yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-11-15 09:33:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update docs for new executors (#2119)

Browse Source 
* Update docs for new executors

* Update website/docs/FAQ.mdx

Co-authored-by: gagb <gagb@users.noreply.github.com>

* Update website/docs/FAQ.mdx

Co-authored-by: gagb <gagb@users.noreply.github.com>

* Update website/docs/installation/Installation.mdx

Co-authored-by: gagb <gagb@users.noreply.github.com>

* Update website/docs/installation/Installation.mdx

Co-authored-by: gagb <gagb@users.noreply.github.com>

---------

Co-authored-by: gagb <gagb@users.noreply.github.com>
This commit is contained in:
Eric Zhu 2024-03-22 21:19:54 -07:00 committed by GitHub
parent 01afc9bbe7
commit 3dfa305acb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 91 additions and 70 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
website/docs/FAQ.mdx
View File

@ -71,31 +71,46 @@ in the system message. This line is in the default system message of the `Assist
If the `# filename` doesn't appear in the suggested code still, consider adding explicit instructions such as "save the code to disk" in the initial user message in `initiate_chat`. If the `# filename` doesn't appear in the suggested code still, consider adding explicit instructions such as "save the code to disk" in the initial user message in `initiate_chat`.
The `AssistantAgent` doesn't save all the code by default, because there are cases in which one would just like to finish a task without saving the code. The `AssistantAgent` doesn't save all the code by default, because there are cases in which one would just like to finish a task without saving the code.
## Code execution ## Legacy code executor
We strongly recommend using docker to execute code. There are two ways to use docker: :::note
The new code executors offers more choices of execution backend.
Read more about [code executors](/docs/tutorial/code-executors).
:::
1. Run AutoGen in a docker container. For example, when developing in [GitHub codespace](https://codespaces.new/microsoft/autogen?quickstart=1), AutoGen runs in a docker container. If you are not developing in Github codespace, follow instructions [here](installation/Docker.md#option-1-install-and-run-autogen-in-docker) to install and run AutoGen in docker. The legacy code executor is used by specifying the `code_execution_config` in the agent's constructor.
2. Run AutoGen outside of a docker, while performing code execution with a docker container. For this option, make sure docker is up and running. If you want to run the code locally (not recommended) then `use_docker` can be set to `False` in `code_execution_config` for each code-execution agent, or set `AUTOGEN_USE_DOCKER` to `False` as an environment variable.
### Enable Python 3 docker image
You might want to override the default docker image used for code execution. To do that set `use_docker` key of `code_execution_config` property to the name of the image. E.g.:
```python ```python
user_proxy = autogen.UserProxyAgent( from autogen import UserProxyAgent
name="agent",
human_input_mode="TERMINATE", user_proxy = UserProxyAgent(
max_consecutive_auto_reply=10, name="user_proxy",
code_execution_config={"work_dir":"_output", "use_docker":"python:3"}, code_execution_config={"work_dir":"_output", "use_docker":"python:3"},
llm_config=llm_config,
system_message=""""Reply TERMINATE if the task has been solved at full satisfaction.
Otherwise, reply CONTINUE, or the reason why the task is not solved yet."""
) )
``` ```
If you have problems with agents running `pip install` or get errors similar to `Error while fetching server API version: ('Connection aborted.', FileNotFoundError(2, 'No such file or directory')`, you can choose **'python:3'** as image as shown in the code example above and that should solve the problem. In this example, the `code_execution_config` specifies that the code will be
executed in a docker container with the image `python:3`.
By default, the image name is `python:3-slim` if not specified.
The `work_dir` specifies the directory where the code will be executed.
If you have problems with agents running `pip install` or get errors similar to
`Error while fetching server API version: ('Connection aborted.', FileNotFoundError(2, 'No such file or directory')`,
you can choose **'python:3'** as image as shown in the code example above and
that should solve the problem.
### Agents keep thanking each other when using `gpt-3.5-turbo` By default it runs code in a docker container. If you want to run code locally
(not recommended) then `use_docker` can be set to `False` in `code_execution_config`
for each code-execution agent, or set `AUTOGEN_USE_DOCKER` to `False` as an
environment variable.
You can also develop your AutoGen application in a docker container.
For example, when developing in [GitHub codespace](https://codespaces.new/microsoft/autogen?quickstart=1),
AutoGen runs in a docker container.
If you are not developing in GitHub Codespaces,
follow instructions [here](installation/Docker.md#option-1-install-and-run-autogen-in-docker)
to install and run AutoGen in docker.
## Agents keep thanking each other when using `gpt-3.5-turbo`
When using `gpt-3.5-turbo` you may often encounter agents going into a "gratitude loop", meaning when they complete a task they will begin congratulating and thanking each other in a continuous loop. This is a limitation in the performance of `gpt-3.5-turbo`, in contrast to `gpt-4` which has no problem remembering instructions. This can hinder the experimentation experience when trying to test out your own use case with cheaper models. When using `gpt-3.5-turbo` you may often encounter agents going into a "gratitude loop", meaning when they complete a task they will begin congratulating and thanking each other in a continuous loop. This is a limitation in the performance of `gpt-3.5-turbo`, in contrast to `gpt-4` which has no problem remembering instructions. This can hinder the experimentation experience when trying to test out your own use case with cheaper models.

