From cdba4a28c469f6cbe585e1efbf7c76d3c3d0bf3f Mon Sep 17 00:00:00 2001 From: Krishna Shedbalkar <60742358+krishnashed@users.noreply.github.com> Date: Sun, 2 Jun 2024 14:33:00 +0530 Subject: [PATCH 01/10] Update Examples.md --- website/docs/Examples.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/Examples.md b/website/docs/Examples.md index 45c16de4571..5062cc5deff 100644 --- a/website/docs/Examples.md +++ b/website/docs/Examples.md @@ -19,7 +19,7 @@ Links to notebook examples: - Automated Data Visualization by Group Chat (with 3 group member agents and 1 manager agent) - [View Notebook](/docs/notebooks/agentchat_groupchat_vis) - Automated Complex Task Solving by Group Chat (with 6 group member agents and 1 manager agent) - [View Notebook](/docs/notebooks/agentchat_groupchat_research) - Automated Task Solving with Coding & Planning Agents - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_planning.ipynb) -- Automated Task Solving with transition paths specified in a graph - [View Notebook](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_graph_modelling_language_using_select_speaker.ipynb) +- Automated Task Solving with transition paths specified in a graph - [View Notebook](https://microsoft.github.io/autogen/docs/notebooks/agentchat_groupchat_finite_state_machine) - Running a group chat as an inner-monolgue via the SocietyOfMindAgent - [View Notebook](/docs/notebooks/agentchat_society_of_mind) - Running a group chat with custom speaker selection function - [View Notebook](/docs/notebooks/agentchat_groupchat_customized) From 16fa4a722ad39e76f69480b622167d4f91a2261a Mon Sep 17 00:00:00 2001 From: Krishna Shedbalkar <60742358+krishnashed@users.noreply.github.com> Date: Sun, 2 Jun 2024 14:48:30 +0530 Subject: [PATCH 02/10] Update agent_chat.md --- website/docs/Use-Cases/agent_chat.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/Use-Cases/agent_chat.md b/website/docs/Use-Cases/agent_chat.md index 605f149ebb8..ca29291252a 100644 --- a/website/docs/Use-Cases/agent_chat.md +++ b/website/docs/Use-Cases/agent_chat.md @@ -82,7 +82,7 @@ AutoGen, by integrating conversation-driven control utilizing both programming a With the pluggable auto-reply function, one can choose to invoke conversations with other agents depending on the content of the current message and context. For example: - Hierarchical chat like in [OptiGuide](https://github.com/microsoft/optiguide). - [Dynamic Group Chat](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat.ipynb) which is a special form of hierarchical chat. In the system, we register a reply function in the group chat manager, which broadcasts messages and decides who the next speaker will be in a group chat setting. -- [Finite state machine (FSM) based group chat](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_graph_modelling_language_using_select_speaker.ipynb) which is a special form of dynamic group chat. In this approach, a directed transition matrix is fed into group chat. Users can specify legal transitions or specify disallowed transitions. +- [Using Finite State Machine graph to set speaker transitions](https://microsoft.github.io/autogen/docs/notebooks/agentchat_groupchat_finite_state_machine) which is a special form of dynamic group chat. In this approach, a directed transition matrix is fed into group chat. Users can specify legal transitions or specify disallowed transitions. - Nested chat like in [conversational chess](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_chess.ipynb). 2. LLM-Based Function Call From 5b342439ad00a8cc17e3dbd2686c9da609bde867 Mon Sep 17 00:00:00 2001 From: Krishna Shedbalkar <60742358+krishnashed@users.noreply.github.com> Date: Sun, 2 Jun 2024 14:51:43 +0530 Subject: [PATCH 03/10] Update agent_chat.md --- website/docs/Use-Cases/agent_chat.