ag2ai · kumaranvpl · Feb 18, 2025 · Feb 18, 2025 · Feb 18, 2025
diff --git a/autogen/agentchat/contrib/agent_optimizer.py b/autogen/agentchat/contrib/agent_optimizer.py
@@ -168,7 +168,7 @@ def execute_func(name, packages, code, **args):
 
 
 class AgentOptimizer:
-    """Base class for optimizing AutoGen agents. Specifically, it is used to optimize the functions used in the agent.
+    """Base class for optimizing AG2 agents. Specifically, it is used to optimize the functions used in the agent.
     More information could be found in the following paper: https://arxiv.org/abs/2402.11359.
     """
 

diff --git a/autogen/agentchat/contrib/gpt_assistant_agent.py b/autogen/agentchat/contrib/gpt_assistant_agent.py
@@ -21,7 +21,7 @@
 
 
 class GPTAssistantAgent(ConversableAgent):
-    """An experimental AutoGen agent class that leverages the OpenAI Assistant API for conversational capabilities.
+    """An experimental AG2 agent class that leverages the OpenAI Assistant API for conversational capabilities.
     This agent is unique in its reliance on the OpenAI Assistant for state management, differing from other agents like ConversableAgent.
     """
 

diff --git a/autogen/logger/base_logger.py b/autogen/logger/base_logger.py
@@ -47,7 +47,7 @@ def log_chat_completion(
     ) -> None:
         """Log a chat completion to database.
 
-        In AutoGen, chat completions are somewhat complicated because they are handled by the `autogen.oai.OpenAIWrapper` class.
+        In AG2, chat completions are somewhat complicated because they are handled by the `autogen.oai.OpenAIWrapper` class.
         One invocation to `create` can lead to multiple underlying OpenAI calls, depending on the llm_config list used, and
         any errors or retries.
 

diff --git a/autogen/oai/bedrock.py b/autogen/oai/bedrock.py
@@ -192,7 +192,7 @@ def parse_params(self, params: dict[str, Any]) -> tuple[dict[str, Any], dict[str
         return base_params, additional_params
 
     def create(self, params) -> ChatCompletion:
-        """Run Amazon Bedrock inference and return AutoGen response"""
+        """Run Amazon Bedrock inference and return AG2 response"""
         # Set custom client class settings
         self.parse_custom_params(params)
 
@@ -522,7 +522,7 @@ def format_tools(tools: list[dict[str, Any]]) -> dict[Literal["tools"], list[dic
 
 
 def format_tool_calls(content):
-    """Converts Converse API response tool calls to AutoGen format"""
+    """Converts Converse API response tool calls to AG2 format"""
     tool_calls = []
     for tool_request in content:
         if "toolUse" in tool_request:

diff --git a/autogen/oai/cerebras.py b/autogen/oai/cerebras.py
@@ -119,7 +119,7 @@ def parse_params(self, params: dict[str, Any]) -> dict[str, Any]:
     def create(self, params: dict) -> ChatCompletion:
         messages = params.get("messages", [])
 
-        # Convert AutoGen messages to Cerebras messages
+        # Convert AG2 messages to Cerebras messages
         cerebras_messages = oai_messages_to_cerebras_messages(messages)
 
         # Parse parameters to the Cerebras API's parameters

diff --git a/autogen/oai/cohere.py b/autogen/oai/cohere.py
@@ -162,7 +162,7 @@ def create(self, params: dict) -> ChatCompletion:
         # Parse parameters to the Cohere API's parameters
         cohere_params = self.parse_params(params)
 
-        # Convert AutoGen messages to Cohere messages
+        # Convert AG2 messages to Cohere messages
         cohere_messages, preamble, final_message = oai_messages_to_cohere_messages(messages, params, cohere_params)
 
         cohere_params["chat_history"] = cohere_messages
@@ -292,8 +292,8 @@ def oai_messages_to_cohere_messages(
     We correct for any specific role orders and types.
 
     Parameters:
-        messages: list[Dict[str, Any]]: AutoGen messages
-        params: Dict[str, Any]:         AutoGen parameters dictionary
+        messages: list[Dict[str, Any]]: AG2 messages
+        params: Dict[str, Any]:         AG2 parameters dictionary
         cohere_params: Dict[str, Any]:  Cohere parameters dictionary
 