44
website/docs/installation/Installation.mdx
View File

@ -78,35 +78,29 @@ pip install pyautogen
::: :::
## Install Docker for Code Execution
## Code execution with Docker (default) We recommend using Docker for code execution.
To install Docker, follow the instructions for your operating system on the [Docker website](https://docs.docker.com/get-docker/).
Even if you install AutoGen locally, we highly recommend using Docker for [code execution](FAQ.mdx#code-execution). A simple example of how to use Docker for code execution is shown below:
The default behaviour for code-execution agents is for code execution to be performed in a docker container.
**To turn this off**: if you want to run the code locally (not recommended) then `use_docker` can be set to `False` in `code_execution_config` for each code-execution agent, or set `AUTOGEN_USE_DOCKER` to `False` as an environment variable.
You might want to override the default docker image used for code execution. To do that set `use_docker` key of `code_execution_config` property to the name of the image. E.g.:
```python ```python
user_proxy = autogen.UserProxyAgent( from pathlib import Path
name="agent", from autogen import UserProxyAgent
human_input_mode="TERMINATE", from autogen.coding import DockerCommandLineCodeExecutor
max_consecutive_auto_reply=10,
code_execution_config={"work_dir":"_output", "use_docker":"python:3"}, work_dir = Path("coding")
llm_config=llm_config, work_dir.mkdir(exist_ok=True)
system_message=""""Reply TERMINATE if the task has been solved at full satisfaction.
Otherwise, reply CONTINUE, or the reason why the task is not solved yet.""" with DockerCommandLineCodeExecutor(work_dir=work_dir) as code_executor:
) user_proxy = UserProxyAgent(
name="user_proxy",
code_execution_config={"executor": code_executor},
)
``` ```
**Turn off code execution entirely**: if you want to turn off code execution entirely, set `code_execution_config` to `False`. E.g.: To learn more about code executors, see the [code executors tutorial](/docs/tutorial/code-executors).
```python You might have seen a different way of defining the executors without creating the
user_proxy = autogen.UserProxyAgent( executor object, please refer to FAQ for this [legacy code executor](/docs/FAQ#legacy-code-executor).
name="agent",
llm_config=llm_config,
code_execution_config=False,
)
```

