bump version to 0.2.22 (#2256)

* bump version to 0.2.22

* doc update

* link update

* consider the failure case

README.md

@@ -233,7 +233,7 @@ contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additio
 
 ## Contributors Wall
 <a href="https://github.com/microsoft/autogen/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=microsoft/autogen&max=200" />
+  <img src="https://contrib.rocks/image?repo=microsoft/autogen&max=204" />
 </a>
 
 # Legal Notices

autogen/version.py

@@ -1 +1 @@
-__version__ = "0.2.21"
+__version__ = "0.2.22"

notebook/agentchat_capability_long_context_handling.ipynb

@@ -664,13 +664,6 @@
   }
  ],
  "metadata": {
-  "front_matter": {
-   "description": "Use the TransformChatHistory capability to handle long contexts",
-   "tags": [
-    "long context handling",
-    "capability"
-   ]
-  },
   "kernelspec": {
    "display_name": "Python 3",
    "language": "python",

notebook/agentchat_compression.ipynb

@@ -853,10 +853,6 @@
   }
  ],
  "metadata": {
-  "front_matter": {
-   "description": "Learn about the CompressibleAgent",
-   "tags": []
-  },
   "kernelspec": {
    "display_name": "msft",
    "language": "python",

notebook/agentchat_function_call_async.ipynb

@@ -364,8 +364,8 @@
   "front_matter": {
    "description": "Learn how to implement both synchronous and asynchronous function calls using AssistantAgent and UserProxyAgent in AutoGen, with examples of their application in individual and group chat settings for task execution with language models.",
    "tags": [
-    "code generation",
     "function call",
+    "tool use",
     "async"
    ]
   },

notebook/agentchat_function_call_currency_calculator.ipynb

@@ -6,7 +6,7 @@
    "id": "ae1f50ec",
    "metadata": {},
    "source": [
-    "<a href=\"https://colab.research.google.com/github/microsoft/autogen/blob/main/notebook/agentchat_function_call_currency_calculator.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+    "# Currency Calculator: Task Solving with Provided Tools as Functions\n"
    ]
   },
   {
@@ -15,8 +15,6 @@
    "id": "9a71fa36",
    "metadata": {},
    "source": [
-    "# Currency Calculator: Task Solving with Provided Tools as Functions\n",
-    "\n",
     "AutoGen offers conversable agents powered by LLM, tool, or human, which can be used to perform tasks collectively via automated chat. This framework allows tool use and human participation through multi-agent conversation. Please find documentation about this feature [here](https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat).\n",
     "\n",
     "In this notebook, we demonstrate how to use `AssistantAgent` and `UserProxyAgent` to make function calls with the new feature of OpenAI models (in model version 0613). A specified prompt and function configs must be passed to `AssistantAgent` to initialize the agent. The corresponding functions must be passed to `UserProxyAgent`, which will execute any function calls made by `AssistantAgent`. Besides this requirement of matching descriptions with functions, we recommend checking the system message in the `AssistantAgent` to ensure the instructions align with the function call descriptions.\n",
@@ -591,23 +589,30 @@
   }
  ],
  "metadata": {
-  "kernelspec": {
-   "display_name": "flaml_dev",
-   "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": "3.10.13"
-  }
+    "front_matter": {
+        "description": "Learn how to register function calls using AssistantAgent and UserProxyAgent in AutoGen.",
+        "tags": [
+            "function call",
+            "tool use"
+        ]
+    },
+    "kernelspec": {
+        "display_name": "flaml_dev",
+        "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": "3.10.13"
+    }
  },
  "nbformat": 4,
  "nbformat_minor": 5

notebook/agentchat_multi_task_async_chats.ipynb

@@ -1737,7 +1737,8 @@
   "front_matter": {
    "description": "Use conversational agents to solve a set of tasks with a sequence of async chats.",
    "tags": [
-    "sequential chat"
+    "orchestration",
+    "sequential chats"
    ]
   },
   "kernelspec": {

notebook/agentchat_multi_task_chats.ipynb

@@ -1533,7 +1533,8 @@
   "front_matter": {
    "description": "Use conversational agents to solve a set of tasks with a sequence of chats.",
    "tags": [
-    "sequential chat"
+    "orchestration",
+    "sequential chats"
    ]
   },
   "kernelspec": {