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/Use-Cases/agent_chat.md b/website/docs/Use-Cases/agent_chat.md index ca29291252a..c55b0d29d5d 100644 --- a/website/docs/Use-Cases/agent_chat.md +++ b/website/docs/Use-Cases/agent_chat.md @@ -82,7 +82,7 @@ AutoGen, by integrating conversation-driven control utilizing both programming a With the pluggable auto-reply function, one can choose to invoke conversations with other agents depending on the content of the current message and context. For example: - Hierarchical chat like in [OptiGuide](https://github.com/microsoft/optiguide). - [Dynamic Group Chat](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_groupchat.ipynb) which is a special form of hierarchical chat. In the system, we register a reply function in the group chat manager, which broadcasts messages and decides who the next speaker will be in a group chat setting. -- [Using Finite State Machine graph to set speaker transitions](https://microsoft.github.io/autogen/docs/notebooks/agentchat_groupchat_finite_state_machine) which is a special form of dynamic group chat. In this approach, a directed transition matrix is fed into group chat. Users can specify legal transitions or specify disallowed transitions. +- [Finite State Machine graphs to set speaker transition constraints](https://microsoft.github.io/autogen/docs/notebooks/agentchat_groupchat_finite_state_machine) which is a special form of dynamic group chat. In this approach, a directed transition matrix is fed into group chat. Users can specify legal transitions or specify disallowed transitions. - Nested chat like in [conversational chess](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_chess.ipynb). 2. LLM-Based Function Call From 2c54cc3a560562648682fdafa6ae4f8cd4a55b93 Mon Sep 17 00:00:00 2001 From: Krishna Shedbalkar <60742358+krishnashed@users.noreply.github.com> Date: Sun, 2 Jun 2024 14:53:43 +0530 Subject: [PATCH 04/10] Update Optional-Dependencies.md --- website/docs/installation/Optional-Dependencies.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/installation/Optional-Dependencies.md b/website/docs/installation/Optional-Dependencies.md index f0176ba8fdc..13991023f81 100644 --- a/website/docs/installation/Optional-Dependencies.md +++ b/website/docs/installation/Optional-Dependencies.md @@ -119,7 +119,7 @@ To use a graph in `GroupChat`, particularly for graph visualization, please inst pip install "pyautogen[graph]" ``` -Example notebook: [Graph Modeling Language with using select_speaker](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_graph_modelling_language_using_select_speaker.ipynb) +Example notebook: [Finite State Machine graphs to set speaker transition constraints](https://microsoft.github.io/autogen/docs/notebooks/agentchat_groupchat_finite_state_machine) ## Long Context Handling From 2fb4098fb555d5f527fdfb24c1714ead5434aaa2 Mon Sep 17 00:00:00 2001 From: Krishna Shedbalkar <60742358+krishnashed@users.noreply.github.com> Date: Sun, 2 Jun 2024 14:55:11 +0530 Subject: [PATCH 05/10] Update JSON_mode_example.ipynb --- notebook/JSON_mode_example.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/notebook/JSON_mode_example.ipynb b/notebook/JSON_mode_example.ipynb index fee7d1136e5..9032835e224 100644 --- a/notebook/JSON_mode_example.ipynb +++ b/notebook/JSON_mode_example.ipynb @@ -15,7 +15,7 @@ "The group chat manager can perfrom some simple maths encoded into the agent descriptions on the rating values (made reliable by json mode) and direct requests deemed too coersive to the \"suspicious agent\" \n", "\n", "\n", - "![agent flow](friendly_and_suspicous.jpg)\n", + "![agent flow](./friendly_and_suspicous.jpg)\n", "\n", "\n", "Please find documentation about this feature in OpenAI [here](https://platform.openai.com/docs/guides/text-generation/json-mode).\n", From 616421fa926b948e56c7e42c6b9f148f1a9d4308 Mon Sep 17 00:00:00 2001 From: Krishna Shedbalkar <60742358+krishnashed@users.noreply.github.com> Date: Sun, 2 Jun 2024 15:42:21 +0530 Subject: [PATCH 06/10] Update JSON_mode_example.ipynb --- notebook/JSON_mode_example.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/notebook/JSON_mode_example.ipynb b/notebook/JSON_mode_example.ipynb index 9032835e224..b458181f216 100644 --- a/notebook/JSON_mode_example.ipynb +++ b/notebook/JSON_mode_example.ipynb @@ -15,7 +15,7 @@ "The group chat manager can perfrom some simple maths encoded into the agent descriptions on the rating values (made reliable by json mode) and direct requests deemed too coersive to the \"suspicious agent\" \n", "\n", "\n", - "![agent flow](./friendly_and_suspicous.jpg)\n", + "![agent flow](https://github.com/microsoft/autogen/blob/main/notebook/friendly_and_suspicous.jpg)\n", "\n", "\n", "Please find documentation about this feature in OpenAI [here](https://platform.openai.com/docs/guides/text-generation/json-mode).\n", From e260bef3034ad648d0033e2c78fd824fe58a4684 Mon Sep 17 00:00:00 2001 From: Krishna Shedbalkar <60742358+krishnashed@users.noreply.github.com> Date: Sun, 2 Jun 2024 15:43:06 +0530 Subject: [PATCH 07/10] Update JSON_mode_example.ipynb --- notebook/JSON_mode_example.