     Returns:

diff --git a/autogen/oai/gemini.py b/autogen/oai/gemini.py
@@ -371,7 +371,7 @@ def create(self, params: dict) -> ChatCompletion:
         return response_oai
 
     def _oai_content_to_gemini_content(self, message: dict[str, Any]) -> tuple[list[Any], str]:
-        """Convert AutoGen content to Gemini parts, catering for text and tool calls"""
+        """Convert AG2 content to Gemini parts, catering for text and tool calls"""
         rst = []
 
         if "role" in message and message["role"] == "tool":

diff --git a/autogen/oai/groq.py b/autogen/oai/groq.py
@@ -133,7 +133,7 @@ def parse_params(self, params: dict[str, Any]) -> dict[str, Any]:
     def create(self, params: dict) -> ChatCompletion:
         messages = params.get("messages", [])
 
-        # Convert AutoGen messages to Groq messages
+        # Convert AG2 messages to Groq messages
         groq_messages = oai_messages_to_groq_messages(messages)
 
         # Parse parameters to the Groq API's parameters

diff --git a/autogen/oai/mistral.py b/autogen/oai/mistral.py
@@ -240,7 +240,7 @@ def get_usage(response: ChatCompletion) -> dict:
 
 @require_optional_import("mistralai", "mistral")
 def tool_def_to_mistral(tool_definitions: list[dict[str, Any]]) -> list[dict[str, Any]]:
-    """Converts AutoGen tool definition to a mistral tool format"""
+    """Converts AG2 tool definition to a mistral tool format"""
     mistral_tools = []
 
     for autogen_tool in tool_definitions:

diff --git a/autogen/oai/together.py b/autogen/oai/together.py
@@ -136,7 +136,7 @@ def parse_params(self, params: dict[str, Any]) -> dict[str, Any]:
     def create(self, params: dict) -> ChatCompletion:
         messages = params.get("messages", [])
 
-        # Convert AutoGen messages to Together.AI messages
+        # Convert AG2 messages to Together.AI messages
         together_messages = oai_messages_to_together_messages(messages)
 
         # Parse parameters to Together.AI API's parameters

diff --git a/notebook/JSON_mode_example.ipynb b/notebook/JSON_mode_example.ipynb
@@ -27,7 +27,7 @@
     "\n",
     "## Requirements\n",
     "JSON mode is a feature of OpenAI API, however strong models (such as Claude 3 Opus), can generate appropriate json as well.\n",
-    "AutoGen requires `Python>=3.9`. To run this notebook example, please install:\n",
+    "AG2 requires `Python>=3.9`. To run this notebook example, please install:\n",
     "```bash\n",
     "pip install autogen\n",
     "```"

diff --git a/notebook/agentchat_MathChat.ipynb b/notebook/agentchat_MathChat.ipynb
@@ -7,7 +7,7 @@
    "source": [
     "# Auto Generated Agent Chat: Using MathChat to Solve Math Problems\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://docs.ag2.ai/docs/Use-Cases/agent_chat).\n",
+    "AG2 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://docs.ag2.ai/docs/Use-Cases/agent_chat).\n",
     "\n",
     "MathChat is an experimental conversational framework for math problem solving. In this notebook, we demonstrate how to use MathChat to solve math problems. MathChat uses the `AssistantAgent` and `MathUserProxyAgent`, which is similar to the usage of `AssistantAgent` and `UserProxyAgent` in other notebooks (e.g., [Automated Task Solving with Code Generation, Execution & Debugging](https://github.com/ag2ai/ag2/blob/main/notebook/agentchat_auto_feedback_from_code_execution.ipynb)). Essentially, `MathUserProxyAgent` implements a different auto reply mechanism corresponding to the MathChat prompts. You can find more details in the paper [An Empirical Study on Challenging Math Problem Solving with GPT-4](https://arxiv.org/abs/2306.01337) or the [blogpost](https://docs.ag2.ai/blog/2023-06-28-MathChat).\n",
     "\n",

diff --git a/notebook/agentchat_RetrieveChat.ipynb b/notebook/agentchat_RetrieveChat.ipynb
@@ -7,7 +7,7 @@
    "source": [
     "# Using RetrieveChat for Retrieve Augmented Code Generation and Question Answering\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.\n",
+    "AG2 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.\n",
     "Please find documentation about this feature [here](https://docs.ag2.ai/docs/Use-Cases/agent_chat).\n",
     "\n",
     "RetrieveChat is a conversational system for retrieval-augmented code generation and question answering. In this notebook, we demonstrate how to utilize RetrieveChat to generate code and answer questions based on customized documentations that are not present in the LLM's training dataset. RetrieveChat uses the `AssistantAgent` and `RetrieveUserProxyAgent`, which is similar to the usage of `AssistantAgent` and `UserProxyAgent` in other notebooks (e.g., [Automated Task Solving with Code Generation, Execution & Debugging](https://github.com/ag2ai/ag2/blob/main/notebook/agentchat_auto_feedback_from_code_execution.ipynb)). Essentially, `RetrieveUserProxyAgent` implement a different auto-reply mechanism corresponding to the RetrieveChat prompts.\n",
@@ -479,7 +479,7 @@
  ],
  "metadata": {
   "front_matter": {
-   "description": "Explore the use of AutoGen's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning.",
+   "description": "Explore the use of AG2's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning.",
    "tags": [
     "RAG"
    ]

