wangtao
/
autogen
mirror of https://github.com/microsoft/autogen.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

add agent notebook and documentation (#1052) 

* add agent notebook and documentation

* fix bug

* set flush to True when printing msg in agent

* add a math problem in agent notebook

* remove

* header

* improve notebook doc

* notebook update

* improve notebook example

* improve doc

* improve notebook doc

* improve print

* doc

* human_input_mode

* human_input_mode str

* indent

* indent

* Update flaml/autogen/agent/user_proxy_agent.py

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* Update notebook/autogen_agent.ipynb

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* Update notebook/autogen_agent.ipynb

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* Update notebook/autogen_agent.ipynb

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* renaming and doc format

* typo

---------

Co-authored-by: Chi Wang <wang.chi@microsoft.com>
This commit is contained in:
Qingyun Wu 2023-05-27 23:17:23 -04:00 committed by GitHub
parent 3e6e834bbb
commit fed28e700b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 718 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
flaml/autogen/agent/agent.py
View File

@ -37,8 +37,8 @@ class Agent:
def _receive(self, message, sender):
"""Receive a message from another agent."""
print("\n****", self.name, "received message from", sender.name, "****\n")
print(message)
print("\n****", self.name, "received message from", sender.name, "****\n", flush=True)
print(message, flush=True)
self._conversations[sender.name].append({"content": message, "role": "user"})
def receive(self, message, sender):

1
flaml/autogen/agent/user_proxy_agent.py
View File

@ -119,4 +119,5 @@ class UserProxyAgent(Agent):
return
self._consecutive_auto_reply_counter[sender.name] += 1
print("\n>>>>>>>> NO HUMAN INPUT RECEIVED. USING AUTO REPLY FOR THE USER...", flush=True)
self.auto_reply(message, sender, default_reply=reply)

712
notebook/autogen_agent_auto_feedback_from_code_execution.ipynb Normal file
View File

