A programming framework for agentic AI
adjust order of side bars (#2040)
Chi Wangcc836de13d11
diff --git a/autogen/agentchat/chat.py b/autogen/agentchat/chat.pyindex 312930f00..bd4559ff4 100644--- a/autogen/agentchat/chat.py+++ b/autogen/agentchat/chat.py@@ -139,20 +139,20 @@ def initiate_chats(chat_queue: List[Dict[str, Any]]) -> List[ChatResult]:Args:chat_queue (List[Dict]): a list of dictionaries containing the information about the chats.- Each dictionary should contain the input arguments for `ConversableAgent.initiate_chat`. For example:- "sender": the sender agent.- "recipient": the recipient agent.- "clear_history" (bool): whether to clear the chat history with the agent. Default is True.- "silent" (bool or None): (Experimental) whether to print the messages in this conversation. Default is False.- "cache" (Cache or None): the cache client to use for this conversation. Default is None.- "max_turns" (int or None): maximum number of turns for the chat. If None, the chat will continue until a termination condition is met. Default is None.- "summary_method" (str or callable): a string or callable specifying the method to get a summary from the chat. Default is DEFAULT_summary_method, i.e., "last_msg".- "summary_args" (dict): a dictionary of arguments to be passed to the summary_method. Default is {}.- "message" (str, callable or None): if None, input() will be called to get the initial message.- **context: additional context information to be passed to the chat.- "carryover": It can be used to specify the carryover information to be passed to this chat.- If provided, we will combine this carryover with the "message" content when generating the initial chat- message in `generate_init_message`.+ Each dictionary should contain the input arguments for [`ConversableAgent.initiate_chat`](/docs/reference/agentchat/conversable_agent#initiate_chat). For example:+ - "sender": the sender agent.+ - "recipient": the recipient agent.+ - "clear_history" (bool): whether to clear the chat history with the agent. Default is True.+ - "silent" (bool or None): (Experimental) whether to print the messages in this conversation. Default is False.+ - "cache" (Cache or None): the cache client to use for this conversation. Default is None.+ - "max_turns" (int or None): maximum number of turns for the chat. If None, the chat will continue until a termination condition is met. Default is None.+ - "summary_method" (str or callable): a string or callable specifying the method to get a summary from the chat. Default is DEFAULT_summary_method, i.e., "last_msg".+ - "summary_args" (dict): a dictionary of arguments to be passed to the summary_method. Default is {}.+ - "message" (str, callable or None): if None, input() will be called to get the initial message.+ - **context: additional context information to be passed to the chat.+ - "carryover": It can be used to specify the carryover information to be passed to this chat.+ If provided, we will combine this carryover with the "message" content when generating the initial chat+ message in `generate_init_message`.Returns:(list): a list of ChatResult objects corresponding to the finished chats in the chat_queue.diff --git a/autogen/agentchat/conversable_agent.py b/autogen/agentchat/conversable_agent.pyindex b42973652..838af6e7d 100644--- a/autogen/agentchat/conversable_agent.py+++ b/autogen/agentchat/conversable_agent.py@@ -296,18 +296,18 @@ class ConversableAgent(LLMAgent):from both sync and async chats. However, an async reply function will only be triggered from asyncchats (initiated with `ConversableAgent.a_initiate_chat`). If an `async` reply function is registeredand a chat is initialized with a sync function, `ignore_async_in_sync_chat` determines the behaviour as follows:- - if `ignore_async_in_sync_chat` is set to `False` (default value), an exception will be raised, and- - if `ignore_async_in_sync_chat` is set to `True`, the reply function will be ignored.+ if `ignore_async_in_sync_chat` is set to `False` (default value), an exception will be raised, and+ if `ignore_async_in_sync_chat` is set to `True`, the reply function will be ignored.Args:trigger (Agent class, str, Agent instance, callable, or list): the trigger.- - If a class is provided, the reply function will be called when the sender is an instance of the class.- - If a string is provided, the reply function will be called when the sender's name matches the string.