ag2 0.7.3__tar.gz → 0.7.4b2__tar.gz

{ag2-0.7.3/ag2.egg-info → ag2-0.7.4b2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ag2
-Version: 0.7.3
+Version: 0.7.4b2
 Summary: Alias package for pyautogen
 Home-page: https://github.com/ag2ai/ag2
 Author: Chi Wang & Qingyun Wu
@@ -49,6 +49,9 @@ Provides-Extra: groq
 Provides-Extra: cohere
 Provides-Extra: ollama
 Provides-Extra: bedrock
+Provides-Extra: commsagent-discord
+Provides-Extra: commsagent-slack
+Provides-Extra: commsagent-telegram
 Provides-Extra: test
 Provides-Extra: docs
 Provides-Extra: types
@@ -62,14 +65,24 @@ License-File: NOTICE.md
 ![Pypi Downloads](https://img.shields.io/pypi/dm/pyautogen?label=PyPI%20downloads)
 [![PyPI version](https://badge.fury.io/py/autogen.svg)](https://badge.fury.io/py/autogen)
 [![Build](https://github.com/ag2ai/ag2/actions/workflows/python-package.yml/badge.svg)](https://github.com/ag2ai/ag2/actions/workflows/python-package.yml)
-![Python Version](https://img.shields.io/badge/3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue)
+![Python Version](https://img.shields.io/pypi/pyversions/pyautogen?logoColor=blue)
 [![Discord](https://img.shields.io/discord/1153072414184452236?logo=discord&style=flat)](https://discord.gg/pAbnFJrkgZ)
-[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40ag2ai)](https://x.com/Chi_Wang_)
+[![X](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40ag2oss)](https://x.com/ag2oss)
 
 <!-- [![NuGet version](https://badge.fury.io/nu/AutoGen.Core.svg)](https://badge.fury.io/nu/AutoGen.Core) -->
 
 # [AG2](https://github.com/ag2ai/ag2)
 
+## Key Features
+- 🤖 Multi-Agent Framework - Build and orchestrate AI agent interactions
+- 🔧 Flexible Integration - Support for various LLMs (OpenAI, Anthropic, Gemini, etc.)
+- 🛠 Tool Usage - Agents can use external tools and execute code
+- 👥 Human-in-the-Loop - Seamless human participation when needed
+- 🔄 Rich Orchestration Patterns - Agents can be organized in any form you like
+- 🎯 Future-Oriented - Designed for solving difficult problems and harnessing latest and future technology
+
+[📚 Documentation](https://docs.ag2.ai/) | [💡 Examples](https://github.com/ag2ai/build-with-ag2) | [🤝 Contributing](https://docs.ag2.ai/docs/contributor-guide/contributing)
+
 [📚 Cite paper](#related-papers).
 
 <!-- <p align="center">
@@ -138,7 +151,11 @@ We adopt the Apache 2.0 license from v0.3. This enhances our commitment to open-
 
 ## What is AG2
 
-AG2 (formerly AutoGen) is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks. AG2 aims to streamline the development and research of agentic AI, much like PyTorch does for Deep Learning. It offers features such as agents capable of interacting with each other, facilitates the use of various large language models (LLMs) and tool use support, autonomous and human-in-the-loop workflows, and multi-agent conversation patterns.
+AG2 (formerly AutoGen) is an open-source AgentOS for building AI agents and facilitating cooperation among multiple agents to solve tasks. AG2 provides fundamental building blocks needed to create, deploy, and manage AI agents that can work together to solve complex problems.
+
+### Core Concepts
+- **Agents**: Stateful entities that can send messages, receive messages, and generate replies using underlying capabilities powered by LLMs, non-LLM tools, or human inputs. Depending on the underlying capability, an agent may reason, plan, execute tasks or involve other agents before generating a reply.
+- **Conversations**: Structured communication patterns between agents.
 
 **Open Source Statement**: The project welcomes contributions from developers and organizations worldwide. Our goal is to foster a collaborative and inclusive community where diverse perspectives and expertise can drive innovation and enhance the project's capabilities. Whether you are an individual contributor or represent an organization, we invite you to join us in shaping the future of this project. Together, we can build something truly remarkable.
 
@@ -179,7 +196,7 @@ _NOTE_: OAI_CONFIG_LIST_sample lists gpt-4o as the default model. If you use a d
 
 ### Option 1. Install and Run AG2 in Docker
 
-Find detailed instructions for users [here](https://docs.ag2.ai/docs/installation/Docker#step-1-install-docker), and for developers [here](https://docs.ag2.ai/docs/contributor-guide/docker).
+Find detailed instructions for users [here](https://docs.ag2.ai/docs/installation/Docker#step-1-install-docker), and for developers [here](https://docs.ag2.ai/docs/contributor-guide/setup-development-environment).
 
 ### Option 2. Install AG2 Locally
 
@@ -202,7 +219,7 @@ Find more options in [Installation](https://docs.ag2.ai/docs/Installation#option
 
 Even if you are installing and running AG2 locally outside of docker, the recommendation and default behavior of agents is to perform [code execution](https://docs.ag2.ai/docs/FAQ#if-you-want-to-run-code-execution-in-docker) in docker. Find more instructions and how to change the default behaviour [here](https://docs.ag2.ai/docs/FAQ#if-you-want-to-run-code-execution-locally).
 
-For LLM inference configurations, check the [FAQs](https://docs.ag2.ai/docs/FAQ#set-your-api-endpoints).
+For LLM inference configurations, check the [FAQs](https://docs.ag2.ai/docs/user-guide/advanced-concepts/llm-configuration-deep-dive#llm-configuration).
 
 <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
   <a href="#readme-top" style="text-decoration: none; color: blue; font-weight: bold;">
@@ -226,7 +243,7 @@ For [example](https://github.com/ag2ai/ag2/blob/main/test/twoagent.py),
 ```python
 from autogen import AssistantAgent, UserProxyAgent, config_list_from_json
 # Load LLM inference endpoints from an env variable or a file
-# See https://docs.ag2.ai/docs/FAQ#set-your-api-endpoints
+# See https://docs.ag2.ai/docs/user-guide/advanced-concepts/llm-configuration-deep-dive#llm-configuration
 # and OAI_CONFIG_LIST_sample
 config_list = config_list_from_json(env_or_file="OAI_CONFIG_LIST")
 # You can also set config_list directly as a list, for example, config_list = [{'model': 'gpt-4o', 'api_key': '<your OpenAI API key here>'},]
@@ -258,7 +275,7 @@ Please find more [code examples](https://docs.ag2.ai/docs/Examples#automated-mul
 
 ## Enhanced LLM Inferences
 
-AG2 also helps maximize the utility out of the expensive LLMs such as gpt-4o. It offers [enhanced LLM inference](https://docs.ag2.ai/docs/Use-Cases/enhanced_inference#api-unification) with powerful functionalities like caching, error handling, multi-config inference and templating.
+AG2 also helps maximize the utility out of the expensive LLMs such as gpt-4o. It offers enhanced LLM inference with powerful functionalities like caching, error handling, multi-config inference and templating.
 
 <!-- For example, you can optimize generations by LLM with your own tuning data, success metrics, and budgets.
 

{ag2-0.7.3 → ag2-0.7.4b2}/README.md

@@ -3,14 +3,24 @@
 ![Pypi Downloads](https://img.shields.io/pypi/dm/pyautogen?label=PyPI%20downloads)
 [![PyPI version](https://badge.fury.io/py/autogen.svg)](https://badge.fury.io/py/autogen)
 [![Build](https://github.com/ag2ai/ag2/actions/workflows/python-package.yml/badge.svg)](https://github.com/ag2ai/ag2/actions/workflows/python-package.yml)
-![Python Version](https://img.shields.io/badge/3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue)
+![Python Version](https://img.shields.io/pypi/pyversions/pyautogen?logoColor=blue)
 [![Discord](https://img.shields.io/discord/1153072414184452236?logo=discord&style=flat)](https://discord.gg/pAbnFJrkgZ)
-[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40ag2ai)](https://x.com/Chi_Wang_)
+[![X](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40ag2oss)](https://x.com/ag2oss)
 
 <!-- [![NuGet version](https://badge.fury.io/nu/AutoGen.Core.svg)](https://badge.fury.io/nu/AutoGen.Core) -->
 
 # [AG2](https://github.com/ag2ai/ag2)
 
+## Key Features
+- 🤖 Multi-Agent Framework - Build and orchestrate AI agent interactions
+- 🔧 Flexible Integration - Support for various LLMs (OpenAI, Anthropic, Gemini, etc.)
+- 🛠 Tool Usage - Agents can use external tools and execute code
+- 👥 Human-in-the-Loop - Seamless human participation when needed
+- 🔄 Rich Orchestration Patterns - Agents can be organized in any form you like
+- 🎯 Future-Oriented - Designed for solving difficult problems and harnessing latest and future technology
+
+[📚 Documentation](https://docs.ag2.ai/) | [💡 Examples](https://github.com/ag2ai/build-with-ag2) | [🤝 Contributing](https://docs.ag2.ai/docs/contributor-guide/contributing)
+
 [📚 Cite paper](#related-papers).
 
 <!-- <p align="center">
@@ -79,7 +89,11 @@ We adopt the Apache 2.0 license from v0.3. This enhances our commitment to open-
 
 ## What is AG2
 
-AG2 (formerly AutoGen) is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks. AG2 aims to streamline the development and research of agentic AI, much like PyTorch does for Deep Learning. It offers features such as agents capable of interacting with each other, facilitates the use of various large language models (LLMs) and tool use support, autonomous and human-in-the-loop workflows, and multi-agent conversation patterns.
+AG2 (formerly AutoGen) is an open-source AgentOS for building AI agents and facilitating cooperation among multiple agents to solve tasks. AG2 provides fundamental building blocks needed to create, deploy, and manage AI agents that can work together to solve complex problems.
+
+### Core Concepts
+- **Agents**: Stateful entities that can send messages, receive messages, and generate replies using underlying capabilities powered by LLMs, non-LLM tools, or human inputs. Depending on the underlying capability, an agent may reason, plan, execute tasks or involve other agents before generating a reply.
+- **Conversations**: Structured communication patterns between agents.
 
 **Open Source Statement**: The project welcomes contributions from developers and organizations worldwide. Our goal is to foster a collaborative and inclusive community where diverse perspectives and expertise can drive innovation and enhance the project's capabilities. Whether you are an individual contributor or represent an organization, we invite you to join us in shaping the future of this project. Together, we can build something truly remarkable.
 
@@ -120,7 +134,7 @@ _NOTE_: OAI_CONFIG_LIST_sample lists gpt-4o as the default model. If you use a d
 
 ### Option 1. Install and Run AG2 in Docker
 
-Find detailed instructions for users [here](https://docs.ag2.ai/docs/installation/Docker#step-1-install-docker), and for developers [here](https://docs.ag2.ai/docs/contributor-guide/docker).
+Find detailed instructions for users [here](https://docs.ag2.ai/docs/installation/Docker#step-1-install-docker), and for developers [here](https://docs.ag2.ai/docs/contributor-guide/setup-development-environment).
 
 ### Option 2. Install AG2 Locally
 
@@ -143,7 +157,7 @@ Find more options in [Installation](https://docs.ag2.ai/docs/Installation#option
 
 Even if you are installing and running AG2 locally outside of docker, the recommendation and default behavior of agents is to perform [code execution](https://docs.ag2.ai/docs/FAQ#if-you-want-to-run-code-execution-in-docker) in docker. Find more instructions and how to change the default behaviour [here](https://docs.ag2.ai/docs/FAQ#if-you-want-to-run-code-execution-locally).
 
-For LLM inference configurations, check the [FAQs](https://docs.ag2.ai/docs/FAQ#set-your-api-endpoints).
+For LLM inference configurations, check the [FAQs](https://docs.ag2.ai/docs/user-guide/advanced-concepts/llm-configuration-deep-dive#llm-configuration).
 
 <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
   <a href="#readme-top" style="text-decoration: none; color: blue; font-weight: bold;">
@@ -167,7 +181,7 @@ For [example](https://github.com/ag2ai/ag2/blob/main/test/twoagent.py),
 ```python
 from autogen import AssistantAgent, UserProxyAgent, config_list_from_json
 # Load LLM inference endpoints from an env variable or a file
-# See https://docs.ag2.ai/docs/FAQ#set-your-api-endpoints
+# See https://docs.ag2.ai/docs/user-guide/advanced-concepts/llm-configuration-deep-dive#llm-configuration
 # and OAI_CONFIG_LIST_sample
 config_list = config_list_from_json(env_or_file="OAI_CONFIG_LIST")
 # You can also set config_list directly as a list, for example, config_list = [{'model': 'gpt-4o', 'api_key': '<your OpenAI API key here>'},]
@@ -199,7 +213,7 @@ Please find more [code examples](https://docs.ag2.ai/docs/Examples#automated-mul
 
 ## Enhanced LLM Inferences
 
-AG2 also helps maximize the utility out of the expensive LLMs such as gpt-4o. It offers [enhanced LLM inference](https://docs.ag2.ai/docs/Use-Cases/enhanced_inference#api-unification) with powerful functionalities like caching, error handling, multi-config inference and templating.
+AG2 also helps maximize the utility out of the expensive LLMs such as gpt-4o. It offers enhanced LLM inference with powerful functionalities like caching, error handling, multi-config inference and templating.
 
 <!-- For example, you can optimize generations by LLM with your own tuning data, success metrics, and budgets.
 

{ag2-0.7.3 → ag2-0.7.4b2/ag2.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ag2
-Version: 0.7.3
+Version: 0.7.4b2
 Summary: Alias package for pyautogen
 Home-page: https://github.com/ag2ai/ag2
 Author: Chi Wang & Qingyun Wu
@@ -49,6 +49,9 @@ Provides-Extra: groq
 Provides-Extra: cohere
 Provides-Extra: ollama
 Provides-Extra: bedrock
+Provides-Extra: commsagent-discord
+Provides-Extra: commsagent-slack
+Provides-Extra: commsagent-telegram
 Provides-Extra: test
 Provides-Extra: docs
 Provides-Extra: types
@@ -62,14 +65,24 @@ License-File: NOTICE.md
 ![Pypi Downloads](https://img.shields.io/pypi/dm/pyautogen?label=PyPI%20downloads)
 [![PyPI version](https://badge.fury.io/py/autogen.svg)](https://badge.fury.io/py/autogen)
 [![Build](https://github.com/ag2ai/ag2/actions/workflows/python-package.yml/badge.svg)](https://github.com/ag2ai/ag2/actions/workflows/python-package.yml)
-![Python Version](https://img.shields.io/badge/3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue)
+![Python Version](https://img.shields.io/pypi/pyversions/pyautogen?logoColor=blue)
 [![Discord](https://img.shields.io/discord/1153072414184452236?logo=discord&style=flat)](https://discord.gg/pAbnFJrkgZ)
-[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40ag2ai)](https://x.com/Chi_Wang_)
+[![X](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40ag2oss)](https://x.com/ag2oss)
 
 <!-- [![NuGet version](https://badge.fury.io/nu/AutoGen.Core.svg)](https://badge.fury.io/nu/AutoGen.Core) -->
 
 # [AG2](https://github.com/ag2ai/ag2)
 
+## Key Features
+- 🤖 Multi-Agent Framework - Build and orchestrate AI agent interactions
+- 🔧 Flexible Integration - Support for various LLMs (OpenAI, Anthropic, Gemini, etc.)
+- 🛠 Tool Usage - Agents can use external tools and execute code
+- 👥 Human-in-the-Loop - Seamless human participation when needed
+- 🔄 Rich Orchestration Patterns - Agents can be organized in any form you like
+- 🎯 Future-Oriented - Designed for solving difficult problems and harnessing latest and future technology
+
+[📚 Documentation](https://docs.ag2.ai/) | [💡 Examples](https://github.com/ag2ai/build-with-ag2) | [🤝 Contributing](https://docs.ag2.ai/docs/contributor-guide/contributing)
+
 [📚 Cite paper](#related-papers).
 
 <!-- <p align="center">
@@ -138,7 +151,11 @@ We adopt the Apache 2.0 license from v0.3. This enhances our commitment to open-
 
 ## What is AG2
 
-AG2 (formerly AutoGen) is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks. AG2 aims to streamline the development and research of agentic AI, much like PyTorch does for Deep Learning. It offers features such as agents capable of interacting with each other, facilitates the use of various large language models (LLMs) and tool use support, autonomous and human-in-the-loop workflows, and multi-agent conversation patterns.
+AG2 (formerly AutoGen) is an open-source AgentOS for building AI agents and facilitating cooperation among multiple agents to solve tasks. AG2 provides fundamental building blocks needed to create, deploy, and manage AI agents that can work together to solve complex problems.
+
+### Core Concepts
+- **Agents**: Stateful entities that can send messages, receive messages, and generate replies using underlying capabilities powered by LLMs, non-LLM tools, or human inputs. Depending on the underlying capability, an agent may reason, plan, execute tasks or involve other agents before generating a reply.
+- **Conversations**: Structured communication patterns between agents.
 
 **Open Source Statement**: The project welcomes contributions from developers and organizations worldwide. Our goal is to foster a collaborative and inclusive community where diverse perspectives and expertise can drive innovation and enhance the project's capabilities. Whether you are an individual contributor or represent an organization, we invite you to join us in shaping the future of this project. Together, we can build something truly remarkable.
 
@@ -179,7 +196,7 @@ _NOTE_: OAI_CONFIG_LIST_sample lists gpt-4o as the default model. If you use a d
 
 ### Option 1. Install and Run AG2 in Docker
 
-Find detailed instructions for users [here](https://docs.ag2.ai/docs/installation/Docker#step-1-install-docker), and for developers [here](https://docs.ag2.ai/docs/contributor-guide/docker).
+Find detailed instructions for users [here](https://docs.ag2.ai/docs/installation/Docker#step-1-install-docker), and for developers [here](https://docs.ag2.ai/docs/contributor-guide/setup-development-environment).
 
 ### Option 2. Install AG2 Locally
 
@@ -202,7 +219,7 @@ Find more options in [Installation](https://docs.ag2.ai/docs/Installation#option
 
 Even if you are installing and running AG2 locally outside of docker, the recommendation and default behavior of agents is to perform [code execution](https://docs.ag2.ai/docs/FAQ#if-you-want-to-run-code-execution-in-docker) in docker. Find more instructions and how to change the default behaviour [here](https://docs.ag2.ai/docs/FAQ#if-you-want-to-run-code-execution-locally).
 
-For LLM inference configurations, check the [FAQs](https://docs.ag2.ai/docs/FAQ#set-your-api-endpoints).
+For LLM inference configurations, check the [FAQs](https://docs.ag2.ai/docs/user-guide/advanced-concepts/llm-configuration-deep-dive#llm-configuration).
 
 <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
   <a href="#readme-top" style="text-decoration: none; color: blue; font-weight: bold;">
@@ -226,7 +243,7 @@ For [example](https://github.com/ag2ai/ag2/blob/main/test/twoagent.py),
 ```python
 from autogen import AssistantAgent, UserProxyAgent, config_list_from_json
 # Load LLM inference endpoints from an env variable or a file
-# See https://docs.ag2.ai/docs/FAQ#set-your-api-endpoints
+# See https://docs.ag2.ai/docs/user-guide/advanced-concepts/llm-configuration-deep-dive#llm-configuration
 # and OAI_CONFIG_LIST_sample
 config_list = config_list_from_json(env_or_file="OAI_CONFIG_LIST")
 # You can also set config_list directly as a list, for example, config_list = [{'model': 'gpt-4o', 'api_key': '<your OpenAI API key here>'},]
@@ -258,7 +275,7 @@ Please find more [code examples](https://docs.ag2.ai/docs/Examples#automated-mul
 
 ## Enhanced LLM Inferences
 
-AG2 also helps maximize the utility out of the expensive LLMs such as gpt-4o. It offers [enhanced LLM inference](https://docs.ag2.ai/docs/Use-Cases/enhanced_inference#api-unification) with powerful functionalities like caching, error handling, multi-config inference and templating.
+AG2 also helps maximize the utility out of the expensive LLMs such as gpt-4o. It offers enhanced LLM inference with powerful functionalities like caching, error handling, multi-config inference and templating.
 
 <!-- For example, you can optimize generations by LLM with your own tuning data, success metrics, and budgets.
 

{ag2-0.7.3 → ag2-0.7.4b2}/ag2.egg-info/SOURCES.txt

@@ -16,6 +16,5 @@ test/test_import.py
 test/test_import_utils.py
 test/test_logging.py
 test/test_notebook.py
-test/test_pydantic.py
 test/test_retrieve_utils.py
 test/test_token_count.py

ag2-0.7.4b2/ag2.egg-info/requires.txt

@@ -0,0 +1,136 @@
+pyautogen==0.7.4b2
+
+[anthropic]
+pyautogen[anthropic]==0.7.4b2
+
+[autobuild]
+pyautogen[autobuild]==0.7.4b2
+
+[bedrock]
+pyautogen[bedrock]==0.7.4b2
+
+[blendsearch]
+pyautogen[blendsearch]==0.7.4b2
+
+[browser-use]
+pyautogen[browser-use]==0.7.4b2
+
+[captainagent]
+pyautogen[captainagent]==0.7.4b2
+
+[cerebras]
+pyautogen[cerebras]==0.7.4b2
+
+[cohere]
+pyautogen[cohere]==0.7.4b2
+
+[commsagent-discord]
+pyautogen[commsagent-discord]==0.7.4b2
+
+[commsagent-slack]
+pyautogen[commsagent-slack]==0.7.4b2
+
+[commsagent-telegram]
+pyautogen[commsagent-telegram]==0.7.4b2
+
+[cosmosdb]
+pyautogen[cosmosdb]==0.7.4b2
+
+[crawl4ai]
+pyautogen[crawl4ai]==0.7.4b2
+
+[dev]
+pyautogen[dev]==0.7.4b2
+
+[docs]
+pyautogen[docs]==0.7.4b2
+
+[flaml]
+pyautogen[flaml]==0.7.4b2
+
+[gemini]
+pyautogen[gemini]==0.7.4b2
+
+[graph]
+pyautogen[graph]==0.7.4b2
+
+[graph-rag-falkor-db]
+pyautogen[graph-rag-falkor-db]==0.7.4b2
+
+[groq]
+pyautogen[groq]==0.7.4b2
+
+[interop]
+pyautogen[interop]==0.7.4b2
+
+[interop-crewai]
+pyautogen[interop-crewai]==0.7.4b2
+
+[interop-langchain]
+pyautogen[interop-langchain]==0.7.4b2
+
+[interop-pydantic-ai]
+pyautogen[interop-pydantic-ai]==0.7.4b2
+
+[jupyter-executor]
+pyautogen[jupyter-executor]==0.7.4b2
+
+[lint]
+pyautogen[lint]==0.7.4b2
+
+[lmm]
+pyautogen[lmm]==0.7.4b2
+
+[long-context]
+pyautogen[long-context]==0.7.4b2
+
+[mathchat]
+pyautogen[mathchat]==0.7.4b2
+
+[mistral]
+pyautogen[mistral]==0.7.4b2
+
+[neo4j]
+pyautogen[neo4j]==0.7.4b2
+
+[ollama]
+pyautogen[ollama]==0.7.4b2
+
+[rag]
+pyautogen[rag]==0.7.4b2
+
+[redis]
+pyautogen[redis]==0.7.4b2
+
+[retrievechat]
+pyautogen[retrievechat]==0.7.4b2
+
+[retrievechat-mongodb]
+pyautogen[retrievechat-mongodb]==0.7.4b2
+
+[retrievechat-pgvector]
+pyautogen[retrievechat-pgvector]==0.7.4b2
+
+[retrievechat-qdrant]
+pyautogen[retrievechat-qdrant]==0.7.4b2
+
+[teachable]
+pyautogen[teachable]==0.7.4b2
+
+[test]
+pyautogen[test]==0.7.4b2
+
+[together]
+pyautogen[together]==0.7.4b2
+
+[twilio]
+pyautogen[twilio]==0.7.4b2
+
+[types]
+pyautogen[types]==0.7.4b2
+
+[websockets]
+pyautogen[websockets]==0.7.4b2
+
+[websurfer]
+pyautogen[websurfer]==0.7.4b2

{ag2-0.7.3 → ag2-0.7.4b2}/pyproject.toml

@@ -11,8 +11,7 @@ name = "pyautogen"
 description = "A programming framework for agentic AI"
 readme = "README.md"
 authors = [
-    {name = "Chi Wang", email = "support@ag2.ai"},
-    {name = "Qingyun Wu", email = "support@ag2.ai"},
+    {name = "Chi Wang & Qingyun Wu", email = "support@ag2.ai"}
 ]
 
 keywords = [
@@ -86,8 +85,8 @@ jupyter-executor = [
 ]
 
 retrievechat = [
-    "protobuf==4.25.3",
-    "chromadb==0.5.3",
+    "protobuf==5.29.3",
+    "chromadb==0.6.3",
     "sentence_transformers",
     "pypdf",
     "ipython",
@@ -114,14 +113,16 @@ retrievechat-qdrant = [
 ]
 
 graph-rag-falkor-db = [
-    "graphrag_sdk==0.3.3",
-    "falkordb>=1.0.10"
+    "graphrag_sdk==0.6.0",
+    "falkordb>=1.0.10",
 ]
 
 rag = [
     "docling>=2.15.1,<3",
     "selenium>=4.28.1,<5",
     "webdriver-manager==4.0.2",
+    "chromadb>=0.5,<1",
+    "llama-index>=0.12,<1",
 ]
 
 
@@ -135,10 +136,10 @@ browser-use = [
 
 neo4j = [
     "docx2txt==0.8",
-    "llama-index==0.12.11",
-    "llama-index-graph-stores-neo4j==0.4.5",
-    "llama-index-core==0.12.11",
-    "llama-index-readers-web==0.3.4",
+    "llama-index==0.12.16",
+    "llama-index-graph-stores-neo4j==0.4.6",
+    "llama-index-core==0.12.16",
+    "llama-index-readers-web==0.3.5",
 ]
 
 # used for agentchat_realtime_swarm notebook and realtime agent twilio demo
@@ -155,7 +156,7 @@ interop-crewai = [
     "litellm<1.57.5; sys_platform=='win32'",
 ]
 interop-langchain = ["langchain-community>=0.3.12,<1"]
-interop-pydantic-ai = ["pydantic-ai==0.0.13"]
+interop-pydantic-ai = ["pydantic-ai==0.0.23"]
 interop =[
     "pyautogen[interop-crewai, interop-langchain, interop-pydantic-ai]",
 ]
@@ -164,7 +165,7 @@ interop =[
 autobuild = ["chromadb", "sentence-transformers", "huggingface-hub", "pysqlite3-binary"]
 
 blendsearch = ["flaml[blendsearch]"]
-mathchat = ["sympy", "pydantic==1.10.9", "wolframalpha"]
+mathchat = ["sympy", "wolframalpha"]
 captainagent = ["pyautogen[autobuild]", "pandas"]
 teachable = ["chromadb"]
 lmm = ["replicate", "pillow"]
@@ -175,6 +176,7 @@ gemini = [
     "google-auth",
     "pillow",
     "jsonschema",
+    "jsonref"
 ]
 together = ["together>=1.2"]
 websurfer = ["beautifulsoup4", "markdownify", "pdfminer.six", "pathvalidate"]
@@ -190,18 +192,23 @@ cohere = ["cohere>=5.5.8"]
 ollama = ["ollama>=0.4.5", "fix_busted_json>=0.0.18"]
 bedrock = ["boto3>=1.34.149"]
 
+commsagent-discord = ["discord.py>=2.4.0,<2.5"]
+commsagent-slack = ["slack_sdk>=3.33.0,<3.40"]
+commsagent-telegram = ["telethon>=1.38.1, <2"]
+
 ## dev dependencies
 
 # test dependencies
 test = [
     "ipykernel==6.29.5",
-    "nbconvert==7.16.5",
+    "nbconvert==7.16.6",
     "nbformat==5.10.4",
     "pytest-cov==6.0.0",
-    "pytest-asyncio==0.25.2",
+    "pytest-asyncio==0.25.3",
     "pytest==8.3.4",
+    "mock==5.1.0",
     "pandas==2.2.3",
-    "fastapi==0.115.6",
+    "fastapi==0.115.8",
 ]
 
 # docs dependencies
@@ -214,13 +221,13 @@ docs = [
 ]
 
 types = [
-    "mypy==1.14.1",
+    "mypy==1.15.0",
     "pyautogen[test, jupyter-executor, interop]",
 ]
 
 lint = [
-    "ruff==0.9.2",
-    "codespell==2.3.0",
+    "ruff==0.9.5",
+    "codespell==2.4.1",
     "pyupgrade-directories==0.3.0",
 ]
 
@@ -229,7 +236,7 @@ dev = [
     "pyautogen[lint,test,types,docs]",
     "pre-commit==4.1.0",
     "detect-secrets==1.5.0",
-    "uv==0.5.21",
+    "uv==0.5.29",
 ]
 
 
@@ -260,7 +267,7 @@ exclude = ["test", "notebook"]
 
 
 [tool.pytest.ini_options]
-addopts = '--cov=. --cov-append --cov-branch --cov-report=xml -m "not conda"'
+addopts = '--cov=autogen --cov-append --cov-branch --cov-report=xml -m "not conda"'
 testpaths = [
     "test",
 ]
@@ -315,6 +322,8 @@ exclude = [
     "setup_*.py",
 ]
 
+preview = true
+
 [tool.ruff.lint]
 # Enable Pyflakes `E` and `F` codes by default.
 select = [
@@ -369,7 +378,6 @@ files = [
     "autogen/exception_utils.py",
     "autogen/coding",
     "autogen/oai/openai_utils.py",
-    "autogen/_pydantic.py",
     "autogen/io",
     "autogen/tools",
     "autogen/interop",
@@ -378,7 +386,6 @@ files = [
     "autogen/import_utils.py",
     "autogen/agentchat/contrib/rag",
     "website/*.py",
-    "test/test_pydantic.py",
     "test/io",
     "test/tools",
     "test/interop",
@@ -420,3 +427,8 @@ warn_unused_ignores = false
 disallow_incomplete_defs = true
 disallow_untyped_decorators = true
 disallow_any_unimported = true
+
+[tool.codespell]
+skip = "*.js,*.map,*.pdf,*.po,*.ts,*.json,*.svg,./notebook,./website/node_modules,.notebook/agentchat_microsoft_fabric.ipynb"
+quiet-level = 3
+ignore-words-list = "ans,linar,nam,tread,ot,assertIn,dependin,socio-economic,ege,leapYear,fO,bu,te,ROUGE,ser,doubleClick,CNa,wOh,Hart,Empress,Chage,mane,digitalize"

{ag2-0.7.3 → ag2-0.7.4b2}/setup_ag2.py

@@ -65,6 +65,9 @@ setuptools.setup(
         "cohere": ["pyautogen[cohere]==" + __version__],
         "ollama": ["pyautogen[ollama]==" + __version__],
         "bedrock": ["pyautogen[bedrock]==" + __version__],
+        "commsagent-discord": ["pyautogen[commsagent-discord]==" + __version__],
+        "commsagent-slack": ["pyautogen[commsagent-slack]==" + __version__],
+        "commsagent-telegram": ["pyautogen[commsagent-telegram]==" + __version__],
         "test": ["pyautogen[test]==" + __version__],
         "docs": ["pyautogen[docs]==" + __version__],
         "types": ["pyautogen[types]==" + __version__],

{ag2-0.7.3 → ag2-0.7.4b2}/test/test_browser_utils.py

@@ -4,7 +4,7 @@
 #
 # Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
 # SPDX-License-Identifier: MIT
-#!/usr/bin/env python3 -m pytest
+# !/usr/bin/env python3 -m pytest
 
 import hashlib
 import math
@@ -18,7 +18,7 @@ import requests
 from autogen.browser_utils import SimpleTextBrowser
 from autogen.import_utils import optional_import_block, skip_on_missing_imports
 
-BLOG_POST_URL = "https://docs.ag2.ai/blog/2023-04-21-LLM-tuning-math"
+BLOG_POST_URL = "https://docs.ag2.ai/docs/blog/2023-04-21-LLM-tuning-math"
 BLOG_POST_TITLE = "Does Model and Inference Parameter Matter in LLM Applications? - A Case Study for MATH - AG2"
 BLOG_POST_STRING = "Large language models (LLMs) are powerful tools that can generate natural language texts for various applications, such as chatbots, summarization, translation, and more. GPT-4 is currently the state of the art LLM in the world. Is model selection irrelevant? What about inference parameters?"
 

{ag2-0.7.3 → ag2-0.7.4b2}/test/test_code_utils.py

@@ -4,7 +4,7 @@
 #
 # Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
 # SPDX-License-Identifier: MIT
-#!/usr/bin/env python3 -m pytest
+# !/usr/bin/env python3 -m pytest
 
 import os
 import tempfile

ag2-0.7.4b2/test/test_conftest.py

@@ -0,0 +1,74 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+#
+# Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
+# SPDX-License-Identifier: MIT
+
+
+import os
+import subprocess
+
+import pytest
+
+from .conftest import Credentials, Secrets, credentials_all_llms, suppress_gemini_resource_exhausted
+
+
+@pytest.mark.parametrize("credentials_from_test_param", credentials_all_llms, indirect=True)
+@suppress_gemini_resource_exhausted
+def test_credentials_from_test_param_fixture(
+    credentials_from_test_param: Credentials,
+    request: pytest.FixtureRequest,
+) -> None:
+    # Get the parameter name request node
+    current_llm = request.node.callspec.id
+
+    assert current_llm is not None
+    assert isinstance(credentials_from_test_param, Credentials)
+
+    first_config = credentials_from_test_param.config_list[0]
+    if "gpt_4" in current_llm:
+        if "api_type" in first_config:
+            assert first_config["api_type"] == "openai"
+    elif "gemini" in current_llm:
+        assert first_config["api_type"] == "google"
+    elif "anthropic" in current_llm:
+        assert first_config["api_type"] == "anthropic"
+    else:
+        assert False, f"Unknown LLM fixture: {current_llm}"
+
+
+class TestSecrets:
+    def test_sanitize_secrets(self):
+        Secrets.add_secret("mysecret")
+        data = "This contains mysecret and ysecre and somemysecreand should be sanitized."
+        sanitized = Secrets.sanitize_secrets(data)
+        assert sanitized == "This contains ***** and ***** and some*****and should be sanitized."
+
+    @pytest.mark.skipif(
+        not os.getenv("RUN_SANITIZATION_TEST"),
+        reason="Skipping sensitive tests. Set RUN_SANITIZATION_TEST=1 to run.",
+    )
+    def test_raise_exception_with_secret(self):
+        Secrets.add_secret("mysecret")
+        raise Exception("This is a test exception. mysecret exposed!!!")
+
+    def test_sensitive_output_is_sanitized(self):
+        # Run pytest for the sensitive tests and capture the output
+        result = subprocess.run(
+            [
+                "pytest",
+                "-s",
+                "test/test_conftest.py::TestSecrets::test_raise_exception_with_secret",
+            ],
+            env={**os.environ, "RUN_SANITIZATION_TEST": "1"},
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            text=True,
+        )
+
+        # Combine stdout and stderr to search for secrets
+        output = result.stdout + result.stderr
+
+        assert "mysecret" not in output, "Secret exposed in test output!"
+        assert "*****" in output, "Sanitization is not working as expected!"

{ag2-0.7.3 → ag2-0.7.4b2}/test/test_logging.py

@@ -295,9 +295,9 @@ def test_to_dict():
     assert result["foo_val"] == expected_foo_val_field
     assert result["o"] == expected_o_field
     assert len(result["agents"]) == 2
-    for agent in result["agents"]:
-        assert "autogen.ConversableAgent" in agent
-    assert "autogen.ConversableAgent" in result["first_agent"]
+    assert result["agents"][0] == "alice"
+    assert result["agents"][1] == "bob"
+    assert "alice" in result["first_agent"]
 
 
 @patch("logging.Logger.error")

{ag2-0.7.3 → ag2-0.7.4b2}/test/test_notebook.py

@@ -4,7 +4,7 @@
 #
 # Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
 # SPDX-License-Identifier: MIT
-#!/usr/bin/env python3 -m pytest
+# !/usr/bin/env python3 -m pytest
 
 import os
 import sys

{ag2-0.7.3 → ag2-0.7.4b2}/test/test_retrieve_utils.py

@@ -4,7 +4,7 @@
 #
 # Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
 # SPDX-License-Identifier: MIT
-#!/usr/bin/env python3 -m pytest
+# !/usr/bin/env python3 -m pytest
 
 """Unit test for retrieve_utils.py"""
 

{ag2-0.7.3 → ag2-0.7.4b2}/test/test_token_count.py

@@ -4,7 +4,7 @@
 #
 # Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
 # SPDX-License-Identifier: MIT
-#!/usr/bin/env python3 -m pytest
+# !/usr/bin/env python3 -m pytest
 
 import pytest
 

ag2-0.7.3/ag2.egg-info/requires.txt

@@ -1,127 +0,0 @@
-pyautogen==0.7.3
-
-[anthropic]
-pyautogen[anthropic]==0.7.3
-
-[autobuild]
-pyautogen[autobuild]==0.7.3
-
-[bedrock]
-pyautogen[bedrock]==0.7.3
-
-[blendsearch]
-pyautogen[blendsearch]==0.7.3
-
-[browser-use]
-pyautogen[browser-use]==0.7.3
-
-[captainagent]
-pyautogen[captainagent]==0.7.3
-
-[cerebras]
-pyautogen[cerebras]==0.7.3
-
-[cohere]
-pyautogen[cohere]==0.7.3
-
-[cosmosdb]
-pyautogen[cosmosdb]==0.7.3
-
-[crawl4ai]
-pyautogen[crawl4ai]==0.7.3
-
-[dev]
-pyautogen[dev]==0.7.3
-
-[docs]
-pyautogen[docs]==0.7.3
-
-[flaml]
-pyautogen[flaml]==0.7.3
-
-[gemini]
-pyautogen[gemini]==0.7.3
-
-[graph]
-pyautogen[graph]==0.7.3
-
-[graph-rag-falkor-db]
-pyautogen[graph-rag-falkor-db]==0.7.3
-
-[groq]
-pyautogen[groq]==0.7.3
-
-[interop]
-pyautogen[interop]==0.7.3
-
-[interop-crewai]
-pyautogen[interop-crewai]==0.7.3
-
-[interop-langchain]
-pyautogen[interop-langchain]==0.7.3
-
-[interop-pydantic-ai]
-pyautogen[interop-pydantic-ai]==0.7.3
-
-[jupyter-executor]
-pyautogen[jupyter-executor]==0.7.3
-
-[lint]
-pyautogen[lint]==0.7.3
-
-[lmm]
-pyautogen[lmm]==0.7.3
-
-[long-context]
-pyautogen[long-context]==0.7.3
-
-[mathchat]
-pyautogen[mathchat]==0.7.3
-
-[mistral]
-pyautogen[mistral]==0.7.3
-
-[neo4j]
-pyautogen[neo4j]==0.7.3
-
-[ollama]
-pyautogen[ollama]==0.7.3
-
-[rag]
-pyautogen[rag]==0.7.3
-
-[redis]
-pyautogen[redis]==0.7.3
-
-[retrievechat]
-pyautogen[retrievechat]==0.7.3
-
-[retrievechat-mongodb]
-pyautogen[retrievechat-mongodb]==0.7.3
-
-[retrievechat-pgvector]
-pyautogen[retrievechat-pgvector]==0.7.3
-
-[retrievechat-qdrant]
-pyautogen[retrievechat-qdrant]==0.7.3
-
-[teachable]
-pyautogen[teachable]==0.7.3
-
-[test]
-pyautogen[test]==0.7.3
-
-[together]
-pyautogen[together]==0.7.3
-
-[twilio]
-pyautogen[twilio]==0.7.3
-
-[types]
-pyautogen[types]==0.7.3
-
-[websockets]
-pyautogen[websockets]==0.7.3
-
-[websurfer]
-pyautogen[websurfer]==0.7.3

ag2-0.7.3/test/test_conftest.py

@@ -1,35 +0,0 @@
-# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
-#
-# SPDX-License-Identifier: Apache-2.0
-#
-# Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
-# SPDX-License-Identifier: MIT
-
-
-import pytest
-
-from .conftest import Credentials, credentials_all_llms, suppress_gemini_resource_exhausted
-
-
-@pytest.mark.parametrize("credentials_from_test_param", credentials_all_llms, indirect=True)
-@suppress_gemini_resource_exhausted
-def test_credentials_from_test_param_fixture(
-    credentials_from_test_param: Credentials,
-    request: pytest.FixtureRequest,
-) -> None:
-    # Get the parameter name request node
-    current_llm = request.node.callspec.id
-
-    assert current_llm is not None
-    assert isinstance(credentials_from_test_param, Credentials)
-
-    first_config = credentials_from_test_param.config_list[0]
-    if "gpt_4" in current_llm:
-        if "api_type" in first_config:
-            assert first_config["api_type"] == "openai"
-    elif "gemini" in current_llm:
-        assert first_config["api_type"] == "google"
-    elif "anthropic" in current_llm:
-        assert first_config["api_type"] == "anthropic"
-    else:
-        assert False, f"Unknown LLM fixture: {current_llm}"

ag2-0.7.3/test/test_pydantic.py

@@ -1,46 +0,0 @@
-# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
-#
-# SPDX-License-Identifier: Apache-2.0
-#
-# Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
-# SPDX-License-Identifier: MIT
-from typing import Annotated, Optional, Union
-
-from pydantic import BaseModel
-
-from autogen._pydantic import model_dump, model_dump_json, type2schema
-
-
-def test_type2schema() -> None:
-    assert type2schema(str) == {"type": "string"}
-    assert type2schema(int) == {"type": "integer"}
-    assert type2schema(float) == {"type": "number"}
-    assert type2schema(bool) == {"type": "boolean"}
-    assert type2schema(None) == {"type": "null"}
-    assert type2schema(Optional[int]) == {"anyOf": [{"type": "integer"}, {"type": "null"}]}
-    assert type2schema(list[int]) == {"items": {"type": "integer"}, "type": "array"}
-    assert type2schema(tuple[int, float, str]) == {
-        "maxItems": 3,
-        "minItems": 3,
-        "prefixItems": [{"type": "integer"}, {"type": "number"}, {"type": "string"}],
-        "type": "array",
-    }
-    assert type2schema(dict[str, int]) == {"additionalProperties": {"type": "integer"}, "type": "object"}
-    assert type2schema(Annotated[str, "some text"]) == {"type": "string"}
-    assert type2schema(Union[int, float]) == {"anyOf": [{"type": "integer"}, {"type": "number"}]}
-
-
-def test_model_dump() -> None:
-    class A(BaseModel):
-        a: str
-        b: int = 2
-
-    assert model_dump(A(a="aaa")) == {"a": "aaa", "b": 2}
-
-
-def test_model_dump_json() -> None:
-    class A(BaseModel):
-        a: str
-        b: int = 2
-
-    assert model_dump_json(A(a="aaa")).replace(" ", "") == '{"a":"aaa","b":2}'