@ -0,0 +1,712 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"slideshow": {
"slide_type": "slide"
}
},
"source": [
"# Interactive LLM Agent\n",
"\n",
"FLAML offers an experimental feature of interactive LLM agents, which can be used to solve various tasks, including coding and math problem-solving.\n",
"\n",
"In this notebook, we demonstrate how to use `PythonAgent` and `UserProxyAgent` to write code and execute the code. Here `PythonAgent` is an LLM-based agent that can write Python code (in a Python coding block) for a user to execute for a given task. `UserProxyAgent` is an agent which serves as a proxy for the human user to execute the code written by `PythonAgent`, or automatically execute the code. Depending on the setting of `user_interaction_mode` and `max_consecutive_auto_reply`, the `UserProxyAgent` either solicits feedback from the human user or uses auto-feedback based on the result of code execution. For example, when `user_interaction_mode` is set to \"ALWAYS\", the `UserProxyAgent` will always prompt the user for feedback. When user feedback is provided, the `UserProxyAgent` will directly pass the feedback to `PythonAgent` without doing any additional steps. When no user feedback is provided, the `UserProxyAgent` will execute the code written by `PythonAgent` directly and return the execution results (success or failure and corresponding outputs) to `PythonAgent`.\n",
"\n",
"## Requirements\n",
"\n",
"FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the [autogen] option:\n",
"```bash\n",
"pip install flaml[autogen]\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"execution": {
"iopub.execute_input": "2023-02-13T23:40:52.317406Z",
"iopub.status.busy": "2023-02-13T23:40:52.316561Z",
"iopub.status.idle": "2023-02-13T23:40:52.321193Z",
"shell.execute_reply": "2023-02-13T23:40:52.320628Z"
}
},
"outputs": [],
"source": [
"# %pip install flaml[autogen]"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Set your API Endpoint\n",
"\n",
"The [`config_list_gpt4_gpt35`](https://microsoft.github.io/FLAML/docs/reference/autogen/oai/openai_utils#config_list_gpt4_gpt35) function tries to create a list of gpt-4 and gpt-3.5 configurations using Azure OpenAI endpoints and OpenAI endpoints. It assumes the api keys and api bases are stored in the corresponding environment variables or local txt files:\n",
"\n",
"- OpenAI API key: os.environ[\"OPENAI_API_KEY\"] or `openai_api_key_file=\"key_openai.txt\"`.\n",
"- Azure OpenAI API key: os.environ[\"AZURE_OPENAI_API_KEY\"] or `aoai_api_key_file=\"key_aoai.txt\"`. Multiple keys can be stored, one per line.\n",
"- Azure OpenAI API base: os.environ[\"AZURE_OPENAI_API_BASE\"] or `aoai_api_base_file=\"base_aoai.txt\"`. Multiple bases can be stored, one per line.\n",
"\n",
"It's OK to have only the OpenAI API key, or only the Azure Open API key + base.\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from flaml import oai\n",
"\n",
"config_list = oai.config_list_gpt4_gpt35()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Example Task: Create and execute a python script with agents\n",
"\n",
"In the example below, let's see how to use the agents in FLAML to write a python script and execute the script. This process involves constructing a `PythonAgent` to serve as the assistant, along with a `UserProxyAgent` that acts as a proxy for the human user. In this example demonstrated below, when constructing the `UserProxyAgent`, we select the `human_input_mode` to \"NEVER\". This means that the `UserProxyAgent` will not solicit feedback from the human user until the limit defined by `max_consecutive_auto_reply` is reached. For the purpose of this example, we've set this limit to 10."
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"**** coding_agent received message from user ****\n",
"\n",
"Create and execute a script to plot a rocket without using matplotlib\n",
"\n",
"**** user received message from coding_agent ****\n",
"\n",
"Creating a rocket involves using ASCII characters to display it visually. Here's a simple script to get you started:\n",
"\n",
"```python\n",
"# filename: rocket.py\n",
"def plot_rocket():\n",
" rocket = '''\n",
" |\n",
" /_\\\n",
" /^|^\\ \n",
" //| \\\\\n",
" // | \\\\\n",
" '''\n",
" print(rocket)\n",
"\n",
"if __name__ == \"__main__\":\n",
" plot_rocket()\n",
"```\n",
"\n",
"Save this code in a file named `rocket.py` and execute the script. After that, let me know the results.\n",
"\n",
" >>>>>>>> NO HUMAN INPUT RECEIVED. USING AUTO REPLY FOR THE USER...\n",
"\n",
"**** coding_agent received message from user ****\n",
"\n",
"exitcode: 0 (execution succeeded)\n",
"Code output: \n",
" |\n",
" /_ /^|^\\ \n",
" //| \\\n",
" // | \\\n",
" \n",
"\n",
"\n",
"**** user received message from coding_agent ****\n",
"\n",
"It seems that there's an issue with the spacing in the rocket drawing. Let's fix that.\n",
"\n",
"```python\n",
"# filename: rocket.py\n",
"def plot_rocket():\n",
" rocket = '''\n",
" |\n",
" /_\\\\\n",
" /^|^\\\\\n",
" //|\\\\\\\\\n",
" // | \\\\\\\\\n",
" '''\n",
" print(rocket)\n",
"\n",
"if __name__ == \"__main__\":\n",
" plot_rocket()\n",
"```\n",
"\n",
"Save this code in the existing `rocket.py` file and execute the script again. After that, let me know the results.\n",
"\n",
" >>>>>>>> NO HUMAN INPUT RECEIVED. USING AUTO REPLY FOR THE USER...\n",
"\n",
"**** coding_agent received message from user ****\n",
"\n",
"exitcode: 0 (execution succeeded)\n",
"Code output: \n",
" |\n",
" /_\\\n",
" /^|^\\\n",
" //|\\\\\n",
" // | \\\\\n",
" \n",
"\n",
"\n",
"**** user received message from coding_agent ****\n",
"\n",
"Great! The rocket is now displayed correctly. If you have any more tasks or modifications, please let me know. Otherwise, I hope you enjoyed the ASCII rocket!\n",
"\n",
"TERMINATE\n"
]
}
],
"source": [
"from flaml.autogen.agent.coding_agent import PythonAgent\n",
"from flaml.autogen.agent.user_proxy_agent import UserProxyAgent\n",
"\n",
"# create an assistant which is essentially a PythonAgent instance named \"coding_agent\"\n",
"assistant = PythonAgent(\"coding_agent\", request_timeout=600, seed=42, config_list=config_list)\n",
"# create a UserProxyAgent instance named \"user\"\n",
"user = UserProxyAgent(\n",
" \"user\",\n",
" human_input_mode=\"NEVER\",\n",
" max_consecutive_auto_reply=10,\n",
" is_termination_msg=lambda x: x.rstrip().endswith(\"TERMINATE\"),\n",
")\n",
"# the assistant receives a message from the user, which contains the task description\n",
"assistant.receive(\n",
" \"\"\"Create and execute a script to plot a rocket without using matplotlib\"\"\",\n",
" user,\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Next, let's see how to use the agents to first write the generated script to a file and then execute the script in two sessions of conversation between the `PythonAgent` and the `UserProxyAgent`."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"**** coding_agent received message from user ****\n",
"\n",
"Create a temp.py file with the following content:\n",
"```\n",
"print('Hello world!')\n",
"```\n",
"\n",
"**** user received message from coding_agent ****\n",
"\n",
"Here is the code to create the temp.py file with the specified content. Please execute this code:\n",
"\n",
"```python\n",
"with open('temp.py', 'w') as file:\n",
" file.write(\"print('Hello world!')\")\n",
"```\n",
"\n",
"After executing this code, you should have a file named temp.py with the content:\n",
"\n",
"```\n",
"print('Hello world!')\n",
"```\n",
"\n",
" >>>>>>>> NO HUMAN INPUT RECEIVED. USING AUTO REPLY FOR THE USER...\n",
"\n",
"**** coding_agent received message from user ****\n",
"\n",
"exitcode: 0 (execution succeeded)\n",
"Code output: \n",
"\n",
"**** user received message from coding_agent ****\n",
"\n",
"Great! The temp.py file has been created successfully. Now, you can run this file to see the output. If you need any further assistance, feel free to ask.\n",
"\n",
"TERMINATE\n"
]
}
],
"source": [
"# it is suggested to reset the assistant to clear the state if the new task is not related to the previous one.\n",
"assistant.reset()\n",
"assistant.receive(\n",
" \"\"\"Create a temp.py file with the following content:\n",
" ```\n",
" print('Hello world!')\n",
" ```\"\"\",\n",
" user,\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"The example above involves code execution. In FLAML, code execution is triggered automatically by the `UserProxyAgent` when it detects an executable code block in a received message and no human user input is provided. This process occurs in a designated working directory, using a Docker container by default. Unless a specific directory is specified, FLAML defaults to the `flaml/autogen/extensions` directory. Users have the option to specify a different working directory by setting the `work_dir` argument when constructing a new instance of the `UserProxyAgent`.\n",
"\n",
"Upon successful execution of the preceding code block, a file named `temp.py` will be created and saved in the default working directory `flaml/autogen/extensions`. Now, let's prompt the assistant to execute the code contained within this file using the following line of code."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"**** coding_agent received message from user ****\n",
"\n",
"Execute temp.py\n",
"\n",
"**** user received message from coding_agent ****\n",
"\n",
"To execute temp.py, run the following code:\n",
"\n",
"```python\n",
"import os\n",
"\n",
"os.system('python temp.py')\n",
"```\n",
"\n",
"This code imports the os module and then runs the temp.py file. After executing this code, you should see the output:\n",
"\n",
"Hello world!\n",
"\n",
" >>>>>>>> NO HUMAN INPUT RECEIVED. USING AUTO REPLY FOR THE USER...\n",
"\n",
"**** coding_agent received message from user ****\n",
"\n",
"exitcode: 0 (execution succeeded)\n",
"Code output: Hello world!\n",
"\n",
"\n",
"**** user received message from coding_agent ****\n",
"\n",
"I'm glad that the code execution was successful and you got the desired output! If you need any further help or assistance with another task, feel free to ask.\n",
"\n",
"TERMINATE\n"
]
}
],
"source": [
"assistant.receive(\"\"\"Execute temp.py\"\"\", user)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.9.16"
},
"vscode": {
"interpreter": {
"hash": "949777d72b0d2535278d3dc13498b2535136f6dfe0678499012e853ee9abcab1"
}
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"state": {
"2d910cfd2d2a4fc49fc30fbbdc5576a7": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"454146d0f7224f038689031002906e6f": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_e4ae2b6f5a974fd4bafb6abb9d12ff26",
"IPY_MODEL_577e1e3cc4db4942b0883577b3b52755",
"IPY_MODEL_b40bdfb1ac1d4cffb7cefcb870c64d45"
],
"layout": "IPY_MODEL_dc83c7bff2f241309537a8119dfc7555",
"tabbable": null,
"tooltip": null
}
},
"577e1e3cc4db4942b0883577b3b52755": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_2d910cfd2d2a4fc49fc30fbbdc5576a7",
"max": 1,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_74a6ba0c3cbc4051be0a83e152fe1e62",
"tabbable": null,
"tooltip": null,
"value": 1
}
},
"6086462a12d54bafa59d3c4566f06cb2": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"74a6ba0c3cbc4051be0a83e152fe1e62": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"7d3f3d9e15894d05a4d188ff4f466554": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"b40bdfb1ac1d4cffb7cefcb870c64d45": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_f1355871cc6f4dd4b50d9df5af20e5c8",
"placeholder": "​",
"style": "IPY_MODEL_ca245376fd9f4354af6b2befe4af4466",
"tabbable": null,
"tooltip": null,
"value": " 1/1 [00:00&lt;00:00, 44.69it/s]"
}
},
"ca245376fd9f4354af6b2befe4af4466": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"dc83c7bff2f241309537a8119dfc7555": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"e4ae2b6f5a974fd4bafb6abb9d12ff26": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_6086462a12d54bafa59d3c4566f06cb2",
"placeholder": "​",
"style": "IPY_MODEL_7d3f3d9e15894d05a4d188ff4f466554",
"tabbable": null,
"tooltip": null,
"value": "100%"
}
},
"f1355871cc6f4dd4b50d9df5af20e5c8": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
}
},
"version_major": 2,
"version_minor": 0
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}

3
website/docs/Use-Cases/Auto-Generation.md
View File

@ -380,6 +380,9 @@ The compact history is more efficient and the individual API call history contai
[`flaml.autogen.agents`](../reference/autogen/agent/agent) contains an experimental implementation of interactive agents which can adapt to human or simulated feedback. This subpackage is under active development.
*Interested in trying it yourself? Please check the following notebook example:*
* [Use agents in FLAML to perform tasks with code](https://github.com/microsoft/FLAML/blob/main/notebook/autogen_agent_auto_feedback_from_code_execution.ipynb)
## Utilities for Applications
### Code