- - If an agent instance is provided, the reply function will be called when the sender is the agent instance.- - If a callable is provided, the reply function will be called when the callable returns True.- - If a list is provided, the reply function will be called when any of the triggers in the list is activated.- - If None is provided, the reply function will be called only when the sender is None.- Note: Be sure to register `None` as a trigger if you would like to trigger an auto-reply function with non-empty messages and `sender=None`.+ If a class is provided, the reply function will be called when the sender is an instance of the class.+ If a string is provided, the reply function will be called when the sender's name matches the string.+ If an agent instance is provided, the reply function will be called when the sender is the agent instance.+ If a callable is provided, the reply function will be called when the callable returns True.+ If a list is provided, the reply function will be called when any of the triggers in the list is activated.+ If None is provided, the reply function will be called only when the sender is None.+ Note: Be sure to register `None` as a trigger if you would like to trigger an auto-reply function with non-empty messages and `sender=None`.reply_func (Callable): the reply function.The function takes a recipient agent, a list of messages, a sender agent and a config as input and returns a reply message.position: the position of the reply function in the reply function list.@@ -880,66 +880,71 @@ class ConversableAgent(LLMAgent):silent (bool or None): (Experimental) whether to print the messages for this conversation. Default is False.cache (Cache or None): the cache client to be used for this conversation. Default is None.max_turns (int or None): the maximum number of turns for the chat between the two agents. One turn means one conversation round trip. Note that this is different from- [max_consecutive_auto_reply](#max_consecutive_auto_reply) which is the maximum number of consecutive auto replies; and it is also different from [max_rounds in GroupChat](./groupchat#groupchat-objects) which is the maximum number of rounds in a group chat session.- If max_turns is set to None, the chat will continue until a termination condition is met. Default is None.- summary_method (string or callable) : a method to get a summary from the chat. Default is DEFAULT_SUMMARY_METHOD, i.e., "last_msg".- - Supported string are "last_msg" and "reflection_with_llm":- when set "last_msg", it returns the last message of the dialog as the summary.- when set "reflection_with_llm", it returns a summary extracted using an llm client.- `llm_config` must be set in either the recipient or sender.- "reflection_with_llm" requires the llm_config to be set in either the sender or the recipient.- - A callable summary_method should take the recipient and sender agent in a chat as input and return a string of summary. E.g,- ```python- def my_summary_method(- sender: ConversableAgent,- recipient: ConversableAgent,- summary_args: dict,- ):- return recipient.last_message(sender)["content"]- ```+ [max_consecutive_auto_reply](#max_consecutive_auto_reply) which is the maximum number of consecutive auto replies; and it is also different from [max_rounds in GroupChat](./groupchat#groupchat-objects) which is the maximum number of rounds in a group chat session.+ If max_turns is set to None, the chat will continue until a termination condition is met. Default is None.+ summary_method (str or callable): a method to get a summary from the chat. Default is DEFAULT_SUMMARY_METHOD, i.e., "last_msg".++ Supported strings are "last_msg" and "reflection_with_llm":+ - when set to "last_msg", it returns the last message of the dialog as the summary.+ - when set to "reflection_with_llm", it returns a summary extracted using an llm client.+ `llm_config` must be set in either the recipient or sender.++ A callable summary_method should take the recipient and sender agent in a chat as input and return a string of summary. E.g.,++ ```python+ def my_summary_method(+ sender: ConversableAgent,+ recipient: ConversableAgent,+ summary_args: dict,+ ):+ return recipient.last_message(sender)["content"]+ ```summary_args (dict): a dictionary of arguments to be passed to the summary_method.- E.g., a string of text used to prompt a LLM-based agent (the sender or receiver agent) to reflext- on the conversation and extract a summary when summary_method is "reflection_with_llm".