54
website/docs/topics/non-openai-models/cloud-togetherai.md
View File

@ -21,11 +21,9 @@ set TOGETHER_API_KEY=YourTogetherAIKeyHere
Create your LLM configuration, with the [model you want](https://docs.together.ai/docs/inference-models). Create your LLM configuration, with the [model you want](https://docs.together.ai/docs/inference-models).
```python ```python
import autogen
import os import os
llm_config={ config_list = [
"config_list": [
{ {
# Available together.ai model strings: # Available together.ai model strings:
# https://docs.together.ai/docs/inference-models # https://docs.together.ai/docs/inference-models
@ -33,64 +31,78 @@ llm_config={
"api_key": os.environ['TOGETHER_API_KEY'], "api_key": os.environ['TOGETHER_API_KEY'],
"base_url": "https://api.together.xyz/v1" "base_url": "https://api.together.xyz/v1"
} }
], ]
"cache_seed": 42
}
``` ```
## Construct Agents ## Construct Agents
```python ```python
from pathlib import Path
from autogen import AssistantAgent, UserProxyAgent
from autogen.coding import LocalCommandLineCodeExecutor
work_dir = Path("groupchat")
work_dir.mkdir(exist_ok=True)
# Create local command line code executor.
code_executor = LocalCommandLineCodeExecutor(work_dir=work_dir)
# User Proxy will execute code and finish the chat upon typing 'exit' # User Proxy will execute code and finish the chat upon typing 'exit'
user_proxy = autogen.UserProxyAgent( user_proxy = UserProxyAgent(
name="UserProxy", name="UserProxy",
system_message="A human admin", system_message="A human admin",
code_execution_config={ code_execution_config={
"last_n_messages": 2, "last_n_messages": 2,
"work_dir": "groupchat", "executor": code_executor,
"use_docker": False, },
}, # Please set use_docker=True if docker is available to run the generated code. Using docker is safer than running the generated code directly.
human_input_mode="TERMINATE", human_input_mode="TERMINATE",
is_termination_msg=lambda x: "TERMINATE" in x.get("content"), is_termination_msg=lambda x: "TERMINATE" in x.get("content"),
) )
# Python Coder agent # Python Coder agent
coder = autogen.AssistantAgent( coder = AssistantAgent(
name="softwareCoder", name="softwareCoder",
description="Software Coder, writes Python code as required and reiterates with feedback from the Code Reviewer.", description="Software Coder, writes Python code as required and reiterates with feedback from the Code Reviewer.",
system_message="You are a senior Python developer, a specialist in writing succinct Python functions.", system_message="You are a senior Python developer, a specialist in writing succinct Python functions.",
llm_config=llm_config, llm_config={"config_list": config_list},
) )
# Code Reviewer agent # Code Reviewer agent
reviewer = autogen.AssistantAgent( reviewer = AssistantAgent(
name="codeReviewer", name="codeReviewer",
description="Code Reviewer, reviews written code for correctness, efficiency, and security. Asks the Software Coder to address issues.", description="Code Reviewer, reviews written code for correctness, efficiency, and security. Asks the Software Coder to address issues.",
system_message="You are a Code Reviewer, experienced in checking code for correctness, efficiency, and security. Review and provide feedback to the Software Coder until you are satisfied, then return the word TERMINATE", system_message="You are a Code Reviewer, experienced in checking code for correctness, efficiency, and security. Review and provide feedback to the Software Coder until you are satisfied, then return the word TERMINATE",
is_termination_msg=lambda x: "TERMINATE" in x.get("content"), is_termination_msg=lambda x: "TERMINATE" in x.get("content"),
llm_config=llm_config, llm_config={"config_list": config_list},
) )
``` ```
## Establish the group chat ## Establish the group chat
```python ```python
from autogen import GroupChat, GroupChatManager
# Establish the Group Chat and disallow a speaker being selected consecutively # Establish the Group Chat and disallow a speaker being selected consecutively
groupchat = autogen.GroupChat(agents=[user_proxy, coder, reviewer], messages=[], max_round=12, allow_repeat_speaker=False) groupchat = GroupChat(agents=[user_proxy, coder, reviewer], messages=[], max_round=12, allow_repeat_speaker=False)
# Manages the group of multiple agents # Manages the group of multiple agents
manager = autogen.GroupChatManager(groupchat=groupchat, llm_config=llm_config) manager = GroupChatManager(groupchat=groupchat, llm_config={"config_list": config_list})
``` ```
## Start Chat ## Start Chat
```python ```python
# Start the chat with a request to write a function from autogen.cache import Cache
user_proxy.initiate_chat(
# Cache LLM responses.
with Cache.disk() as cache:
# Start the chat with a request to write a function
user_proxy.initiate_chat(
manager, manager,
message="Write a Python function for the Fibonacci sequence, the function will have one parameter for the number in the sequence, which the function will return the Fibonacci number for." message="Write a Python function for the Fibonacci sequence, the function will have one parameter for the number in the sequence, which the function will return the Fibonacci number for.",
) cache=cache,
# type exit to terminate the chat )
# type exit to terminate the chat
``` ```
Output: Output: