mirror of
https://github.com/microsoft/autogen.git
synced 2025-11-02 10:50:03 +00:00
change back name to flaml
This commit is contained in:
Qingyun Wu
parent
2eab9a358e
commit
45b3f1d80d
0
website/docs/Blog.md
Normal file
0
website/docs/Blog.md
Normal file
@ -69,7 +69,7 @@ pip install -e autogen
|
||||
|
||||
### Docker
|
||||
|
||||
We provide a simple [Dockerfile](https://github.com/microsoft/autogen/blob/main/Dockerfile).
|
||||
We provide a simple [Dockerfile](https://github.com/microsoft/flaml/blob/main/Dockerfile).
|
||||
|
||||
```bash
|
||||
docker build https://github.com/microsoft/autogen.git#main -t autogen-dev
|
||||
@ -79,7 +79,7 @@ docker run -it autogen-dev
|
||||
### Develop in Remote Container
|
||||
|
||||
If you use vscode, you can open the autogen folder in a [Container](https://code.visualstudio.com/docs/remote/containers).
|
||||
We have provided the configuration in [devcontainer](https://github.com/microsoft/autogen/blob/main/.devcontainer).
|
||||
We have provided the configuration in [devcontainer](https://github.com/microsoft/flaml/blob/main/.devcontainer).
|
||||
|
||||
### Pre-commit
|
||||
|
||||
|
||||
@ -4,12 +4,12 @@ AutoGen offers conversable agents powered by LLM, tool or human, which can be us
|
||||
Please find documentation about this feature [here](/docs/Use-Cases/Autogen#agents).
|
||||
|
||||
Links to notebook examples:
|
||||
* [Automated Task Solving with Code Generation, Execution & Debugging](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_auto_feedback_from_code_execution.ipynb)
|
||||
* [Auto Code Generation, Execution, Debugging and Human Feedback](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_human_feedback.ipynb)
|
||||
* [Solve Tasks Requiring Web Info](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_web_info.ipynb)
|
||||
* [Use Provided Tools as Functions](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_function_call.ipynb)
|
||||
* [Automated Task Solving with Coding & Planning Agents](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_planning.ipynb)
|
||||
* [Automated Task Solving with GPT-4 + Multiple Human Users](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_two_users.ipynb)
|
||||
* [Automated Chess Game Playing & Chitchatting by GPT-4 Agents](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_chess.ipynb)
|
||||
* [Automated Task Solving by Group Chat](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_groupchat.ipynb)
|
||||
* [Automated Continual Learning from New Data](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_stream.ipynb)
|
||||
* [Automated Task Solving with Code Generation, Execution & Debugging](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_auto_feedback_from_code_execution.ipynb)
|
||||
* [Auto Code Generation, Execution, Debugging and Human Feedback](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_human_feedback.ipynb)
|
||||
* [Solve Tasks Requiring Web Info](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_web_info.ipynb)
|
||||
* [Use Provided Tools as Functions](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_function_call.ipynb)
|
||||
* [Automated Task Solving with Coding & Planning Agents](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_planning.ipynb)
|
||||
* [Automated Task Solving with GPT-4 + Multiple Human Users](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_two_users.ipynb)
|
||||
* [Automated Chess Game Playing & Chitchatting by GPT-4 Agents](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_chess.ipynb)
|
||||
* [Automated Task Solving by Group Chat](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_groupchat.ipynb)
|
||||
* [Automated Continual Learning from New Data](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_stream.ipynb)
|
||||
|
||||
@ -4,5 +4,5 @@ AutoGen also offers a cost-effective hyperparameter optimization technique [EcoO
|
||||
Please find documentation about this feature [here](/docs/Use-Cases/enhanced_inference).
