ag2 0.7.2b1__tar.gz → 0.7.3__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of ag2 might be problematic. Click here for more details.

Files changed (24) hide show
  1. {ag2-0.7.2b1 → ag2-0.7.3}/NOTICE.md +1 -1
  2. {ag2-0.7.2b1/ag2.egg-info → ag2-0.7.3}/PKG-INFO +40 -37
  3. {ag2-0.7.2b1 → ag2-0.7.3}/README.md +36 -36
  4. {ag2-0.7.2b1 → ag2-0.7.3/ag2.egg-info}/PKG-INFO +40 -37
  5. ag2-0.7.3/ag2.egg-info/requires.txt +127 -0
  6. {ag2-0.7.2b1 → ag2-0.7.3}/pyproject.toml +35 -4
  7. {ag2-0.7.2b1 → ag2-0.7.3}/setup_ag2.py +4 -1
  8. {ag2-0.7.2b1 → ag2-0.7.3}/test/test_browser_utils.py +5 -13
  9. {ag2-0.7.2b1 → ag2-0.7.3}/test/test_code_utils.py +4 -10
  10. {ag2-0.7.2b1 → ag2-0.7.3}/test/test_conftest.py +3 -2
  11. {ag2-0.7.2b1 → ag2-0.7.3}/test/test_graph_utils.py +1 -1
  12. {ag2-0.7.2b1 → ag2-0.7.3}/test/test_import.py +1 -1
  13. {ag2-0.7.2b1 → ag2-0.7.3}/test/test_import_utils.py +1 -1
  14. {ag2-0.7.2b1 → ag2-0.7.3}/test/test_logging.py +3 -3
  15. {ag2-0.7.2b1 → ag2-0.7.3}/test/test_notebook.py +32 -28
  16. {ag2-0.7.2b1 → ag2-0.7.3}/test/test_pydantic.py +1 -1
  17. {ag2-0.7.2b1 → ag2-0.7.3}/test/test_retrieve_utils.py +8 -22
  18. {ag2-0.7.2b1 → ag2-0.7.3}/test/test_token_count.py +3 -10
  19. ag2-0.7.2b1/ag2.egg-info/requires.txt +0 -118
  20. {ag2-0.7.2b1 → ag2-0.7.3}/LICENSE +0 -0
  21. {ag2-0.7.2b1 → ag2-0.7.3}/ag2.egg-info/SOURCES.txt +0 -0
  22. {ag2-0.7.2b1 → ag2-0.7.3}/ag2.egg-info/dependency_links.txt +0 -0
  23. {ag2-0.7.2b1 → ag2-0.7.3}/ag2.egg-info/top_level.txt +0 -0
  24. {ag2-0.7.2b1 → ag2-0.7.3}/setup.cfg +0 -0
{ag2-0.7.2b1 → ag2-0.7.3}/NOTICE.md RENAMED
@@ -1,6 +1,6 @@
1
1
  ## NOTICE
2
2
 
3
- Copyright (c) 2023-2025, Owners of https://github.com/ag2ai
3
+ Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
4
4
 
5
5
  This project is a fork of https://github.com/microsoft/autogen.
6
6
 
{ag2-0.7.2b1/ag2.egg-info → ag2-0.7.3}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: ag2
3
- Version: 0.7.2b1
3
+ Version: 0.7.3
4
4
  Summary: Alias package for pyautogen
5
5
  Home-page: https://github.com/ag2ai/ag2
6
6
  Author: Chi Wang & Qingyun Wu
@@ -19,6 +19,9 @@ Provides-Extra: retrievechat-pgvector
19
19
  Provides-Extra: retrievechat-mongodb
20
20
  Provides-Extra: retrievechat-qdrant
21
21
  Provides-Extra: graph-rag-falkor-db
22
+ Provides-Extra: rag
23
+ Provides-Extra: crawl4ai
24
+ Provides-Extra: browser-use
22
25
  Provides-Extra: neo4j
23
26
  Provides-Extra: twilio
24
27
  Provides-Extra: interop-crewai
@@ -68,20 +71,20 @@ License-File: NOTICE.md
68
71
  # [AG2](https://github.com/ag2ai/ag2)
69
72
 
70
73
  [📚 Cite paper](#related-papers).
74
+
71
75
  <!-- <p align="center">
72
76
  <img src="https://github.com/ag2ai/ag2/blob/main/website/static/img/flaml.svg" width=200>
73
77
  <br>
74
78
  </p> -->
75
79
 
76
- > **:tada: IMPORTANT**
80
+ > **🎉 IMPORTANT**
77
81
  >
78
- > :fire: :tada: **Nov 11, 2024:** We are evolving AutoGen into **AG2**!
82
+ > 🔥 🎉 **Nov 11, 2024:** We are evolving AutoGen into **AG2**!
79
83
  > A new organization [AG2AI](https://github.com/ag2ai) is created to host the development of AG2 and related projects with open governance. Check [AG2's new look](https://ag2.ai/).
80
84
  >
81
85
  > We invite collaborators from all organizations and individuals to join the development.
82
86
 
83
-
84
- :fire: :tada: AG2 is available via `pyautogen` (or its alias `autogen` or `ag2`) on PyPI!
87
+ 🔥 🎉 AG2 is available via `pyautogen` (or its alias `autogen` or `ag2`) on PyPI!
85
88
 
