\n",
|
||||
"# Create the token provider\n",
|
||||
"token_provider = get_bearer_token_provider(DefaultAzureCredential(), \"https://cognitiveservices.azure.com/.default\")\n",
|
||||
"\n",
|
||||
"az_model_client = AzureOpenAIChatCompletionClient(\n",
|
||||
" azure_deployment=\"{your-azure-deployment}\",\n",
|
||||
" model=\"{model-name, such as gpt-4o}\",\n",
|
||||
" api_version=\"2024-06-01\",\n",
|
||||
" azure_endpoint=\"https://{your-custom-endpoint}.openai.azure.com/\",\n",
|
||||
" azure_ad_token_provider=token_provider, # Optional if you choose key-based authentication.\n",
|
||||
" # api_key=\"sk-...\", # For key-based authentication.\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"See [here](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/managed-identity#chat-completions) for how to use the Azure client directly or for more info."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Local Models\n",
|
||||
"\n",
|
||||
"We are working on it. Stay tuned!"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Models\n",
|
||||
"\n",
|
||||
"In many cases, agents need access to model services such as OpenAI, Azure OpenAI, and local models.\n",
|
||||
"AgentChat utilizes model clients provided by the\n",
|
||||
"[`autogen-ext`](../../core-user-guide/framework/model-clients.ipynb) package."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## OpenAI\n",
|
||||
"\n",
|
||||
"To access OpenAI models, you need to install the `openai` extension to use the {py:class}`~autogen_ext.models.OpenAIChatCompletionClient`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "shellscript"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pip install 'autogen-ext[openai]==0.4.0.dev8'"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You will also need to obtain an [API key](https://platform.openai.com/account/api-keys) from OpenAI."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from autogen_ext.models import OpenAIChatCompletionClient\n",
|
||||
"\n",
|
||||
"opneai_model_client = OpenAIChatCompletionClient(\n",
|
||||
" model=\"gpt-4o-2024-08-06\",\n",
|
||||
" # api_key=\"sk-...\", # Optional if you have an OPENAI_API_KEY environment variable set.\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To test the model client, you can use the following code:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"CreateResult(finish_reason='stop', content='The capital of France is Paris.', usage=RequestUsage(prompt_tokens=15, completion_tokens=7), cached=False, logprobs=None)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from autogen_core.components.models import UserMessage\n",
|
||||
"\n",
|
||||
"result = await opneai_model_client.create([UserMessage(content=\"What is the capital of France?\", source=\"user\")])\n",
|
||||
"print(result)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"```{note}\n",
|
||||
"You can use this client with models hosted on OpenAI-compatible endpoints, however, we have not tested this functionality.\n",
|
||||
"See {py:class}`~autogen_ext.models.OpenAIChatCompletionClient` for more information.\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Azure OpenAI\n",
|
||||
"\n",
|
||||
"Install the `azure` and `openai` extensions to use the {py:class}`~autogen_ext.models.AzureOpenAIChatCompletionClient`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"vscode": {
|
||||
"languageId": "shellscript"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pip install 'autogen-ext[openai,azure]==0.4.0.dev8'"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To use the client, you need to provide your deployment id, Azure Cognitive Services endpoint, api version, and model capabilities.\n",
|
||||
"For authentication, you can either provide an API key or an Azure Active Directory (AAD) token credential.\n",
|
||||
"\n",
|
||||
"The following code snippet shows how to use AAD authentication.\n",
|
||||
"The identity used must be assigned the [Cognitive Services OpenAI User](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/role-based-access-control#cognitive-services-openai-user) role."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from autogen_ext.models import AzureOpenAIChatCompletionClient\n",
|
||||
"from azure.identity import DefaultAzureCredential, get_bearer_token_provider\n",
|
||||
"\n",
|
||||
"# Create the token provider\n",
|
||||
"token_provider = get_bearer_token_provider(DefaultAzureCredential(), \"https://cognitiveservices.azure.com/.default\")\n",