notebook/agentchat_nested_chats_chess.ipynb

@@ -1129,7 +1129,7 @@
    "source": [
     "In the output above, you can see \"Start a new chat\" is displayed\n",
     "whenever a new nested chat is started between the board proxy agent and a player agent.\n",
-    "The \"carryover\" empty as it is a new chat in the sequence."
+    "The \"carryover\" is empty as it is a new chat in the sequence."
    ]
   }
  ],
@@ -1137,7 +1137,9 @@
   "front_matter": {
    "description": "LLM-backed agents playing chess with each other using nested chats.",
    "tags": [
-    "nested chat"
+    "nested chat",
+    "tool use",
+    "orchestration"
    ]
   },
   "kernelspec": {

notebook/agentchat_nested_sequential_chats.ipynb

@@ -811,7 +811,7 @@
   "front_matter": {
    "description": "Solve complex tasks with one or more sequence chats nested as inner monologue.",
    "tags": [
-    "nested chat", "sequential chat"
+    "nested chat", "sequential chats", "orchestration"
    ]
   },
   "kernelspec": {

notebook/agentchat_nestedchat.ipynb

@@ -664,7 +664,8 @@
   "front_matter": {
    "description": "Solve complex tasks with a chat nested as inner monologue.",
    "tags": [
-    "nested chat"
+    "nested chat",
+    "orchestration"
    ]
   },
   "kernelspec": {

notebook/agentchat_nestedchat_optiguide.ipynb

@@ -1122,7 +1122,9 @@
   "front_matter": {
    "description": "This is a nested chat re-implementation of OptiGuide which is an LLM-based supply chain optimization framework.",
    "tags": [
-    "nested chat"
+    "nested chat",
+    "hierarchical chat",
+    "orchestration"
    ]
   },
   "kernelspec": {

notebook/agentchat_society_of_mind.ipynb

@@ -357,7 +357,7 @@
  ],
  "metadata": {
   "front_matter": {
-    "tags": ["orchestration"],
+    "tags": ["orchestration", "nested chat"],
     "description": "Explore the demonstration of the SocietyOfMindAgent in the AutoGen library, which runs a group chat as an internal monologue, but appears to the external world as a single agent, offering a structured way to manage complex interactions among multiple agents and handle issues such as extracting responses from complex dialogues and dealing with context window constraints."
   },
   "kernelspec": {

notebook/agentchats_sequential_chats.ipynb

@@ -1128,6 +1128,7 @@
   "front_matter": {
    "description": "Use AutoGen to solve a set of tasks with a sequence of chats.",
    "tags": [
+    "orchestration",
     "sequential chats"
    ]
   },

test/agentchat/test_agent_logging.py

@@ -103,10 +103,13 @@ def test_two_agents_logging(db_connection):
         first_request_message = request["messages"][0]["content"]
         first_request_role = request["messages"][0]["role"]
 
-        if idx == 0 or idx == 2:
+        # some config may fail
+        if idx == 0 or idx == len(rows) - 1:
             assert first_request_message == TEACHER_MESSAGE
-        elif idx == 1:
+        elif idx == 1 and len(rows) == 3:
             assert first_request_message == STUDENT_MESSAGE
+        else:
+            assert first_request_message in (TEACHER_MESSAGE, STUDENT_MESSAGE)
         assert first_request_role == "system"
 
         response = json.loads(row["response"])

website/docs/Examples.md

@@ -45,7 +45,7 @@ Links to notebook examples:
 ### Tool Use
 
 - **Web Search**: Solve Tasks Requiring Web Info - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_web_info.ipynb)
-- Use Provided Tools as Functions - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_function_call.ipynb)
+- Use Provided Tools as Functions - [View Notebook](/docs/notebooks/agentchat_function_call_currency_calculator)
 - Use Tools via Sync and Async Function Calling - [View Notebook](/docs/notebooks/agentchat_function_call_async)
 - Task Solving with Langchain Provided Tools as Functions - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_langchain.ipynb)
 - **RAG**: Group Chat with Retrieval Augmented Generation (with 5 group member agents and 1 manager agent) - [View Notebook](/docs/notebooks/agentchat_groupchat_RAG)
@@ -87,7 +87,7 @@ Links to notebook examples:
 ### Long Context Handling
 
 <!-- - Conversations with Chat History Compression Enabled - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_compression.ipynb) -->
-- Long Context Handling as A Capability - [View Notebook](/docs/notebooks/agentchat_capability_long_context_handling)
+- Long Context Handling as A Capability - [View Notebook](/docs/notebooks/agentchat_transform_messages)
 
 ### Evaluation and Assessment
 

website/docs/tutorial/what-next.md

@@ -25,7 +25,7 @@ topics:
 
 ## Dig Deeper
 
-- Read the [topic docs](/docs/topics) to learn more
+- Read the [user guide](/docs/topics) to learn more
 - Read the examples and guides in the [notebooks section](/docs/notebooks)
 - Check [research](/docs/Research) and [blog](/blog)