|
||||
|
||||
Links to notebook examples:
|
||||
* [Optimize for Code Generation](https://github.com/microsoft/autogen/blob/main/notebook/autogen_openai_completion.ipynb) | [Open in colab](https://colab.research.google.com/github/microsoft/autogen/blob/main/notebook/autogen_openai_completion.ipynb)
|
||||
* [Optimize for Math](https://github.com/microsoft/autogen/blob/main/notebook/autogen_chatgpt_gpt4.ipynb) | [Open in colab](https://colab.research.google.com/github/microsoft/autogen/blob/main/notebook/autogen_chatgpt_gpt4.ipynb)
|
||||
* [Optimize for Code Generation](https://github.com/microsoft/flaml/blob/main/notebook/autogen_openai_completion.ipynb) | [Open in colab](https://colab.research.google.com/github/microsoft/flaml/blob/main/notebook/autogen_openai_completion.ipynb)
|
||||
* [Optimize for Math](https://github.com/microsoft/flaml/blob/main/notebook/autogen_chatgpt_gpt4.ipynb) | [Open in colab](https://colab.research.google.com/github/microsoft/flaml/blob/main/notebook/autogen_chatgpt_gpt4.ipynb)
|
||||
|
||||
@ -18,13 +18,13 @@ AutoGen is powered by collaborative [research studies](/docs/Research) from Micr
|
||||
|
||||
### Quickstart
|
||||
|
||||
Install AutoGen from pip: `pip install pyautogen`. Find more options in [Installation](/docs/Installation).
|
||||
Install AutoGen from pip: `pip install "flaml[autogen]"`. Find more options in [Installation](/docs/Installation).
|
||||
|
||||
|
||||
Autogen enables the next-gen LLM applications with a generic multi-agent conversation framework. It offers customizable and conversable agents which integrate LLMs, tools and human.
|
||||
By automating chat among multiple capable agents, one can easily make them collectively perform tasks autonomously or with human feedback, including tasks that require using tools via code. For example,
|
||||
```python
|
||||
from autogen import AssistantAgent, UserProxyAgent
|
||||
from flaml.autogen import AssistantAgent, UserProxyAgent
|
||||
assistant = AssistantAgent("assistant")
|
||||
user_proxy = UserProxyAgent("user_proxy")
|
||||
user_proxy.initiate_chat(assistant, message="Show me the YTD gain of 10 largest technology companies as of today.")
|
||||
@ -49,9 +49,9 @@ response = autogen.Completion.create(context=test_instance, **config)
|
||||
|
||||
### Where to Go Next?
|
||||
|
||||
* Understand the use cases for [multi-agent conversation](/docs/Use-Cases/multiagent_conversation).
|
||||
* Understand the use cases for [multi-agent conversation](/docs/Use-Cases/agent_chat).
|
||||
* Understand the use cases for [enhanced LLM inference](/docs/Use-Cases/enhanced_inference).
|
||||
* Find code examples from [Examples](/docs/Examples).
|
||||
* Find code examples from [Examples](/docs/Examples/AutoGen-AgentChat).
|
||||
* Learn about [research](/docs/Research) around AutoGen and check [blogposts](/blog).
|
||||
* Chat on [Discord](TBD).
|
||||
|
||||
|
||||
@ -5,10 +5,10 @@
|
||||
AutoGen requires **Python version >= 3.8**. It can be installed from pip:
|
||||
|
||||
```bash
|
||||
pip install pyautogen
|
||||
pip install "flaml[autogen]"
|
||||
```
|
||||
|
||||
or conda:
|
||||
```
|
||||
conda install pyautogen -c conda-forge
|
||||
conda install "flaml[autogen]" -c conda-forge
|
||||
```
|
||||
|
||||
@ -1,15 +1,18 @@
|
||||
# Multi-agent conversation Framework
|
||||
# Multi-agent Conversation Framework
|
||||
|
||||
AutoGen offers a unified multi-agent conversation framework as a high-level abstraction of using foundation models. It features capable, customizable and conversable agents which integrate LLM, tool and human via automated agent chat.
|
||||
By automating chat among multiple capable agents, one can easily make them collectively perform tasks autonomously or with human feedback, including tasks that require using tools via code.
|
||||
|
||||
This framework simplifies the orchestration, automation and optimization of a complex LLM workflow. It maximizes the performance of LLM models and augments their weakness. It enables building next-gen LLM applications based on multi-agent conversations with minimal effort.
|
||||
|
||||
### Conversable Agents
|
||||
### Agents
|
||||
|
||||
We have designed a generic `ResponsiveAgent` class for Agents that are capable of conversing with each other through the exchange of messages to jointly finish a task. An agent can communicate with other agents and perform actions. Different agents can differ in what actions they perform after receiving messages. Two representative subclasses are `AssistantAgent` and `UserProxyAgent`.
|
||||
We have designed a generic `ResponsiveAgent` class for Agents that are capable of conversing with each other through the exchange of messages to jointly finish a task. An agent can communicate with other agents and perform actions.
|
||||
|
||||
Different agents can differ in what actions they perform after receiving messages. Two representative subclasses are `AssistantAgent` and `UserProxyAgent`.
|
||||
|
||||
- `AssistantAgent`. Designed to act as an assistant by responding to user requests. It could write Python code (in a Python coding block) for a user to execute when a message (typically a description of a task that needs to be solved) is received. Under the hood, the Python code is written by LLM (e.g., GPT-4). It can also receive the execution results and suggest code with bug fix. Its behavior can be altered by passing a new system message. The LLM [inference](#enhanced-inference) configuration can be configured via `llm_config`.
|
||||
|
||||
- `UserProxyAgent`. Serves as a proxy for the human user. Upon receiving a message, the UserProxyAgent will either solicit the human user's input or prepare an automatically generated reply. The chosen action depends on the settings of the `human_input_mode` and `max_consecutive_auto_reply` when the `UserProxyAgent` instance is constructed, and whether a human user input is available.
|
||||
By default, the automatically generated reply is crafted based on automatic code execution. The `UserProxyAgent` triggers code execution automatically when it detects an executable code block in the received message and no human user input is provided. Code execution can be disabled by setting `code_execution_config` to False. LLM-based response is disabled by default. It can be enabled by setting `llm_config` to a dict corresponding to the [inference](#enhanced-inference) configuration.
|
||||
When `llm_config` is set to a dict, `UserProxyAgent` can generate replies using an LLM when code execution is not performed.
|
||||
@ -17,13 +20,8 @@ When `llm_config` is set to a dict, `UserProxyAgent` can generate replies using
|
||||
The auto-reply capability of `ResponsiveAgent` allows for more autonomous multi-agent communication while retaining the possibility of human intervention.
|
||||
One can also easily extend it by registering auto_reply functions with the `register_auto_reply()` method.
|
||||
|
||||
## Multi-agent Conversations
|
||||
|
||||
### Basic Example
|
||||
|
||||
Example usage of the agents to solve a task with code:
|
||||
```python
|
||||
from autogen import AssistantAgent, UserProxyAgent
|
||||
from flaml.autogen import AssistantAgent, UserProxyAgent
|
||||
|
||||
# create an AssistantAgent instance named "assistant"
|
||||
assistant = AssistantAgent(name="assistant")
|
||||
@ -33,7 +31,14 @@ user_proxy = UserProxyAgent(
|
||||
name="user_proxy",
|
||||
human_input_mode="NEVER", # in this mode, the agent will never solicit human input but always auto reply
|
||||
)
|
||||
```
|
||||
|
||||
## Multi-agent Conversations
|
||||
|
||||
### A Basci Two-Agent Conversation Example
|
||||
|
||||
Example usage of the agents to solve a task with code:
|
||||
```python
|
||||
# the assistant receives a message from the user, which contains the task description
|
||||
user.initiate_chat(
|
||||
assistant,
|
||||
@ -49,19 +54,16 @@ In the example above, we create an AssistantAgent named "assistant" to serve as
|
||||
Please find a visual illustration of how UserProxyAgent and AssistantAgent collaboratively solve the above task below:
|
||||
|
||||
|
||||
### Human Input Mode
|
||||
### Customizable Conversation Pattern
|
||||
|
||||
The `human_input_mode` parameter of `UserProxyAgent` controls the behavior of the agent when it receives a message. It can be set to `"NEVER"`, `"ALWAYS"`, or `"TERMINATE"`.