86
89
  ```
87
90
  pip install pyautogen
@@ -90,49 +93,48 @@ pip install pyautogen
90
93
  📄 **License:**
91
94
  We adopt the Apache 2.0 license from v0.3. This enhances our commitment to open-source collaboration while providing additional protections for contributors and users alike.
92
95
 
96
+ 🎉 May 29, 2024: DeepLearning.ai launched a new short course [AI Agentic Design Patterns with AutoGen](https://www.deeplearning.ai/short-courses/ai-agentic-design-patterns-with-autogen), made in collaboration with Microsoft and Penn State University, and taught by AutoGen creators [Chi Wang](https://github.com/sonichi) and [Qingyun Wu](https://github.com/qingyun-wu).
93
97
 
94
- :tada: May 29, 2024: DeepLearning.ai launched a new short course [AI Agentic Design Patterns with AutoGen](https://www.deeplearning.ai/short-courses/ai-agentic-design-patterns-with-autogen), made in collaboration with Microsoft and Penn State University, and taught by AutoGen creators [Chi Wang](https://github.com/sonichi) and [Qingyun Wu](https://github.com/qingyun-wu).
95
-
96
- :tada: May 24, 2024: Foundation Capital published an article on [Forbes: The Promise of Multi-Agent AI](https://www.forbes.com/sites/joannechen/2024/05/24/the-promise-of-multi-agent-ai/?sh=2c1e4f454d97) and a video [AI in the Real World Episode 2: Exploring Multi-Agent AI and AutoGen with Chi Wang](https://www.youtube.com/watch?v=RLwyXRVvlNk).
98
+ 🎉 May 24, 2024: Foundation Capital published an article on [Forbes: The Promise of Multi-Agent AI](https://www.forbes.com/sites/joannechen/2024/05/24/the-promise-of-multi-agent-ai/?sh=2c1e4f454d97) and a video [AI in the Real World Episode 2: Exploring Multi-Agent AI and AutoGen with Chi Wang](https://www.youtube.com/watch?v=RLwyXRVvlNk).
97
99
 
98
- :tada: May 13, 2024: [The Economist](https://www.economist.com/science-and-technology/2024/05/13/todays-ai-models-are-impressive-teams-of-them-will-be-formidable) published an article about multi-agent systems (MAS) following a January 2024 interview with [Chi Wang](https://github.com/sonichi).
100
+ 🎉 May 13, 2024: [The Economist](https://www.economist.com/science-and-technology/2024/05/13/todays-ai-models-are-impressive-teams-of-them-will-be-formidable) published an article about multi-agent systems (MAS) following a January 2024 interview with [Chi Wang](https://github.com/sonichi).
99
101
 
100
- :tada: May 11, 2024: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://openreview.net/pdf?id=uAjxFFing2) received the best paper award at the [ICLR 2024 LLM Agents Workshop](https://llmagents.github.io/).
102
+ 🎉 May 11, 2024: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://openreview.net/pdf?id=uAjxFFing2) received the best paper award at the [ICLR 2024 LLM Agents Workshop](https://llmagents.github.io/).
101
103
 
102
- <!-- :tada: Apr 26, 2024: [AutoGen.NET](https://docs.ag2.ai/ag2-for-net/) is available for .NET developers! -->
104
+ <!-- 🎉 Apr 26, 2024: [AutoGen.NET](https://docs.ag2.ai/ag2-for-net/) is available for .NET developers! -->
103
105
 
104
- :tada: Apr 17, 2024: Andrew Ng cited AutoGen in [The Batch newsletter](https://www.deeplearning.ai/the-batch/issue-245/) and [What's next for AI agentic workflows](https://youtu.be/sal78ACtGTc?si=JduUzN_1kDnMq0vF) at Sequoia Capital's AI Ascent (Mar 26).
106
+ 🎉 Apr 17, 2024: Andrew Ng cited AutoGen in [The Batch newsletter](https://www.deeplearning.ai/the-batch/issue-245/) and [What's next for AI agentic workflows](https://youtu.be/sal78ACtGTc?si=JduUzN_1kDnMq0vF) at Sequoia Capital's AI Ascent (Mar 26).
105
107
 
106
- :tada: Mar 3, 2024: What's new in AutoGen? 📰[Blog](https://docs.ag2.ai/blog/2024-03-03-AutoGen-Update); 📺[Youtube](https://www.youtube.com/watch?v=j_mtwQiaLGU).
108
+ 🎉 Mar 3, 2024: What's new in AutoGen? 📰[Blog](https://docs.ag2.ai/blog/2024-03-03-AutoGen-Update); 📺[Youtube](https://www.youtube.com/watch?v=j_mtwQiaLGU).
107
109
 
108
- <!-- :tada: Mar 1, 2024: the first AutoGen multi-agent experiment on the challenging [GAIA](https://huggingface.co/spaces/gaia-benchmark/leaderboard) benchmark achieved the No. 1 accuracy in all the three levels. -->
110
+ <!-- 🎉 Mar 1, 2024: the first AutoGen multi-agent experiment on the challenging [GAIA](https://huggingface.co/spaces/gaia-benchmark/leaderboard) benchmark achieved the No. 1 accuracy in all the three levels. -->
109
111
 
110
- <!-- :tada: Jan 30, 2024: AutoGen is highlighted by Peter Lee in Microsoft Research Forum [Keynote](https://t.co/nUBSjPDjqD). -->
112
+ <!-- 🎉 Jan 30, 2024: AutoGen is highlighted by Peter Lee in Microsoft Research Forum [Keynote](https://t.co/nUBSjPDjqD). -->
111
113
 
112
- :tada: Dec 31, 2023: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https://arxiv.org/abs/2308.08155) is selected by [TheSequence: My Five Favorite AI Papers of 2023](https://thesequence.substack.com/p/my-five-favorite-ai-papers-of-2023).
114
+ 🎉 Dec 31, 2023: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https://arxiv.org/abs/2308.08155) is selected by [TheSequence: My Five Favorite AI Papers of 2023](https://thesequence.substack.com/p/my-five-favorite-ai-papers-of-2023).
113
115
 
114
- <!-- :fire: Nov 24: pyautogen [v0.2](https://github.com/ag2ai/ag2/releases/tag/v0.2.0) is released with many updates and new features compared to v0.1.1. It switches to using openai-python v1. Please read the [migration guide](https://docs.ag2.ai/docs/installation/Installation). -->
116
+ <!-- 🔥 Nov 24: pyautogen [v0.2](https://github.com/ag2ai/ag2/releases/tag/v0.2.0) is released with many updates and new features compared to v0.1.1. It switches to using openai-python v1. Please read the [migration guide](https://docs.ag2.ai/docs/installation/Installation). -->
115
117
 
116
- <!-- :fire: Nov 11: OpenAI's Assistants are available in AutoGen and interoperatable with other AutoGen agents! Checkout our [blogpost](https://docs.ag2.ai/blog/2023-11-13-OAI-assistants) for details and examples. -->
118
+ <!-- 🔥 Nov 11: OpenAI's Assistants are available in AutoGen and interoperatable with other AutoGen agents! Checkout our [blogpost](https://docs.ag2.ai/blog/2023-11-13-OAI-assistants) for details and examples. -->
117
119
 
118
- :tada: Nov 8, 2023: AutoGen is selected into [Open100: Top 100 Open Source achievements](https://www.benchcouncil.org/evaluation/opencs/annual.html) 35 days after spinoff from [FLAML](https://github.com/microsoft/FLAML).
120
+ 🎉 Nov 8, 2023: AutoGen is selected into [Open100: Top 100 Open Source achievements](https://www.benchcouncil.org/evaluation/opencs/annual.html) 35 days after spinoff from [FLAML](https://github.com/microsoft/FLAML).
119
121
 
120
- <!-- :tada: Nov 6, 2023: AutoGen is mentioned by Satya Nadella in a [fireside chat](https://youtu.be/0pLBvgYtv6U). -->
122
+ <!-- 🎉 Nov 6, 2023: AutoGen is mentioned by Satya Nadella in a [fireside chat](https://youtu.be/0pLBvgYtv6U). -->
121
123
 
122
- <!-- :tada: Nov 1, 2023: AutoGen is the top trending repo on GitHub in October 2023. -->
124
+ <!-- 🎉 Nov 1, 2023: AutoGen is the top trending repo on GitHub in October 2023. -->
123
125
 
124
- <!-- :tada: Oct 03, 2023: AutoGen spins off from [FLAML](https://github.com/microsoft/FLAML) on GitHub. -->
126
+ <!-- 🎉 Oct 03, 2023: AutoGen spins off from [FLAML](https://github.com/microsoft/FLAML) on GitHub. -->
125
127
 
126
- <!-- :tada: Aug 16: Paper about AutoGen on [arxiv](https://arxiv.org/abs/2308.08155). -->
128
+ <!-- 🎉 Aug 16: Paper about AutoGen on [arxiv](https://arxiv.org/abs/2308.08155). -->
127
129
 
128
- :tada: Mar 29, 2023: AutoGen is first created in [FLAML](https://github.com/microsoft/FLAML).
130
+ 🎉 Mar 29, 2023: AutoGen is first created in [FLAML](https://github.com/microsoft/FLAML).
129
131
 
130
132
  <!--
131
- :fire: FLAML is highlighted in OpenAI's [cookbook](https://github.com/openai/openai-cookbook#related-resources-from-around-the-web).
133
+ 🔥 FLAML is highlighted in OpenAI's [cookbook](https://github.com/openai/openai-cookbook#related-resources-from-around-the-web).
132
134
 
133
- :fire: [autogen](https://docs.ag2.ai/) is released with support for ChatGPT and GPT-4, based on [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://arxiv.org/abs/2303.04673).
135
+ 🔥 [autogen](https://docs.ag2.ai/) is released with support for ChatGPT and GPT-4, based on [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://arxiv.org/abs/2303.04673).
134
136
 
135
- :fire: FLAML supports Code-First AutoML & Tuning – Private Preview in [Microsoft Fabric Data Science](https://learn.microsoft.com/en-us/fabric/data-science/). -->
137
+ 🔥 FLAML supports Code-First AutoML & Tuning – Private Preview in [Microsoft Fabric Data Science](https://learn.microsoft.com/en-us/fabric/data-science/). -->
136
138
 
137
139
  ## What is AG2
138
140
 
@@ -142,10 +144,8 @@ AG2 (formerly AutoGen) is an open-source programming framework for building AI a
142
144
 
143
145
  The project is currently maintained by a [dynamic group of volunteers](MAINTAINERS.md) from several organizations. Contact project administrators Chi Wang and Qingyun Wu via [support@ag2.ai](mailto:support@ag2.ai) if you are interested in becoming a maintainer.
144
146
 
145
-
146
147
  ![AG2 Overview](https://media.githubusercontent.com/media/ag2ai/ag2/refs/heads/main/website/static/img/autogen_agentchat.png)
147
148
 
148
-
149
149
  <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
150
150
  <a href="#readme-top" style="text-decoration: none; color: blue; font-weight: bold;">
151
151
  ↑ Back to Top ↑
@@ -157,15 +157,17 @@ The project is currently maintained by a [dynamic group of volunteers](MAINTAINE
157
157
  -->
158
158
 
159
159
  ## Quickstart
160
+
160
161
  The easiest way to start playing is
162
+
161
163
  1. Click below to use the GitHub Codespace
162
164
 
163
- [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/ag2ai/ag2?quickstart=1)
165
+ [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/ag2ai/ag2?quickstart=1)
164
166
 
165
- 2. Copy OAI_CONFIG_LIST_sample to ./notebook folder, name to OAI_CONFIG_LIST, and set the correct configuration.
166
- 3. Start playing with the notebooks!
167
+ 2. Copy OAI_CONFIG_LIST_sample to ./notebook folder, name to OAI_CONFIG_LIST, and set the correct configuration.
168
+ 3. Start playing with the notebooks!
167
169
 
168
- *NOTE*: OAI_CONFIG_LIST_sample lists gpt-4o as the default model. If you use a different model, you may need to revise various system prompts (especially if using weaker models like gpt-4o-mini). Proceed with caution when updating this default and be aware of additional risks related to alignment and safety.
170
+ _NOTE_: OAI_CONFIG_LIST_sample lists gpt-4o as the default model. If you use a different model, you may need to revise various system prompts (especially if using weaker models like gpt-4o-mini). Proceed with caution when updating this default and be aware of additional risks related to alignment and safety.
169
171
 
170
172
  <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
171
173
  <a href="#readme-top" style="text-decoration: none; color: blue; font-weight: bold;">
@@ -245,7 +247,6 @@ The figure below shows an example conversation flow with AG2.
245
247
 
246
248
  ![Agent Chat Example](https://media.githubusercontent.com/media/ag2ai/ag2/refs/heads/main/website/static/img/chat_example.png)
247
249
 
248
-
249
250
  Alternatively, the [sample code](https://github.com/ag2ai/build-with-ag2/blob/main/samples/simple_chat.py) here allows a user to chat with an AG2 agent in ChatGPT style.
250
251
  Please find more [code examples](https://docs.ag2.ai/docs/Examples#automated-multi-agent-chat) for this feature.
251
252
 
@@ -307,7 +308,6 @@ In addition, you can find:
307
308
  Explore detailed implementations with sample code and applications to help you get started with AG2.
308
309
  [Cookbook](https://github.com/ag2ai/build-with-ag2)
309
310
 
310
-
311
311
  ## Related Papers
312
312
 
313
313
  [AutoGen](https://arxiv.org/abs/2308.08155)
@@ -357,6 +357,7 @@ Explore detailed implementations with sample code and applications to help you g
357
357
  ```
358
358
 