|
||||
"\n",
|
||||
"az_model_client = AzureOpenAIChatCompletionClient(\n",
|
||||
" azure_deployment=\"{your-azure-deployment}\",\n",
|
||||
" model=\"{model-name, such as gpt-4o}\",\n",
|
||||
" api_version=\"2024-06-01\",\n",
|
||||
" azure_endpoint=\"https://{your-custom-endpoint}.openai.azure.com/\",\n",
|
||||
" azure_ad_token_provider=token_provider, # Optional if you choose key-based authentication.\n",
|
||||
" # api_key=\"sk-...\", # For key-based authentication.\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"See [here](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/managed-identity#chat-completions) for how to use the Azure client directly or for more info."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Local Models\n",
|
||||
"\n",
|
||||
"We are working on it. Stay tuned!"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
|
||||
@@ -1,223 +1,223 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Distributed Agent Runtime\n",
|
||||
"\n",
|
||||
"```{attention}\n",
|
||||
"The distributed agent runtime is an experimental feature. Expect breaking changes\n",
|
||||
"to the API.\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"A distributed agent runtime facilitates communication and agent lifecycle management\n",
|
||||
"across process boundaries.\n",
|
||||
"It consists of a host service and at least one worker runtime.\n",
|
||||
"\n",
|
||||
"The host service maintains connections to all active worker runtimes,\n",
|
||||
"facilitates message delivery, and keeps sessions for all direct messages (i.e., RPCs).\n",
|
||||
"A worker runtime processes application code (agents) and connects to the host service.\n",
|
||||
"It also advertises the agents which they support to the host service,\n",
|
||||
"so the host service can deliver messages to the correct worker.\n",
|
||||
"\n",
|
||||
"````{note}\n",
|
||||
"The distributed agent runtime requires extra dependencies, install them using:\n",
|
||||
"```bash\n",
|
||||
"pip install autogen-core[grpc]==0.4.0.dev7\n",
|
||||
"```\n",
|
||||
"````\n",
|
||||
"\n",
|
||||
"We can start a host service using {py:class}`~autogen_core.application.WorkerAgentRuntimeHost`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from autogen_core.application import WorkerAgentRuntimeHost\n",
|
||||
"\n",
|
||||
"host = WorkerAgentRuntimeHost(address=\"localhost:50051\")\n",
|
||||
"host.start() # Start a host service in the background."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The above code starts the host service in the background and accepts\n",
|
||||
"worker connections on port 50051.\n",
|
||||
"\n",
|
||||
"Before running worker runtimes, let's define our agent.\n",
|
||||
"The agent will publish a new message on every message it receives.\n",
|
||||
"It also keeps track of how many messages it has published, and \n",
|
||||
"stops publishing new messages once it has published 5 messages."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from dataclasses import dataclass\n",
|
||||
"\n",
|
||||
"from autogen_core.base import MessageContext\n",
|
||||
"from autogen_core.components import DefaultTopicId, RoutedAgent, default_subscription, message_handler\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"@dataclass\n",
|
||||
"class MyMessage:\n",
|
||||
" content: str\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"@default_subscription\n",
|
||||
"class MyAgent(RoutedAgent):\n",
|
||||
" def __init__(self, name: str) -> None:\n",
|
||||
" super().__init__(\"My agent\")\n",
|
||||
" self._name = name\n",
|
||||
" self._counter = 0\n",
|
||||
"\n",
|
||||
" @message_handler\n",
|
||||
" async def my_message_handler(self, message: MyMessage, ctx: MessageContext) -> None:\n",
|
||||
" self._counter += 1\n",
|
||||
" if self._counter > 5:\n",
|
||||
" return\n",
|
||||
" content = f\"{self._name}: Hello x {self._counter}\"\n",
|
||||
" print(content)\n",
|
||||
" await self.publish_message(MyMessage(content=content), DefaultTopicId())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now we can set up the worker agent runtimes.\n",
|
||||
"We use {py:class}`~autogen_core.application.WorkerAgentRuntime`.\n",
|
||||
"We set up two worker runtimes. Each runtime hosts one agent.\n",
|
||||
"All agents publish and subscribe to the default topic, so they can see all\n",
|
||||
"messages being published.\n",
|
||||
"\n",
|