diff --git a/notebook/agentchat_RetrieveChat_couchbase.ipynb b/notebook/agentchat_RetrieveChat_couchbase.ipynb
@@ -7,7 +7,7 @@
             "source": [
                 "# Using RetrieveChat Powered by Couchbase Capella for Retrieve Augmented Code Generation and Question Answering\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.\n",
+                "AG2 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.\n",
                 "Please find documentation about this feature [here](https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat).\n",
                 "\n",
                 "RetrieveChat is a conversational system for retrieval-augmented code generation and question answering. In this notebook, we demonstrate how to utilize RetrieveChat to generate code and answer questions based on customized documentations that are not present in the LLM's training dataset. RetrieveChat uses the `AssistantAgent` and `RetrieveUserProxyAgent`, which is similar to the usage of `AssistantAgent` and `UserProxyAgent` in other notebooks (e.g., [Automated Task Solving with Code Generation, Execution & Debugging](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_auto_feedback_from_code_execution.ipynb)). Essentially, `RetrieveUserProxyAgent` implement a different auto-reply mechanism corresponding to the RetrieveChat prompts.\n",
@@ -578,7 +578,7 @@
     ],
     "metadata": {
         "front_matter": {
-            "description": "Explore the use of AutoGen's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning.",
+            "description": "Explore the use of AG2's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning.",
             "tags": [
                 "RAG"
             ]

diff --git a/notebook/agentchat_RetrieveChat_mongodb.ipynb b/notebook/agentchat_RetrieveChat_mongodb.ipynb
@@ -7,7 +7,7 @@
    "source": [
     "# Using RetrieveChat Powered by MongoDB Atlas for Retrieve Augmented Code Generation and Question Answering\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.\n",
+    "AG2 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.\n",
     "Please find documentation about this feature [here](https://docs.ag2.ai/docs/Use-Cases/agent_chat).\n",
     "\n",
     "RetrieveChat is a conversational system for retrieval-augmented code generation and question answering. In this notebook, we demonstrate how to utilize RetrieveChat to generate code and answer questions based on customized documentations that are not present in the LLM's training dataset. RetrieveChat uses the `AssistantAgent` and `RetrieveUserProxyAgent`, which is similar to the usage of `AssistantAgent` and `UserProxyAgent` in other notebooks (e.g., [Automated Task Solving with Code Generation, Execution & Debugging](https://github.com/ag2ai/ag2/blob/main/notebook/agentchat_auto_feedback_from_code_execution.ipynb)). Essentially, `RetrieveUserProxyAgent` implement a different auto-reply mechanism corresponding to the RetrieveChat prompts.\n",
@@ -551,7 +551,7 @@
  ],
  "metadata": {
   "front_matter": {
-   "description": "Explore the use of AutoGen's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning.",
+   "description": "Explore the use of AG2's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning.",
    "tags": [
     "MongoDB",
     "integration",

diff --git a/notebook/agentchat_RetrieveChat_pgvector.ipynb b/notebook/agentchat_RetrieveChat_pgvector.ipynb
@@ -7,7 +7,7 @@
    "source": [
     "# Using RetrieveChat Powered by PGVector for Retrieve Augmented Code Generation and Question Answering\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.\n",
+    "AG2 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.\n",
     "Please find documentation about this feature [here](https://docs.ag2.ai/docs/Use-Cases/agent_chat).\n",
     "\n",
     "RetrieveChat is a conversational system for retrieval-augmented code generation and question answering. In this notebook, we demonstrate how to utilize RetrieveChat to generate code and answer questions based on customized documentations that are not present in the LLM's training dataset. RetrieveChat uses the `AssistantAgent` and `RetrieveUserProxyAgent`, which is similar to the usage of `AssistantAgent` and `UserProxyAgent` in other notebooks (e.g., [Automated Task Solving with Code Generation, Execution & Debugging](https://github.com/ag2ai/ag2/blob/main/notebook/agentchat_auto_feedback_from_code_execution.ipynb)). Essentially, `RetrieveUserProxyAgent` implement a different auto-reply mechanism corresponding to the RetrieveChat prompts.\n",
@@ -1485,7 +1485,7 @@
  ],
  "metadata": {
   "front_matter": {
-   "description": "Explore the use of AutoGen's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning.",
+   "description": "Explore the use of AG2's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning.",
    "tags": [
     "PGVector",
     "integration",