359
359
  [StateFlow](https://arxiv.org/abs/2403.11322)
360
+
360
361
  ```
361
362
  @article{wu2024stateflow,
362
363
  title={StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows},
@@ -373,6 +374,7 @@ Explore detailed implementations with sample code and applications to help you g
373
374
  </p>
374
375
 
375
376
  ## Contributors Wall
377
+
376
378
  <a href="https://github.com/ag2ai/ag2/graphs/contributors">
377
379
  <img src="https://contrib.rocks/image?repo=ag2ai/ag2&max=204" />
378
380
  </a>
@@ -384,13 +386,14 @@ Explore detailed implementations with sample code and applications to help you g
384
386
  </p>
385
387
 
386
388
  ## License
389
+
387
390
  This project is licensed under the [Apache License, Version 2.0 (Apache-2.0)](./LICENSE).
388
391
 
389
392
  This project is a spin-off of [AutoGen](https://github.com/microsoft/autogen) and contains code under two licenses:
390
393
 
391
- - The original code from https://github.com/microsoft/autogen is licensed under the MIT License. See the [LICENSE_original_MIT](./license_original/LICENSE_original_MIT) file for details.
394
+ - The original code from https://github.com/microsoft/autogen is licensed under the MIT License. See the [LICENSE_original_MIT](./license_original/LICENSE_original_MIT) file for details.
392
395
 
393
- - Modifications and additions made in this fork are licensed under the Apache License, Version 2.0. See the [LICENSE](./LICENSE) file for the full license text.
396
+ - Modifications and additions made in this fork are licensed under the Apache License, Version 2.0. See the [LICENSE](./LICENSE) file for the full license text.
394
397
 
395
398
  We have documented these changes for clarity and to ensure transparency with our user and contributor community. For more details, please see the [NOTICE](./NOTICE.md) file.
396
399
 
{ag2-0.7.2b1 → ag2-0.7.3}/README.md RENAMED
@@ -12,20 +12,20 @@
12
12
  # [AG2](https://github.com/ag2ai/ag2)
13
13
 
14
14
  [📚 Cite paper](#related-papers).
15
+
15
16
  <!-- <p align="center">
16
17
  <img src="https://github.com/ag2ai/ag2/blob/main/website/static/img/flaml.svg" width=200>
17
18
  <br>
18
19
  </p> -->
19
20
 
20
- > **:tada: IMPORTANT**
21
+ > **🎉 IMPORTANT**
21
22
  >
22
- > :fire: :tada: **Nov 11, 2024:** We are evolving AutoGen into **AG2**!
23
+ > 🔥 🎉 **Nov 11, 2024:** We are evolving AutoGen into **AG2**!
23
24
  > A new organization [AG2AI](https://github.com/ag2ai) is created to host the development of AG2 and related projects with open governance. Check [AG2's new look](https://ag2.ai/).
24
25
  >
25
26
  > We invite collaborators from all organizations and individuals to join the development.
26
27
 
27
-
28
- :fire: :tada: AG2 is available via `pyautogen` (or its alias `autogen` or `ag2`) on PyPI!
28
+ 🔥 🎉 AG2 is available via `pyautogen` (or its alias `autogen` or `ag2`) on PyPI!
29
29
 
30
30
  ```
31
31
  pip install pyautogen
@@ -34,49 +34,48 @@ pip install pyautogen
34
34
  📄 **License:**
35
35
  We adopt the Apache 2.0 license from v0.3. This enhances our commitment to open-source collaboration while providing additional protections for contributors and users alike.
36
36
 