||||
"To run the agents, we publishes a message from a worker."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"worker1: Hello x 1\n",
|
||||
"worker2: Hello x 1\n",
|
||||
"worker2: Hello x 2\n",
|
||||
"worker1: Hello x 2\n",
|
||||
"worker1: Hello x 3\n",
|
||||
"worker2: Hello x 3\n",
|
||||
"worker2: Hello x 4\n",
|
||||
"worker1: Hello x 4\n",
|
||||
"worker1: Hello x 5\n",
|
||||
"worker2: Hello x 5\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import asyncio\n",
|
||||
"\n",
|
||||
"from autogen_core.application import WorkerAgentRuntime\n",
|
||||
"\n",
|
||||
"worker1 = WorkerAgentRuntime(host_address=\"localhost:50051\")\n",
|
||||
"worker1.start()\n",
|
||||
"await MyAgent.register(worker1, \"worker1\", lambda: MyAgent(\"worker1\"))\n",
|
||||
"\n",
|
||||
"worker2 = WorkerAgentRuntime(host_address=\"localhost:50051\")\n",
|
||||
"worker2.start()\n",
|
||||
"await MyAgent.register(worker2, \"worker2\", lambda: MyAgent(\"worker2\"))\n",
|
||||
"\n",
|
||||
"await worker2.publish_message(MyMessage(content=\"Hello!\"), DefaultTopicId())\n",
|
||||
"\n",
|
||||
"# Let the agents run for a while.\n",
|
||||
"await asyncio.sleep(5)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can see each agent published exactly 5 messages.\n",
|
||||
"\n",
|
||||
"To stop the worker runtimes, we can call {py:meth}`~autogen_core.application.WorkerAgentRuntime.stop`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"await worker1.stop()\n",
|
||||
"await worker2.stop()\n",
|
||||
"\n",
|
||||
"# To keep the worker running until a termination signal is received (e.g., SIGTERM).\n",
|
||||
"# await worker1.stop_when_signal()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can call {py:meth}`~autogen_core.application.WorkerAgentRuntimeHost.stop`\n",
|
||||
"to stop the host service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"await host.stop()\n",
|
||||
"\n",
|
||||
"# To keep the host service running until a termination signal (e.g., SIGTERM)\n",
|
||||
"# await host.stop_when_signal()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Next Steps\n",
|
||||
"To see complete examples of using distributed runtime, please take a look at the following samples:\n",
|
||||
"\n",
|
||||
"- [Distributed Workers](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-core/samples/worker) \n",
|
||||
"- [Distributed Semantic Router](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-core/samples/semantic_router) \n",
|
||||
"- [Distributed Group Chat](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-core/samples/distributed-group-chat) \n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "agnext",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Distributed Agent Runtime\n",
|
||||
"\n",
|
||||
"```{attention}\n",
|
||||
"The distributed agent runtime is an experimental feature. Expect breaking changes\n",
|
||||
"to the API.\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"A distributed agent runtime facilitates communication and agent lifecycle management\n",
|
||||
"across process boundaries.\n",
|
||||
"It consists of a host service and at least one worker runtime.\n",
|
||||
"\n",
|
||||
"The host service maintains connections to all active worker runtimes,\n",
|
||||
"facilitates message delivery, and keeps sessions for all direct messages (i.e., RPCs).\n",
|
||||
"A worker runtime processes application code (agents) and connects to the host service.\n",
|
||||
"It also advertises the agents which they support to the host service,\n",
|
||||
"so the host service can deliver messages to the correct worker.\n",
|
||||
"\n",
|
||||
"````{note}\n",
|
||||
"The distributed agent runtime requires extra dependencies, install them using:\n",
|
||||
"```bash\n",
|
||||
"pip install autogen-core[grpc]==0.4.0.dev8\n",
|
||||
"```\n",
|
||||
"````\n",
|
||||
"\n",
|
||||
"We can start a host service using {py:class}`~autogen_core.application.WorkerAgentRuntimeHost`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from autogen_core.application import WorkerAgentRuntimeHost\n",
|
||||
"\n",
|
||||
"host = WorkerAgentRuntimeHost(address=\"localhost:50051\")\n",
|
||||
"host.start() # Start a host service in the background."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The above code starts the host service in the background and accepts\n",
|
||||
"worker connections on port 50051.\n",
|
||||
"\n",
|
||||
"Before running worker runtimes, let's define our agent.\n",
|
||||
"The agent will publish a new message on every message it receives.\n",
|
||||
"It also keeps track of how many messages it has published, and \n",
|
||||
"stops publishing new messages once it has published 5 messages."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from dataclasses import dataclass\n",
|
||||
"\n",
|
||||
"from autogen_core.base import MessageContext\n",
|
||||
"from autogen_core.components import DefaultTopicId, RoutedAgent, default_subscription, message_handler\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"@dataclass\n",
|
||||
"class MyMessage:\n",
|
||||
" content: str\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"@default_subscription\n",
|
||||
"class MyAgent(RoutedAgent):\n",
|
||||
" def __init__(self, name: str) -> None:\n",
|
||||
" super().__init__(\"My agent\")\n",
|
||||
" self._name = name\n",
|
||||
" self._counter = 0\n",
|
||||
"\n",
|
||||
" @message_handler\n",
|
||||
" async def my_message_handler(self, message: MyMessage, ctx: MessageContext) -> None:\n",
|
||||
" self._counter += 1\n",
|
||||
" if self._counter > 5:\n",
|
||||
" return\n",
|
||||
" content = f\"{self._name}: Hello x {self._counter}\"\n",
|
||||
" print(content)\n",
|
||||
" await self.publish_message(MyMessage(content=content), DefaultTopicId())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now we can set up the worker agent runtimes.\n",
|
||||
"We use {py:class}`~autogen_core.application.WorkerAgentRuntime`.\n",
|
||||
"We set up two worker runtimes. Each runtime hosts one agent.\n",
|
||||
"All agents publish and subscribe to the default topic, so they can see all\n",
|
||||
"messages being published.\n",
|
||||
"\n",
|
||||
"To run the agents, we publishes a message from a worker."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"worker1: Hello x 1\n",
|
||||
"worker2: Hello x 1\n",
|
||||
"worker2: Hello x 2\n",
|
||||
"worker1: Hello x 2\n",
|
||||
"worker1: Hello x 3\n",
|
||||
"worker2: Hello x 3\n",
|
||||
"worker2: Hello x 4\n",
|
||||
"worker1: Hello x 4\n",
|
||||
"worker1: Hello x 5\n",
|
||||
"worker2: Hello x 5\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import asyncio\n",
|
||||
"\n",
|
||||
"from autogen_core.application import WorkerAgentRuntime\n",
|
||||
"\n",
|
||||
"worker1 = WorkerAgentRuntime(host_address=\"localhost:50051\")\n",
|
||||
"worker1.start()\n",
|
||||
"await MyAgent.register(worker1, \"worker1\", lambda: MyAgent(\"worker1\"))\n",
|
||||
"\n",
|
||||
"worker2 = WorkerAgentRuntime(host_address=\"localhost:50051\")\n",
|
||||
"worker2.start()\n",
|
||||
"await MyAgent.register(worker2, \"worker2\", lambda: MyAgent(\"worker2\"))\n",
|
||||
"\n",
|
||||
"await worker2.publish_message(MyMessage(content=\"Hello!\"), DefaultTopicId())\n",
|
||||
"\n",
|
||||
"# Let the agents run for a while.\n",
|
||||
"await asyncio.sleep(5)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can see each agent published exactly 5 messages.\n",
|
||||
"\n",
|
||||
"To stop the worker runtimes, we can call {py:meth}`~autogen_core.application.WorkerAgentRuntime.stop`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"await worker1.stop()\n",
|
||||
"await worker2.stop()\n",
|
||||
"\n",
|
||||
"# To keep the worker running until a termination signal is received (e.g., SIGTERM).\n",
|
||||
"# await worker1.stop_when_signal()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can call {py:meth}`~autogen_core.application.WorkerAgentRuntimeHost.stop`\n",
|
||||
"to stop the host service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"await host.stop()\n",
|
||||
"\n",
|
||||
"# To keep the host service running until a termination signal (e.g., SIGTERM)\n",
|
||||
"# await host.stop_when_signal()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Next Steps\n",
|
||||
"To see complete examples of using distributed runtime, please take a look at the following samples:\n",
|
||||
"\n",
|
||||
"- [Distributed Workers](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-core/samples/worker) \n",
|
||||
"- [Distributed Semantic Router](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-core/samples/semantic_router) \n",
|
||||
"- [Distributed Group Chat](https://github.com/microsoft/autogen/tree/main/python/packages/autogen-core/samples/distributed-group-chat) \n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "agnext",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user