- Default is DEFAULT_SUMMARY_PROMPT, i.e., "Summarize takeaway from the conversation. Do not add any introductory phrases. If the intended request is NOT properly addressed, please point it out."+ One example key is "summary_prompt", and value is a string of text used to prompt a LLM-based agent (the sender or receiver agent) to reflect+ on the conversation and extract a summary when summary_method is "reflection_with_llm".+ The default summary_prompt is DEFAULT_SUMMARY_PROMPT, i.e., "Summarize takeaway from the conversation. Do not add any introductory phrases. If the intended request is NOT properly addressed, please point it out."message (str, dict or Callable): the initial message to be sent to the recipient. Needs to be provided. Otherwise, input() will be called to get the initial message.- - If a string or a dict is provided, it will be used as the initial message. `generate_init_message` is called to generate the initial message for the agent based on this string and the context.- If dict, it may contain the following reserved fields (either content or function_call need to be provided).- 1. "content": content of the message, can be None.- 2. "function_call": a dictionary containing the function name and arguments. (deprecated in favor of "tool_calls")- 3. "tool_calls": a list of dictionaries containing the function name and arguments.- 4. "role": role of the message, can be "assistant", "user", "function".- This field is only needed to distinguish between "function" or "assistant"/"user".- 5. "name": In most cases, this field is not needed. When the role is "function", this field is needed to indicate the function name.- 6. "context" (dict): the context of the message, which will be passed to- [OpenAIWrapper.create](../oai/client#create).- - If a callable is provided, it will be called to get the initial message in the form of a string or a dict. If the returned value is a dict, it should contain the following reserved fields:+ - If a string or a dict is provided, it will be used as the initial message. `generate_init_message` is called to generate the initial message for the agent based on this string and the context.+ If dict, it may contain the following reserved fields (either content or tool_calls need to be provided).++ 1. "content": content of the message, can be None.+ 2. "function_call": a dictionary containing the function name and arguments. (deprecated in favor of "tool_calls")+ 3. "tool_calls": a list of dictionaries containing the function name and arguments.+ 4. "role": role of the message, can be "assistant", "user", "function".+ This field is only needed to distinguish between "function" or "assistant"/"user".+ 5. "name": In most cases, this field is not needed. When the role is "function", this field is needed to indicate the function name.+ 6. "context" (dict): the context of the message, which will be passed to+ [OpenAIWrapper.create](../oai/client#create).++ - If a callable is provided, it will be called to get the initial message in the form of a string or a dict.If the returned type is dict, it may contain the reserved fields mentioned above.Example of a callable message (returning a string):- ```python- def my_message(sender: ConversableAgent, recipient: ConversableAgent, context: dict) -> Union[str, Dict]:- carryover = context.get("carryover", "")- if isinstance(message, list):- carryover = carryover[-1]- final_msg = "Write a blogpost." + "\nContext: \n" + carryover- return final_msg- ```++ ```python+ def my_message(sender: ConversableAgent, recipient: ConversableAgent, context: dict) -> Union[str, Dict]:+ carryover = context.get("carryover", "")+ if isinstance(message, list):+ carryover = carryover[-1]+ final_msg = "Write a blogpost." + "\\nContext: \\n" + carryover+ return final_msg+ ```Example of a callable message (returning a dict):- ```python- def my_message(sender: ConversableAgent, recipient: ConversableAgent, context: dict) -> Union[str, Dict]:- final_msg = {}- carryover = context.get("carryover", "")- carryover = context.get("carryover", "")- if isinstance(message, list):- carryover = carryover[-1]- final_msg["content"] = "Write a blogpost." + "\nContext: \n" + carryover- final_msg["context"] = {"prefix": "Today I feel"}- return final_msg- ```++ ```python+ def my_message(sender: ConversableAgent, recipient: ConversableAgent, context: dict) -> Union[str, Dict]:+ final_msg = {}+ carryover = context.get("carryover", "")+ if isinstance(message, list):+ carryover = carryover[-1]+ final_msg["content"] = "Write a blogpost." + "\\nContext: \\n" + carryover+ final_msg["context"] = {"prefix": "Today I feel"}+ return final_msg+ ```**context: any context information. It has the following reserved fields:- "carryover": a string or a list of string to specify the carryover information to be passed to this chat.- If provided, we will combine this carryover (by attaching a "context: "string and the carryover content after the message content) with the "message" content when generating the initial chat+ - "carryover": a string or a list of string to specify the carryover information to be passed to this chat.+ If provided, we will combine this carryover (by attaching a "context: " string and the carryover content after the message content) with the "message" content when generating the initial chatmessage in `generate_init_message`.Raises:diff --git a/autogen/version.py b/autogen/version.pyindex 04d1c7c53..198d6db62 100644--- a/autogen/version.py+++ b/autogen/version.py@@ -1 +1 @@-__version__ = "0.2.19"+__version__ = "0.2.20"diff --git a/test/agentchat/test_async_chats.py b/test/agentchat/test_async_chats.pyindex 8ad0216a7..95a54f4cf 100755--- a/test/agentchat/test_async_chats.py+++ b/test/agentchat/test_async_chats.py@@ -1,15 +1,14 @@#!/usr/bin/env python3 -m pytest-from autogen import AssistantAgent, UserProxyAgent-from autogen import GroupChat, GroupChatManager-import asyncio-from test_assistant_agent import KEY_LOC, OAI_CONFIG_LISTimport pytest-from conftest import skip_openai+import sys+import osimport autogen-from typing import Literal-from typing_extensions import Annotated-from autogen import initiate_chats+from autogen import AssistantAgent, UserProxyAgent+from test_assistant_agent import KEY_LOC, OAI_CONFIG_LIST++sys.path.append(os.path.join(os.path.dirname(__file__), ".."))+from conftest import skip_openai # noqa: E402@pytest.mark.skipif(skip_openai, reason="requested to skip openai tests")@@ -31,6 +30,7 @@ async def test_async_chats():financial_assistant_1 = AssistantAgent(name="Financial_assistant_1",llm_config={"config_list": config_list},+ system_message="You are a knowledgeable AI Assistant.",)financial_assistant_2 = AssistantAgent(name="Financial_assistant_2",@@ -60,7 +60,7 @@ async def test_async_chats():)def my_summary_method(recipient, sender, summary_args):- return recipient.chat_messages[sender][0].get("content", "")+ return recipient.chat_messages[sender][-1].get("content", "")chat_res = await user.a_initiate_chats([@@ -78,6 +78,7 @@ async def test_async_chats():"message": financial_tasks[1],"silent": True,"summary_method": "reflection_with_llm",+ "max_turns": 3,},{"chat_id": 3,diff --git a/test/agentchat/test_conversable_agent.py b/test/agentchat/test_conversable_agent.pyindex b48279ac6..5c5676dd1 100755--- a/test/agentchat/test_conversable_agent.py+++ b/test/agentchat/test_conversable_agent.py@@ -10,7 +10,6 @@ import inspectfrom unittest.mock import MagicMockimport pytest-from unittest.mock import patchfrom pydantic import BaseModel, Fieldfrom typing_extensions import Annotatedimport autogen@@ -19,16 +18,12 @@ from autogen.agentchat import ConversableAgent, UserProxyAgentfrom autogen.agentchat.conversable_agent import register_functionfrom autogen.exception_utils import InvalidCarryOverType, SenderRequiredfrom test_assistant_agent import KEY_LOC, OAI_CONFIG_LIST-from conftest import MOCK_OPEN_AI_API_KEY, skip_openai-try:- import openai-except ImportError:- skip = True-else:- skip = False or skip_openai+sys.path.append(os.path.join(os.path.dirname(__file__), ".."))+from conftest import MOCK_OPEN_AI_API_KEY, skip_openai # noqa: E402here = os.path.abspath(os.path.dirname(__file__))+REASON = "requested to skip openai tests"@pytest.fixture@@ -921,8 +916,8 @@ def test_register_functions():@pytest.mark.skipif(- skip or not sys.version.startswith("3.10"),- reason="do not run if openai is not installed or py!=3.10",+ skip_openai,+ reason=REASON,)def test_function_registration_e2e_sync() -> None:config_list = autogen.config_list_from_json(@@ -998,8 +993,8 @@ def test_function_registration_e2e_sync() -> None:@pytest.mark.skipif(- skip or not sys.version.startswith("3.10"),- reason="do not run if openai is not installed or py!=3.10",+ skip_openai,+ reason=REASON,)@pytest.mark.asyncio()async def test_function_registration_e2e_async() -> None:@@ -1075,7 +1070,7 @@ async def test_function_registration_e2e_async() -> None:stopwatch_mock.assert_called_once_with(num_seconds="5")[email protected](skip_openai, reason="requested to skip openai tests")[email protected](skip_openai, reason=REASON)def test_max_turn():config_list = autogen.config_list_from_json(OAI_CONFIG_LIST, KEY_LOC)@@ -1097,7 +1092,7 @@ def test_max_turn():assert len(res.chat_history) <= 6[email protected](skip, reason="openai not installed OR requested to skip")[email protected](skip_openai, reason=REASON)def test_message_func():import random@@ -1153,7 +1148,7 @@ def test_message_func():print(chat_res_play.summary)[email protected](skip, reason="openai not installed OR requested to skip")[email protected](skip_openai, reason=REASON)def test_summary():import randomdiff --git a/website/docs/topics/prompting-and-reasoning/reflection.ipynb b/website/docs/topics/prompting-and-reasoning/reflection.ipynbindex a042c45e8..24fcb6a0f 100644--- a/website/docs/topics/prompting-and-reasoning/reflection.ipynb+++ b/website/docs/topics/prompting-and-reasoning/reflection.ipynb@@ -8,7 +8,9 @@"source": ["# LLM Reflection\n","\n",- "AutoGen supports different LLM prompting and reasoning strategies, such as ReAct, Reflection/Self-Critique, and more. This notebook demonstrates how to realize general LLM reflection with AutoGen. Reflection is a general prompting strategy which involves having LLMs analyze their own outputs, behaviors, knowledge, or reasoning processes."+ "AutoGen supports different LLM prompting and reasoning strategies, such as ReAct, Reflection/Self-Critique, and more. This notebook demonstrates how to realize general LLM reflection with AutoGen. Reflection is a general prompting strategy which involves having LLMs analyze their own outputs, behaviors, knowledge, or reasoning processes.\n",+ "\n",+ "This example leverages a generic interface [nested chats](/docs/tutorial/conversation-patterns#nested-chats) to implement the reflection using multi-agents."]},{diff --git a/website/docs/tutorial/conversation-patterns.ipynb b/website/docs/tutorial/conversation-patterns.ipynbindex c3da6fda0..2763787bd 100644--- a/website/docs/tutorial/conversation-patterns.ipynb+++ b/website/docs/tutorial/conversation-patterns.ipynb@@ -1524,9 +1524,9 @@"metadata": {},"source": ["The implementation of the nested chats handler makes use of the\n",- "[`registered_reply`](../reference/agentchat/conversable_agent/#register_reply)\n",+ "[`register_reply`](../reference/agentchat/conversable_agent/#register_reply)\n","method, which allows you to make extensive customization to\n",- " `ConversableAgent`."+ " `ConversableAgent`. The GroupChatManager uses the same mechanism to implement the group chat."]},{@@ -1537,7 +1537,7 @@"\n","In this chapter, we covered two-agent chat, sequential chat, group chat,\n","and nested chat patterns. You can compose these patterns like LEGO blocks to \n",- "create complex workflows.\n",+ "create complex workflows. You can also use [`register_reply`](../reference/agentchat/conversable_agent/#register_reply) to create new patterns.\n","\n","This is the last chapter on basic AutoGen concepts. \n","In the next chatper, we will give you some tips on what to do next."diff --git a/website/sidebars.js b/website/sidebars.jsindex f88e660f6..1abe16d68 100644--- a/website/sidebars.js+++ b/website/sidebars.js@@ -11,7 +11,17 @@module.exports = {docsSidebar: [- 'Getting-Started',+ 'Getting-Started',+ {+ type: "category",+ label: "Installation",+ collapsed: true,+ items: ["installation/Docker", "installation/Optional-Dependencies"],+ link: {+ type: 'doc',+ id: "installation/Installation"+ },+ },{type: 'category',label: 'Tutorial',@@ -48,16 +58,7 @@}],},- {- type: "category",- label: "Installation",- collapsed: true,- items: ["installation/Docker", "installation/Optional-Dependencies"],- link: {- type: 'doc',- id: "installation/Installation"- },- },+ {'Use Cases': [{type: 'autogenerated', dirName: 'Use-Cases'}]},{type: 'category',label: 'Topics',@@ -67,8 +68,8 @@description: 'Learn about various topics in AutoGen',slug: 'topics',},- items: [{type: 'autogenerated', dirName: 'topics'}]},- {'Use Cases': [{type: 'autogenerated', dirName: 'Use-Cases'}]},+ items: [{type: 'autogenerated', dirName: 'topics'}]+ },'Contribute','Research',{'Ecosystem': [{type: 'autogenerated', dirName: 'ecosystem'}]},@@ -89,6 +90,5 @@id: "notebooks"},},-]};