37
+ 🎉 May 29, 2024: DeepLearning.ai launched a new short course [AI Agentic Design Patterns with AutoGen](https://www.deeplearning.ai/short-courses/ai-agentic-design-patterns-with-autogen), made in collaboration with Microsoft and Penn State University, and taught by AutoGen creators [Chi Wang](https://github.com/sonichi) and [Qingyun Wu](https://github.com/qingyun-wu).
37
38
 
38
- :tada: May 29, 2024: DeepLearning.ai launched a new short course [AI Agentic Design Patterns with AutoGen](https://www.deeplearning.ai/short-courses/ai-agentic-design-patterns-with-autogen), made in collaboration with Microsoft and Penn State University, and taught by AutoGen creators [Chi Wang](https://github.com/sonichi) and [Qingyun Wu](https://github.com/qingyun-wu).
39
-
40
- :tada: May 24, 2024: Foundation Capital published an article on [Forbes: The Promise of Multi-Agent AI](https://www.forbes.com/sites/joannechen/2024/05/24/the-promise-of-multi-agent-ai/?sh=2c1e4f454d97) and a video [AI in the Real World Episode 2: Exploring Multi-Agent AI and AutoGen with Chi Wang](https://www.youtube.com/watch?v=RLwyXRVvlNk).
39
+ 🎉 May 24, 2024: Foundation Capital published an article on [Forbes: The Promise of Multi-Agent AI](https://www.forbes.com/sites/joannechen/2024/05/24/the-promise-of-multi-agent-ai/?sh=2c1e4f454d97) and a video [AI in the Real World Episode 2: Exploring Multi-Agent AI and AutoGen with Chi Wang](https://www.youtube.com/watch?v=RLwyXRVvlNk).
41
40
 
42
- :tada: May 13, 2024: [The Economist](https://www.economist.com/science-and-technology/2024/05/13/todays-ai-models-are-impressive-teams-of-them-will-be-formidable) published an article about multi-agent systems (MAS) following a January 2024 interview with [Chi Wang](https://github.com/sonichi).
41
+ 🎉 May 13, 2024: [The Economist](https://www.economist.com/science-and-technology/2024/05/13/todays-ai-models-are-impressive-teams-of-them-will-be-formidable) published an article about multi-agent systems (MAS) following a January 2024 interview with [Chi Wang](https://github.com/sonichi).
43
42
 
44
- :tada: May 11, 2024: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://openreview.net/pdf?id=uAjxFFing2) received the best paper award at the [ICLR 2024 LLM Agents Workshop](https://llmagents.github.io/).
43
+ 🎉 May 11, 2024: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://openreview.net/pdf?id=uAjxFFing2) received the best paper award at the [ICLR 2024 LLM Agents Workshop](https://llmagents.github.io/).
45
44
 
46
- <!-- :tada: Apr 26, 2024: [AutoGen.NET](https://docs.ag2.ai/ag2-for-net/) is available for .NET developers! -->
45
+ <!-- 🎉 Apr 26, 2024: [AutoGen.NET](https://docs.ag2.ai/ag2-for-net/) is available for .NET developers! -->
47
46
 
48
- :tada: Apr 17, 2024: Andrew Ng cited AutoGen in [The Batch newsletter](https://www.deeplearning.ai/the-batch/issue-245/) and [What's next for AI agentic workflows](https://youtu.be/sal78ACtGTc?si=JduUzN_1kDnMq0vF) at Sequoia Capital's AI Ascent (Mar 26).
47
+ 🎉 Apr 17, 2024: Andrew Ng cited AutoGen in [The Batch newsletter](https://www.deeplearning.ai/the-batch/issue-245/) and [What's next for AI agentic workflows](https://youtu.be/sal78ACtGTc?si=JduUzN_1kDnMq0vF) at Sequoia Capital's AI Ascent (Mar 26).
49
48
 
50
- :tada: Mar 3, 2024: What's new in AutoGen? 📰[Blog](https://docs.ag2.ai/blog/2024-03-03-AutoGen-Update); 📺[Youtube](https://www.youtube.com/watch?v=j_mtwQiaLGU).
49
+ 🎉 Mar 3, 2024: What's new in AutoGen? 📰[Blog](https://docs.ag2.ai/blog/2024-03-03-AutoGen-Update); 📺[Youtube](https://www.youtube.com/watch?v=j_mtwQiaLGU).
51
50
 
52
- <!-- :tada: Mar 1, 2024: the first AutoGen multi-agent experiment on the challenging [GAIA](https://huggingface.co/spaces/gaia-benchmark/leaderboard) benchmark achieved the No. 1 accuracy in all the three levels. -->
51
+ <!-- 🎉 Mar 1, 2024: the first AutoGen multi-agent experiment on the challenging [GAIA](https://huggingface.co/spaces/gaia-benchmark/leaderboard) benchmark achieved the No. 1 accuracy in all the three levels. -->
53
52
 
54
- <!-- :tada: Jan 30, 2024: AutoGen is highlighted by Peter Lee in Microsoft Research Forum [Keynote](https://t.co/nUBSjPDjqD). -->
53
+ <!-- 🎉 Jan 30, 2024: AutoGen is highlighted by Peter Lee in Microsoft Research Forum [Keynote](https://t.co/nUBSjPDjqD). -->
55
54
 
56
- :tada: Dec 31, 2023: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https://arxiv.org/abs/2308.08155) is selected by [TheSequence: My Five Favorite AI Papers of 2023](https://thesequence.substack.com/p/my-five-favorite-ai-papers-of-2023).
55
+ 🎉 Dec 31, 2023: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https://arxiv.org/abs/2308.08155) is selected by [TheSequence: My Five Favorite AI Papers of 2023](https://thesequence.substack.com/p/my-five-favorite-ai-papers-of-2023).
57
56
 
58
- <!-- :fire: Nov 24: pyautogen [v0.2](https://github.com/ag2ai/ag2/releases/tag/v0.2.0) is released with many updates and new features compared to v0.1.1. It switches to using openai-python v1. Please read the [migration guide](https://docs.ag2.ai/docs/installation/Installation). -->
57
+ <!-- 🔥 Nov 24: pyautogen [v0.2](https://github.com/ag2ai/ag2/releases/tag/v0.2.0) is released with many updates and new features compared to v0.1.1. It switches to using openai-python v1. Please read the [migration guide](https://docs.ag2.ai/docs/installation/Installation). -->
59
58
 
60
- <!-- :fire: Nov 11: OpenAI's Assistants are available in AutoGen and interoperatable with other AutoGen agents! Checkout our [blogpost](https://docs.ag2.ai/blog/2023-11-13-OAI-assistants) for details and examples. -->
59
+ <!-- 🔥 Nov 11: OpenAI's Assistants are available in AutoGen and interoperatable with other AutoGen agents! Checkout our [blogpost](https://docs.ag2.ai/blog/2023-11-13-OAI-assistants) for details and examples. -->
61
60
 
62
- :tada: Nov 8, 2023: AutoGen is selected into [Open100: Top 100 Open Source achievements](https://www.benchcouncil.org/evaluation/opencs/annual.html) 35 days after spinoff from [FLAML](https://github.com/microsoft/FLAML).
61
+ 🎉 Nov 8, 2023: AutoGen is selected into [Open100: Top 100 Open Source achievements](https://www.benchcouncil.org/evaluation/opencs/annual.html) 35 days after spinoff from [FLAML](https://github.com/microsoft/FLAML).
63
62
 
64
- <!-- :tada: Nov 6, 2023: AutoGen is mentioned by Satya Nadella in a [fireside chat](https://youtu.be/0pLBvgYtv6U). -->
63
+ <!-- 🎉 Nov 6, 2023: AutoGen is mentioned by Satya Nadella in a [fireside chat](https://youtu.be/0pLBvgYtv6U). -->
65
64
 
66
- <!-- :tada: Nov 1, 2023: AutoGen is the top trending repo on GitHub in October 2023. -->
65
+ <!-- 🎉 Nov 1, 2023: AutoGen is the top trending repo on GitHub in October 2023. -->
67
66
 
68
- <!-- :tada: Oct 03, 2023: AutoGen spins off from [FLAML](https://github.com/microsoft/FLAML) on GitHub. -->
67
+ <!-- 🎉 Oct 03, 2023: AutoGen spins off from [FLAML](https://github.com/microsoft/FLAML) on GitHub. -->
69
68
 
70
- <!-- :tada: Aug 16: Paper about AutoGen on [arxiv](https://arxiv.org/abs/2308.08155). -->
69
+ <!-- 🎉 Aug 16: Paper about AutoGen on [arxiv](https://arxiv.org/abs/2308.08155). -->
71
70
 
72
- :tada: Mar 29, 2023: AutoGen is first created in [FLAML](https://github.com/microsoft/FLAML).
71
+ 🎉 Mar 29, 2023: AutoGen is first created in [FLAML](https://github.com/microsoft/FLAML).
73
72
 
74
73
  <!--
75
- :fire: FLAML is highlighted in OpenAI's [cookbook](https://github.com/openai/openai-cookbook#related-resources-from-around-the-web).
74
+ 🔥 FLAML is highlighted in OpenAI's [cookbook](https://github.com/openai/openai-cookbook#related-resources-from-around-the-web).
76
75
 
77
- :fire: [autogen](https://docs.ag2.ai/) is released with support for ChatGPT and GPT-4, based on [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://arxiv.org/abs/2303.04673).
76
+ 🔥 [autogen](https://docs.ag2.ai/) is released with support for ChatGPT and GPT-4, based on [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://arxiv.org/abs/2303.04673).
78
77
 
79
- :fire: FLAML supports Code-First AutoML & Tuning – Private Preview in [Microsoft Fabric Data Science](https://learn.microsoft.com/en-us/fabric/data-science/). -->
78
+ 🔥 FLAML supports Code-First AutoML & Tuning – Private Preview in [Microsoft Fabric Data Science](https://learn.microsoft.com/en-us/fabric/data-science/). -->
80
79
 
81
80
  ## What is AG2
82
81
 
@@ -86,10 +85,8 @@ AG2 (formerly AutoGen) is an open-source programming framework for building AI a
86
85
 
87
86
  The project is currently maintained by a [dynamic group of volunteers](MAINTAINERS.md) from several organizations. Contact project administrators Chi Wang and Qingyun Wu via [support@ag2.ai](mailto:support@ag2.ai) if you are interested in becoming a maintainer.
88
87
 
89
-
90
88
  ![AG2 Overview](https://media.githubusercontent.com/media/ag2ai/ag2/refs/heads/main/website/static/img/autogen_agentchat.png)
91
89
 
92
-
93
90
  <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
94
91
  <a href="#readme-top" style="text-decoration: none; color: blue; font-weight: bold;">
95
92
  ↑ Back to Top ↑
@@ -101,15 +98,17 @@ The project is currently maintained by a [dynamic group of volunteers](MAINTAINE
101
98
  -->
102
99
 
103
100
  ## Quickstart
101
+
104
102
  The easiest way to start playing is
103
+
105
104
  1. Click below to use the GitHub Codespace
106
105
 
107
- [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/ag2ai/ag2?quickstart=1)
106
+ [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/ag2ai/ag2?quickstart=1)
108
107
 
109
- 2. Copy OAI_CONFIG_LIST_sample to ./notebook folder, name to OAI_CONFIG_LIST, and set the correct configuration.
110
- 3. Start playing with the notebooks!
108
+ 2. Copy OAI_CONFIG_LIST_sample to ./notebook folder, name to OAI_CONFIG_LIST, and set the correct configuration.
109
+ 3. Start playing with the notebooks!
111
110
 
112
- *NOTE*: OAI_CONFIG_LIST_sample lists gpt-4o as the default model. If you use a different model, you may need to revise various system prompts (especially if using weaker models like gpt-4o-mini). Proceed with caution when updating this default and be aware of additional risks related to alignment and safety.
111
+ _NOTE_: OAI_CONFIG_LIST_sample lists gpt-4o as the default model. If you use a different model, you may need to revise various system prompts (especially if using weaker models like gpt-4o-mini). Proceed with caution when updating this default and be aware of additional risks related to alignment and safety.
113
112
 