|
||||
- Under the mode `human_input_mode="NEVER"`, the multi-turn conversation between the assistant and the user_proxy stops when the number of auto-reply reaches the upper limit specified by `max_consecutive_auto_reply` or the received message is a termination message according to `is_termination_msg`.
|
||||
- When `human_input_mode` is set to `"ALWAYS"`, the user proxy agent solicits human input every time a message is received; and the conversation stops when the human input is "exit", or when the received message is a termination message and no human input is provided.
|
||||
- When `human_input_mode` is set to `"TERMINATE"`, the user proxy agent solicits human input only when a termination message is received or the number of auto replies reaches `max_consecutive_auto_reply`.
|
||||
### Dynamic Multi-Agent Conversation
|
||||
|
||||
### Function Calling
|
||||
To leverage [function calling capability of OpenAI's Chat Completions API](https://openai.com/blog/function-calling-and-other-api-updates?ref=upstract.com), one can pass in a list of callable functions or class methods to `UserProxyAgent`, which corresponds to the description of functions passed to OpenAI's API.
|
||||
Leveraging [function calling capability of OpenAI's Chat Completions API](https://openai.com/blog/function-calling-and-other-api-updates?ref=upstract.com), one can pass in a list of callable functions or class methods to `UserProxyAgent`, which corresponds to the description of functions passed to OpenAI's API.
|
||||
|
||||
Example usage of the agents to solve a task with function calling feature:
|
||||
```python
|
||||
from autogen import AssistantAgent, UserProxyAgent
|
||||
from flaml.autogen import AssistantAgent, UserProxyAgent
|
||||
|
||||
# put the descriptions of functions in config to be passed to OpenAI's API
|
||||
llm_config = {
|
||||
@ -138,18 +140,17 @@ user_proxy.initiate_chat(
|
||||
)
|
||||
```
|
||||
|
||||
### Notebook Examples
|
||||
### Diverse Applications Implemented with AutoGen
|
||||
|
||||
*Interested in trying it yourself? Please check the following notebook examples:*
|
||||
* [Automated Task Solving with Code Generation, Execution & Debugging](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_auto_feedback_from_code_execution.ipynb)
|
||||
* [Auto Code Generation, Execution, Debugging and Human Feedback](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_human_feedback.ipynb)
|
||||
* [Solve Tasks Requiring Web Info](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_web_info.ipynb)
|
||||
* [Use Provided Tools as Functions](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_function_call.ipynb)
|
||||
* [Automated Task Solving with Coding & Planning Agents](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_planning.ipynb)
|
||||
* [Automated Task Solving with GPT-4 + Multiple Human Users](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_two_users.ipynb)
|
||||
* [Automated Chess Game Playing & Chitchatting by GPT-4 Agents](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_chess.ipynb)
|
||||
* [Automated Task Solving by Group Chat](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_groupchat.ipynb)
|
||||
* [Automated Continual Learning from New Data](https://github.com/microsoft/autogen/blob/main/notebook/autogen_agentchat_stream.ipynb)
|
||||
* [Automated Task Solving with Code Generation, Execution & Debugging](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_auto_feedback_from_code_execution.ipynb)
|
||||
* [Auto Code Generation, Execution, Debugging and Human Feedback](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_human_feedback.ipynb)
|
||||
* [Solve Tasks Requiring Web Info](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_web_info.ipynb)
|
||||
* [Use Provided Tools as Functions](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_function_call.ipynb)
|
||||
* [Automated Task Solving with Coding & Planning Agents](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_planning.ipynb)
|
||||
* [Automated Task Solving with GPT-4 + Multiple Human Users](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_two_users.ipynb)
|
||||
* [Automated Chess Game Playing & Chitchatting by GPT-4 Agents](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_chess.ipynb)
|
||||
* [Automated Task Solving by Group Chat](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_groupchat.ipynb)
|
||||
* [Automated Continual Learning from New Data](https://github.com/microsoft/flaml/blob/main/notebook/autogen_agentchat_stream.ipynb)
|
||||
|
||||
|
||||
|
||||
@ -158,4 +159,4 @@ user_proxy.initiate_chat(
|
||||
|
||||
*Interested in the research that leads to this package? Please check the following papers.*
|
||||
|
||||
* [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https://arxiv.org/abs/2308.08155) Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang and Chi Wang. ArXiv 2023.