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/notebook/JSON_mode_example.ipynb b/notebook/JSON_mode_example.ipynb index b458181f216..86e6b98b87f 100644 --- a/notebook/JSON_mode_example.ipynb +++ b/notebook/JSON_mode_example.ipynb @@ -15,7 +15,7 @@ "The group chat manager can perfrom some simple maths encoded into the agent descriptions on the rating values (made reliable by json mode) and direct requests deemed too coersive to the \"suspicious agent\" \n", "\n", "\n", - "![agent flow](https://github.com/microsoft/autogen/blob/main/notebook/friendly_and_suspicous.jpg)\n", + "![agent flow](https://media.githubusercontent.com/media/krishnashed/autogen/broken-links-fix/notebook/friendly_and_suspicous.jpg)\n", "\n", "\n", "Please find documentation about this feature in OpenAI [here](https://platform.openai.com/docs/guides/text-generation/json-mode).\n", From ff37ef67c206a04ca448c7cae38a823f019c2088 Mon Sep 17 00:00:00 2001 From: Krishna Shedbalkar <60742358+krishnashed@users.noreply.github.com> Date: Sun, 2 Jun 2024 15:50:27 +0530 Subject: [PATCH 08/10] Update JSON_mode_example.ipynb --- notebook/JSON_mode_example.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/notebook/JSON_mode_example.ipynb b/notebook/JSON_mode_example.ipynb index 86e6b98b87f..f3adce9dec3 100644 --- a/notebook/JSON_mode_example.ipynb +++ b/notebook/JSON_mode_example.ipynb @@ -15,7 +15,7 @@ "The group chat manager can perfrom some simple maths encoded into the agent descriptions on the rating values (made reliable by json mode) and direct requests deemed too coersive to the \"suspicious agent\" \n", "\n", "\n", - "![agent flow](https://media.githubusercontent.com/media/krishnashed/autogen/broken-links-fix/notebook/friendly_and_suspicous.jpg)\n", + "![agent flow](https://media.githubusercontent.com/media/microsoft/autogen/main/notebook/friendly_and_suspicous.jpg)\n", "\n", "\n", "Please find documentation about this feature in OpenAI [here](https://platform.openai.com/docs/guides/text-generation/json-mode).\n", From a017a9f3369911d3381b46ac4c0b960442b3300b Mon Sep 17 00:00:00 2001 From: Krishna Shedbalkar <60742358+krishnashed@users.noreply.github.com> Date: Sun, 2 Jun 2024 15:52:22 +0530 Subject: [PATCH 09/10] Update agentchat_agentoptimizer.ipynb --- notebook/agentchat_agentoptimizer.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/notebook/agentchat_agentoptimizer.ipynb b/notebook/agentchat_agentoptimizer.ipynb index 7177703ab06..ac82932da97 100644 --- a/notebook/agentchat_agentoptimizer.ipynb +++ b/notebook/agentchat_agentoptimizer.ipynb @@ -16,7 +16,7 @@ "Specifically, given a set of training data, AgentOptimizer would iteratively prompt the LLM to optimize the existing function list of the AssistantAgent and UserProxyAgent with code implementation if necessary. It also includes two strategies, roll-back, and early-stop, to streamline the training process.\n", "In the example scenario, we test the proposed AgentOptimizer in solving problems from the [MATH dataset](https://github.com/hendrycks/math). \n", "\n", - "![AgentOptimizer](../website/blog/2023-12-23-AgentOptimizer/img/agentoptimizer.png)\n", + "![AgentOptimizer](https://media.githubusercontent.com/media/microsoft/autogen/main/website/blog/2023-12-23-AgentOptimizer/img/agentoptimizer.png)\n", "\n", "More information could be found in the [paper](https://arxiv.org/abs/2402.11359).\n", "\n", From 12a01146655fd5a8478bacf29e4107982b1cfa5b Mon Sep 17 00:00:00 2001 From: Krishna Shedbalkar <60742358+krishnashed@users.noreply.github.com> Date: Sun, 2 Jun 2024 15:53:53 +0530 Subject: [PATCH 10/10] Update agentchat_nested_chats_chess.ipynb --- notebook/agentchat_nested_chats_chess.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/notebook/agentchat_nested_chats_chess.ipynb b/notebook/agentchat_nested_chats_chess.ipynb index 3e6ba6239d2..b3e369fba8c 100644 --- a/notebook/agentchat_nested_chats_chess.ipynb +++ b/notebook/agentchat_nested_chats_chess.ipynb @@ -298,7 +298,7 @@ "\n", "The following diagram illustrates the nested chat between the player agent and the board agent.\n", "\n", - "![Conversational Chess](nested-chats-chess.png)\n", + "![Conversational Chess](https://media.githubusercontent.com/media/microsoft/autogen/main/notebook/nested-chats-chess.png)\n", "\n", "See [nested chats tutorial chapter](/docs/tutorial/conversation-patterns#nested-chats)\n", "for more information."