114
113
  <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
115
114
  <a href="#readme-top" style="text-decoration: none; color: blue; font-weight: bold;">
@@ -189,7 +188,6 @@ The figure below shows an example conversation flow with AG2.
189
188
 
190
189
  ![Agent Chat Example](https://media.githubusercontent.com/media/ag2ai/ag2/refs/heads/main/website/static/img/chat_example.png)
191
190
 
192
-
193
191
  Alternatively, the [sample code](https://github.com/ag2ai/build-with-ag2/blob/main/samples/simple_chat.py) here allows a user to chat with an AG2 agent in ChatGPT style.
194
192
  Please find more [code examples](https://docs.ag2.ai/docs/Examples#automated-multi-agent-chat) for this feature.
195
193
 
@@ -251,7 +249,6 @@ In addition, you can find:
251
249
  Explore detailed implementations with sample code and applications to help you get started with AG2.
252
250
  [Cookbook](https://github.com/ag2ai/build-with-ag2)
253
251
 
254
-
255
252
  ## Related Papers
256
253
 
257
254
  [AutoGen](https://arxiv.org/abs/2308.08155)
@@ -301,6 +298,7 @@ Explore detailed implementations with sample code and applications to help you g
301
298
  ```
302
299
 
303
300
  [StateFlow](https://arxiv.org/abs/2403.11322)
301
+
304
302
  ```
305
303
  @article{wu2024stateflow,
306
304
  title={StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows},
@@ -317,6 +315,7 @@ Explore detailed implementations with sample code and applications to help you g
317
315
  </p>
318
316
 
319
317
  ## Contributors Wall
318
+
320
319
  <a href="https://github.com/ag2ai/ag2/graphs/contributors">
321
320
  <img src="https://contrib.rocks/image?repo=ag2ai/ag2&max=204" />
322
321
  </a>
@@ -328,12 +327,13 @@ Explore detailed implementations with sample code and applications to help you g
328
327
  </p>
329
328
 
330
329
  ## License
330
+
331
331
  This project is licensed under the [Apache License, Version 2.0 (Apache-2.0)](./LICENSE).
332
332
 
333
333
  This project is a spin-off of [AutoGen](https://github.com/microsoft/autogen) and contains code under two licenses:
334
334
 
335
- - The original code from https://github.com/microsoft/autogen is licensed under the MIT License. See the [LICENSE_original_MIT](./license_original/LICENSE_original_MIT) file for details.
335
+ - The original code from https://github.com/microsoft/autogen is licensed under the MIT License. See the [LICENSE_original_MIT](./license_original/LICENSE_original_MIT) file for details.
336
336
 
337
- - Modifications and additions made in this fork are licensed under the Apache License, Version 2.0. See the [LICENSE](./LICENSE) file for the full license text.
337
+ - Modifications and additions made in this fork are licensed under the Apache License, Version 2.0. See the [LICENSE](./LICENSE) file for the full license text.
338
338
 
339
339
  We have documented these changes for clarity and to ensure transparency with our user and contributor community. For more details, please see the [NOTICE](./NOTICE.md) file.
{ag2-0.7.2b1 → ag2-0.7.3/ag2.egg-info}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: ag2
3
- Version: 0.7.2b1
3
+ Version: 0.7.3
4
4
  Summary: Alias package for pyautogen
5
5
  Home-page: https://github.com/ag2ai/ag2
6
6
  Author: Chi Wang & Qingyun Wu
@@ -19,6 +19,9 @@ Provides-Extra: retrievechat-pgvector
19
19
  Provides-Extra: retrievechat-mongodb
20
20
  Provides-Extra: retrievechat-qdrant
21
21
  Provides-Extra: graph-rag-falkor-db
22
+ Provides-Extra: rag
23
+ Provides-Extra: crawl4ai
24
+ Provides-Extra: browser-use
22
25
  Provides-Extra: neo4j
23
26
  Provides-Extra: twilio
24
27
  Provides-Extra: interop-crewai
@@ -68,20 +71,20 @@ License-File: NOTICE.md
68
71
  # [AG2](https://github.com/ag2ai/ag2)
69
72
 
70
73
  [📚 Cite paper](#related-papers).
74
+
71
75
  <!-- <p align="center">
72
76
  <img src="https://github.com/ag2ai/ag2/blob/main/website/static/img/flaml.svg" width=200>
73
77
  <br>
74
78
  </p> -->
75
79
 
76
- > **:tada: IMPORTANT**
80
+ > **🎉 IMPORTANT**
77
81
  >
78
- > :fire: :tada: **Nov 11, 2024:** We are evolving AutoGen into **AG2**!
82
+ > 🔥 🎉 **Nov 11, 2024:** We are evolving AutoGen into **AG2**!
79
83
  > A new organization [AG2AI](https://github.com/ag2ai) is created to host the development of AG2 and related projects with open governance. Check [AG2's new look](https://ag2.ai/).
80
84
  >
81
85
  > We invite collaborators from all organizations and individuals to join the development.
82
86
 
83
-
84
- :fire: :tada: AG2 is available via `pyautogen` (or its alias `autogen` or `ag2`) on PyPI!
87
+ 🔥 🎉 AG2 is available via `pyautogen` (or its alias `autogen` or `ag2`) on PyPI!
85
88
 
86
89
  ```
87
90
  pip install pyautogen
@@ -90,49 +93,48 @@ pip install pyautogen
90
93
  📄 **License:**
91
94
  We adopt the Apache 2.0 license from v0.3. This enhances our commitment to open-source collaboration while providing additional protections for contributors and users alike.
92
95
 
96
+ 🎉 May 29, 2024: DeepLearning.ai launched a new short course [AI Agentic Design Patterns with AutoGen](https://www.deeplearning.ai/short-courses/ai-agentic-design-patterns-with-autogen), made in collaboration with Microsoft and Penn State University, and taught by AutoGen creators [Chi Wang](https://github.com/sonichi) and [Qingyun Wu](https://github.com/qingyun-wu).
93
97
 
94
- :tada: May 29, 2024: DeepLearning.ai launched a new short course [AI Agentic Design Patterns with AutoGen](https://www.deeplearning.ai/short-courses/ai-agentic-design-patterns-with-autogen), made in collaboration with Microsoft and Penn State University, and taught by AutoGen creators [Chi Wang](https://github.com/sonichi) and [Qingyun Wu](https://github.com/qingyun-wu).
95
-
96
- :tada: May 24, 2024: Foundation Capital published an article on [Forbes: The Promise of Multi-Agent AI](https://www.forbes.com/sites/joannechen/2024/05/24/the-promise-of-multi-agent-ai/?sh=2c1e4f454d97) and a video [AI in the Real World Episode 2: Exploring Multi-Agent AI and AutoGen with Chi Wang](https://www.youtube.com/watch?v=RLwyXRVvlNk).
98
+ 🎉 May 24, 2024: Foundation Capital published an article on [Forbes: The Promise of Multi-Agent AI](https://www.forbes.com/sites/joannechen/2024/05/24/the-promise-of-multi-agent-ai/?sh=2c1e4f454d97) and a video [AI in the Real World Episode 2: Exploring Multi-Agent AI and AutoGen with Chi Wang](https://www.youtube.com/watch?v=RLwyXRVvlNk).
97
99
 
98
- :tada: May 13, 2024: [The Economist](https://www.economist.com/science-and-technology/2024/05/13/todays-ai-models-are-impressive-teams-of-them-will-be-formidable) published an article about multi-agent systems (MAS) following a January 2024 interview with [Chi Wang](https://github.com/sonichi).
100
+ 🎉 May 13, 2024: [The Economist](https://www.economist.com/science-and-technology/2024/05/13/todays-ai-models-are-impressive-teams-of-them-will-be-formidable) published an article about multi-agent systems (MAS) following a January 2024 interview with [Chi Wang](https://github.com/sonichi).
99
101
 
100
- :tada: May 11, 2024: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://openreview.net/pdf?id=uAjxFFing2) received the best paper award at the [ICLR 2024 LLM Agents Workshop](https://llmagents.github.io/).
102
+ 🎉 May 11, 2024: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://openreview.net/pdf?id=uAjxFFing2) received the best paper award at the [ICLR 2024 LLM Agents Workshop](https://llmagents.github.io/).
101
103
 
102
- <!-- :tada: Apr 26, 2024: [AutoGen.NET](https://docs.ag2.ai/ag2-for-net/) is available for .NET developers! -->
104
+ <!-- 🎉 Apr 26, 2024: [AutoGen.NET](https://docs.ag2.ai/ag2-for-net/) is available for .NET developers! -->
103
105
 
104
- :tada: Apr 17, 2024: Andrew Ng cited AutoGen in [The Batch newsletter](https://www.deeplearning.ai/the-batch/issue-245/) and [What's next for AI agentic workflows](https://youtu.be/sal78ACtGTc?si=JduUzN_1kDnMq0vF) at Sequoia Capital's AI Ascent (Mar 26).
106
+ 🎉 Apr 17, 2024: Andrew Ng cited AutoGen in [The Batch newsletter](https://www.deeplearning.ai/the-batch/issue-245/) and [What's next for AI agentic workflows](https://youtu.be/sal78ACtGTc?si=JduUzN_1kDnMq0vF) at Sequoia Capital's AI Ascent (Mar 26).
105
107
 
106
- :tada: Mar 3, 2024: What's new in AutoGen? 📰[Blog](https://docs.ag2.ai/blog/2024-03-03-AutoGen-Update); 📺[Youtube](https://www.youtube.com/watch?v=j_mtwQiaLGU).
108
+ 🎉 Mar 3, 2024: What's new in AutoGen? 📰[Blog](https://docs.ag2.ai/blog/2024-03-03-AutoGen-Update); 📺[Youtube](https://www.youtube.com/watch?v=j_mtwQiaLGU).
107
109
 
108
- <!-- :tada: Mar 1, 2024: the first AutoGen multi-agent experiment on the challenging [GAIA](https://huggingface.co/spaces/gaia-benchmark/leaderboard) benchmark achieved the No. 1 accuracy in all the three levels. -->
110
+ <!-- 🎉 Mar 1, 2024: the first AutoGen multi-agent experiment on the challenging [GAIA](https://huggingface.co/spaces/gaia-benchmark/leaderboard) benchmark achieved the No. 1 accuracy in all the three levels. -->
109
111
 
110
- <!-- :tada: Jan 30, 2024: AutoGen is highlighted by Peter Lee in Microsoft Research Forum [Keynote](https://t.co/nUBSjPDjqD). -->
112
+ <!-- 🎉 Jan 30, 2024: AutoGen is highlighted by Peter Lee in Microsoft Research Forum [Keynote](https://t.co/nUBSjPDjqD). -->
111
113
 
112
- :tada: Dec 31, 2023: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https://arxiv.org/abs/2308.08155) is selected by [TheSequence: My Five Favorite AI Papers of 2023](https://thesequence.substack.com/p/my-five-favorite-ai-papers-of-2023).
114
+ 🎉 Dec 31, 2023: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https://arxiv.org/abs/2308.08155) is selected by [TheSequence: My Five Favorite AI Papers of 2023](https://thesequence.substack.com/p/my-five-favorite-ai-papers-of-2023).
113
115
 
114
- <!-- :fire: Nov 24: pyautogen [v0.2](https://github.com/ag2ai/ag2/releases/tag/v0.2.0) is released with many updates and new features compared to v0.1.1. It switches to using openai-python v1. Please read the [migration guide](https://docs.ag2.ai/docs/installation/Installation). -->
116
+ <!-- 🔥 Nov 24: pyautogen [v0.2](https://github.com/ag2ai/ag2/releases/tag/v0.2.0) is released with many updates and new features compared to v0.1.1. It switches to using openai-python v1. Please read the [migration guide](https://docs.ag2.ai/docs/installation/Installation). -->
115
117
 
116
- <!-- :fire: Nov 11: OpenAI's Assistants are available in AutoGen and interoperatable with other AutoGen agents! Checkout our [blogpost](https://docs.ag2.ai/blog/2023-11-13-OAI-assistants) for details and examples. -->
118
+ <!-- 🔥 Nov 11: OpenAI's Assistants are available in AutoGen and interoperatable with other AutoGen agents! Checkout our [blogpost](https://docs.ag2.ai/blog/2023-11-13-OAI-assistants) for details and examples. -->
117
119
 
118
- :tada: Nov 8, 2023: AutoGen is selected into [Open100: Top 100 Open Source achievements](https://www.benchcouncil.org/evaluation/opencs/annual.html) 35 days after spinoff from [FLAML](https://github.com/microsoft/FLAML).
120
+ 🎉 Nov 8, 2023: AutoGen is selected into [Open100: Top 100 Open Source achievements](https://www.benchcouncil.org/evaluation/opencs/annual.html) 35 days after spinoff from [FLAML](https://github.com/microsoft/FLAML).
119
121
 
120
- <!-- :tada: Nov 6, 2023: AutoGen is mentioned by Satya Nadella in a [fireside chat](https://youtu.be/0pLBvgYtv6U). -->
122
+ <!-- 🎉 Nov 6, 2023: AutoGen is mentioned by Satya Nadella in a [fireside chat](https://youtu.be/0pLBvgYtv6U). -->
121
123
 
122
- <!-- :tada: Nov 1, 2023: AutoGen is the top trending repo on GitHub in October 2023. -->
124
+ <!-- 🎉 Nov 1, 2023: AutoGen is the top trending repo on GitHub in October 2023. -->
123
125
 
124
- <!-- :tada: Oct 03, 2023: AutoGen spins off from [FLAML](https://github.com/microsoft/FLAML) on GitHub. -->
126
+ <!-- 🎉 Oct 03, 2023: AutoGen spins off from [FLAML](https://github.com/microsoft/FLAML) on GitHub. -->
125
127
 
126
- <!-- :tada: Aug 16: Paper about AutoGen on [arxiv](https://arxiv.org/abs/2308.08155). -->
128
+ <!-- 🎉 Aug 16: Paper about AutoGen on [arxiv](https://arxiv.org/abs/2308.08155). -->
127
129
 
128
- :tada: Mar 29, 2023: AutoGen is first created in [FLAML](https://github.com/microsoft/FLAML).
130
+ 🎉 Mar 29, 2023: AutoGen is first created in [FLAML](https://github.com/microsoft/FLAML).
129
131
 
130
132
  <!--
131
- :fire: FLAML is highlighted in OpenAI's [cookbook](https://github.com/openai/openai-cookbook#related-resources-from-around-the-web).
133
+ 🔥 FLAML is highlighted in OpenAI's [cookbook](https://github.com/openai/openai-cookbook#related-resources-from-around-the-web).
132
134
 
133
- :fire: [autogen](https://docs.ag2.ai/) is released with support for ChatGPT and GPT-4, based on [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://arxiv.org/abs/2303.04673).
135
+ 🔥 [autogen](https://docs.ag2.ai/) is released with support for ChatGPT and GPT-4, based on [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://arxiv.org/abs/2303.04673).
134
136
 
135
- :fire: FLAML supports Code-First AutoML & Tuning – Private Preview in [Microsoft Fabric Data Science](https://learn.microsoft.com/en-us/fabric/data-science/). -->
137
+ 🔥 FLAML supports Code-First AutoML & Tuning – Private Preview in [Microsoft Fabric Data Science](https://learn.microsoft.com/en-us/fabric/data-science/). -->
136
138
 
137
139
  ## What is AG2
138
140
 
@@ -142,10 +144,8 @@ AG2 (formerly AutoGen) is an open-source programming framework for building AI a
142
144
 
143
145
  The project is currently maintained by a [dynamic group of volunteers](MAINTAINERS.md) from several organizations. Contact project administrators Chi Wang and Qingyun Wu via [support@ag2.ai](mailto:support@ag2.ai) if you are interested in becoming a maintainer.
144
146
 
145
-
146
147
  ![AG2 Overview](https://media.githubusercontent.com/media/ag2ai/ag2/refs/heads/main/website/static/img/autogen_agentchat.png)
147
148
 
148
-
149
149
  <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
150
150
  <a href="#readme-top" style="text-decoration: none; color: blue; font-weight: bold;">
151
151
  ↑ Back to Top ↑
@@ -157,15 +157,17 @@ The project is currently maintained by a [dynamic group of volunteers](MAINTAINE
157
157
  -->
158
158
 
159
159
  ## Quickstart
160
+
160
161
  The easiest way to start playing is
162
+
161
163
  1. Click below to use the GitHub Codespace
162
164
 
163
- [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/ag2ai/ag2?quickstart=1)
165
+ [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/ag2ai/ag2?quickstart=1)
164
166
 
165
- 2. Copy OAI_CONFIG_LIST_sample to ./notebook folder, name to OAI_CONFIG_LIST, and set the correct configuration.
166
- 3. Start playing with the notebooks!
167
+ 2. Copy OAI_CONFIG_LIST_sample to ./notebook folder, name to OAI_CONFIG_LIST, and set the correct configuration.
168
+ 3. Start playing with the notebooks!
167
169
 
168
- *NOTE*: OAI_CONFIG_LIST_sample lists gpt-4o as the default model. If you use a different model, you may need to revise various system prompts (especially if using weaker models like gpt-4o-mini). Proceed with caution when updating this default and be aware of additional risks related to alignment and safety.
170
+ _NOTE_: OAI_CONFIG_LIST_sample lists gpt-4o as the default model. If you use a different model, you may need to revise various system prompts (especially if using weaker models like gpt-4o-mini). Proceed with caution when updating this default and be aware of additional risks related to alignment and safety.
169
171
 
170
172
  <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
171
173
  <a href="#readme-top" style="text-decoration: none; color: blue; font-weight: bold;">
@@ -245,7 +247,6 @@ The figure below shows an example conversation flow with AG2.
245
247
 
246
248
  ![Agent Chat Example](https://media.githubusercontent.com/media/ag2ai/ag2/refs/heads/main/website/static/img/chat_example.png)
247
249
 
248
-
249
250
  Alternatively, the [sample code](https://github.com/ag2ai/build-with-ag2/blob/main/samples/simple_chat.py) here allows a user to chat with an AG2 agent in ChatGPT style.
250
251
  Please find more [code examples](https://docs.ag2.ai/docs/Examples#automated-multi-agent-chat) for this feature.
251
252
 
@@ -307,7 +308,6 @@ In addition, you can find:
307
308
  Explore detailed implementations with sample code and applications to help you get started with AG2.
308
309
  [Cookbook](https://github.com/ag2ai/build-with-ag2)
309
310
 
310
-
311
311
  ## Related Papers
312
312
 
313
313
  [AutoGen](https://arxiv.org/abs/2308.08155)
@@ -357,6 +357,7 @@ Explore detailed implementations with sample code and applications to help you g
357
357
  ```
358
358
 