|
||||
* [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https://arxiv.org/abs/2308.08155). Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang and Chi Wang. ArXiv 2023.
|
||||
|
||||
@ -6,8 +6,8 @@ There are a number of benefits of using `autogen` to perform inference: performa
|
||||
## Tune Inference Parameters
|
||||
|
||||
*Links to notebook examples:*
|
||||
* [Optimize for Code Generation](https://github.com/microsoft/autogen/blob/main/notebook/autogen_openai_completion.ipynb)
|
||||
* [Optimize for Math](https://github.com/microsoft/autogen/blob/main/notebook/autogen_chatgpt_gpt4.ipynb)
|
||||
* [Optimize for Code Generation](https://github.com/microsoft/flaml/blob/main/notebook/autogen_openai_completion.ipynb)
|
||||
* [Optimize for Math](https://github.com/microsoft/flaml/blob/main/notebook/autogen_chatgpt_gpt4.ipynb)
|
||||
|
||||
### Choices to optimize
|
||||
|
||||
|
||||
@ -26,15 +26,15 @@ module.exports = {
|
||||
position: 'left',
|
||||
label: 'Docs',
|
||||
},
|
||||
{to: 'blog', label: 'Blog', position: 'left'},
|
||||
// {to: 'blog', label: 'Blog', position: 'left'},
|
||||
// {
|
||||
// type: 'doc',
|
||||
// docId: 'FAQ',
|
||||
// position: 'left',
|
||||
// label: 'FAQ',
|
||||
// },
|
||||
{
|
||||
type: 'doc',
|
||||
docId: 'FAQ',
|
||||
position: 'left',
|
||||
label: 'FAQ',
|
||||
},
|
||||
{
|
||||
href: 'https://github.com/microsoft/AutoGen',
|
||||
href: 'https://github.com/microsoft/FLAML',
|
||||
label: 'GitHub',
|
||||
position: 'right',
|
||||
},
|
||||
|
||||
@ -7,7 +7,7 @@ const FeatureList = [
|
||||
{
|
||||
title: 'Customizable and Convertible Agents ',
|
||||
Svg: require('../../static/img/auto.svg').default,
|
||||
docLink: './docs/getting-started',
|
||||
docLink: './docs/Use-Cases/agent_chat#agents',
|
||||
description: (
|
||||
<>
|
||||
AutoGen provides customizable and convertible agents that can be backed by
|
||||
@ -18,7 +18,7 @@ const FeatureList = [
|
||||
{
|
||||
title: 'Flexible Multi-Conversation Patterns',
|
||||
Svg: require('../../static/img/extend.svg').default,
|
||||
docLink: './docs/getting-started',
|
||||
docLink: './docs/Use-Cases/agent_chat#multi-agent-conversations',
|
||||
description: (
|
||||
<>
|
||||
AutoGen supports flexible conversation patterns for realizing complex and dynamic workflows.
|
||||
@ -28,7 +28,7 @@ const FeatureList = [
|
||||
{
|
||||
title: 'Diverse Applications',
|
||||
Svg: require('../../static/img/fast.svg').default,
|
||||
docLink: './docs/getting-started',
|
||||
docLink: './docs/Use-Cases/agent_chat#notebook-examples',
|
||||
description: (
|
||||
<>
|
||||
AutoGen offers a collection of working systems spanning span a wide range of applications from various domains and complexities.
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user