diff --git a/notebook/agentchat_RetrieveChat_qdrant.ipynb b/notebook/agentchat_RetrieveChat_qdrant.ipynb
@@ -276,9 +276,9 @@
       "    <br>\n",
       "</p>\n",
       "\n",
-      ":fire: Heads-up: We have migrated [AutoGen](https://docs.ag2.ai/) into a dedicated [github repository](https://github.com/ag2ai/ag2). Alongside this move, we have also launched a dedicated [Discord](https://discord.gg/pAbnFJrkgZ) server and a [website](https://docs.ag2.ai/) for comprehensive documentation.\n",
+      ":fire: Heads-up: We have migrated [AG2](https://docs.ag2.ai/) into a dedicated [github repository](https://github.com/ag2ai/ag2). Alongside this move, we have also launched a dedicated [Discord](https://discord.gg/pAbnFJrkgZ) server and a [website](https://docs.ag2.ai/) for comprehensive documentation.\n",
       "\n",
-      ":fire: The automated multi-agent chat framework in [AutoGen](https://docs.ag2.ai/) is in preview from v2.0.0.\n",
+      ":fire: The automated multi-agent chat framework in [AG2](https://docs.ag2.ai/) is in preview from v2.0.0.\n",
       "\n",
       ":fire: FLAML is highlighted in OpenAI's [cookbook](https://github.com/openai/openai-cookbook#related-resources-from-around-the-web).\n",
       "\n",

diff --git a/notebook/agentchat_cost_token_tracking.ipynb b/notebook/agentchat_cost_token_tracking.ipynb
@@ -4,8 +4,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Usage tracking with AutoGen\n",
-    "## 1. Use AutoGen's OpenAIWrapper for cost estimation\n",
+    "# Usage tracking with AG2\n",
+    "## 1. Use AG2's OpenAIWrapper for cost estimation\n",
     "The `OpenAIWrapper` from `autogen` tracks token counts and costs of your API calls. Use the `create()` method to initiate requests and `print_usage_summary()` to retrieve a detailed usage report, including total cost and token usage for both cached and actual requests.\n",
     "\n",
     "- `mode=[\"actual\", \"total\"]` (default): print usage summary for non-caching completions and all completions (including cache).\n",
@@ -21,7 +21,7 @@
     "To gather usage data for a list of agents, we provide an utility function `autogen.gather_usage_summary(agents)` where you pass in a list of agents and gather the usage summary.\n",
     "\n",
     "## 3. Custom token price for up-to-date cost estimation\n",
-    "AutoGen tries to keep the token prices up-to-date. However, you can pass in a `price` field in `config_list` if the token price is not listed or up-to-date. Please creating an issue or pull request to help us keep the token prices up-to-date!\n",
+    "AG2 tries to keep the token prices up-to-date. However, you can pass in a `price` field in `config_list` if the token price is not listed or up-to-date. Please creating an issue or pull request to help us keep the token prices up-to-date!\n",
     "\n",
     "Note: in json files, the price should be a list of two floats.\n",
     "\n",
@@ -41,7 +41,7 @@
     "\n",
     "## Requirements\n",
     "\n",
-    "AutoGen requires `Python>=3.9`:\n",
+    "AG2 requires `Python>=3.9`:\n",
     "```bash\n",
     "pip install \"pyautogen\"\n",
     "```"

diff --git a/notebook/agentchat_dalle_and_gpt4v.ipynb b/notebook/agentchat_dalle_and_gpt4v.ipynb
@@ -291,7 +291,7 @@
     "# Ask the question with an image\n",
     "user_proxy.initiate_chat(\n",
     "    dalle,\n",
-    "    message=\"\"\"Create an image with black background, a happy robot is showing a sign with \"I Love AutoGen\".\"\"\",\n",
+    "    message=\"\"\"Create an image with black background, a happy robot is showing a sign with \"I Love AG2\".\"\"\",\n",
     ")"
    ]
   },
@@ -424,7 +424,7 @@
     "user_proxy = UserProxyAgent(name=\"User\", human_input_mode=\"NEVER\", max_consecutive_auto_reply=0)\n",
     "\n",
     "user_proxy.initiate_chat(\n",
-    "    creator, message=\"\"\"Create an image with black background, a happy robot is showing a sign with \"I Love AutoGen\".\"\"\"\n",
+    "    creator, message=\"\"\"Create an image with black background, a happy robot is showing a sign with \"I Love AG2\".\"\"\"\n",
     ")"
    ]
   }