359
359
  [StateFlow](https://arxiv.org/abs/2403.11322)
360
+
360
361
  ```
361
362
  @article{wu2024stateflow,
362
363
  title={StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows},
@@ -373,6 +374,7 @@ Explore detailed implementations with sample code and applications to help you g
373
374
  </p>
374
375
 
375
376
  ## Contributors Wall
377
+
376
378
  <a href="https://github.com/ag2ai/ag2/graphs/contributors">
377
379
  <img src="https://contrib.rocks/image?repo=ag2ai/ag2&max=204" />
378
380
  </a>
@@ -384,13 +386,14 @@ Explore detailed implementations with sample code and applications to help you g
384
386
  </p>
385
387
 
386
388
  ## License
389
+
387
390
  This project is licensed under the [Apache License, Version 2.0 (Apache-2.0)](./LICENSE).
388
391
 
389
392
  This project is a spin-off of [AutoGen](https://github.com/microsoft/autogen) and contains code under two licenses:
390
393
 
391
- - The original code from https://github.com/microsoft/autogen is licensed under the MIT License. See the [LICENSE_original_MIT](./license_original/LICENSE_original_MIT) file for details.
394
+ - The original code from https://github.com/microsoft/autogen is licensed under the MIT License. See the [LICENSE_original_MIT](./license_original/LICENSE_original_MIT) file for details.
392
395
 
393
- - Modifications and additions made in this fork are licensed under the Apache License, Version 2.0. See the [LICENSE](./LICENSE) file for the full license text.
396
+ - Modifications and additions made in this fork are licensed under the Apache License, Version 2.0. See the [LICENSE](./LICENSE) file for the full license text.
394
397
 
395
398
  We have documented these changes for clarity and to ensure transparency with our user and contributor community. For more details, please see the [NOTICE](./NOTICE.md) file.
396
399