Upgrade Quarto and use notebook metadata for frontmatter (microsoft#1836

) * Update process_notebook to use metadata instead of a yaml comment * upgrade quarto and version check in tool * formatting * address comments
yorkewoo · Mar 2, 2024 · d604643 · d604643
1 parent 97923ee
commit d604643
Show file tree

Hide file tree

Showing 18 changed files with 208 additions and 244 deletions.
diff --git a/.devcontainer/Dockerfile b/.devcontainer/Dockerfile
@@ -14,13 +14,13 @@ RUN apt-get update \
    && apt-get -y install --no-install-recommends build-essential npm \
    && apt-get autoremove -y \
    && apt-get clean -y \
-   && wget https://github.com/quarto-dev/quarto-cli/releases/download/v1.4.549/quarto-1.4.549-linux-amd64.deb \
-   && dpkg -i quarto-1.4.549-linux-amd64.deb \
-   && rm -rf /var/lib/apt/lists/* quarto-1.4.549-linux-amd64.deb
+   && wget https://github.com/quarto-dev/quarto-cli/releases/download/v1.5.23/quarto-1.5.23-linux-amd64.deb \
+   && dpkg -i quarto-1.5.23-linux-amd64.deb \
+   && rm -rf /var/lib/apt/lists/* quarto-1.5.23-linux-amd64.deb
 ENV DEBIAN_FRONTEND=dialog
 
 # For docs
 RUN npm install --global yarn
 RUN pip install pydoc-markdown
 RUN pip install pyyaml
-RUN pip install colored
+RUN pip install colored
diff --git a/.devcontainer/dev/Dockerfile b/.devcontainer/dev/Dockerfile
@@ -33,12 +33,12 @@ RUN cd website
 RUN yarn install --frozen-lockfile --ignore-engines
 
 RUN arch=$(arch | sed s/aarch64/arm64/ | sed s/x86_64/amd64/) && \
-    wget -q https://github.com/quarto-dev/quarto-cli/releases/download/v1.4.549/quarto-1.4.549-linux-${arch}.tar.gz && \
+    wget -q https://github.com/quarto-dev/quarto-cli/releases/download/v1.5.23/quarto-1.5.23-linux-${arch}.tar.gz && \
     mkdir -p /home/autogen/quarto/ && \
-    tar -xzf quarto-1.4.549-linux-${arch}.tar.gz --directory /home/autogen/quarto/ && \
-    rm quarto-1.4.549-linux-${arch}.tar.gz
+    tar -xzf quarto-1.5.23-linux-${arch}.tar.gz --directory /home/autogen/quarto/ && \
+    rm quarto-1.5.23-linux-${arch}.tar.gz
 
-ENV PATH="${PATH}:/home/autogen/quarto/quarto-1.4.549/bin/"
+ENV PATH="${PATH}:/home/autogen/quarto/quarto-1.5.23/bin/"
 
 # Exposes the Yarn port for Docusaurus
 EXPOSE 3000

diff --git a/.github/workflows/deploy-website.yml b/.github/workflows/deploy-website.yml
@@ -44,9 +44,9 @@ jobs:
       - name: quarto install
         working-directory: ${{ runner.temp }}
         run: |
-          wget -q https://github.com/quarto-dev/quarto-cli/releases/download/v1.4.549/quarto-1.4.549-linux-amd64.tar.gz
-          tar -xzf quarto-1.4.549-linux-amd64.tar.gz
-          echo "$(pwd)/quarto-1.4.549/bin/" >> $GITHUB_PATH
+          wget -q https://github.com/quarto-dev/quarto-cli/releases/download/v1.5.23/quarto-1.5.23-linux-amd64.tar.gz
+          tar -xzf quarto-1.5.23-linux-amd64.tar.gz
+          echo "$(pwd)/quarto-1.5.23/bin/" >> $GITHUB_PATH
       - name: quarto run
         run: |
           quarto render .
@@ -90,9 +90,9 @@ jobs:
       - name: quarto install
         working-directory: ${{ runner.temp }}
         run: |
-          wget -q https://github.com/quarto-dev/quarto-cli/releases/download/v1.4.549/quarto-1.4.549-linux-amd64.tar.gz
-          tar -xzf quarto-1.4.549-linux-amd64.tar.gz
-          echo "$(pwd)/quarto-1.4.549/bin/" >> $GITHUB_PATH
+          wget -q https://github.com/quarto-dev/quarto-cli/releases/download/v1.5.23/quarto-1.5.23-linux-amd64.tar.gz
+          tar -xzf quarto-1.5.23-linux-amd64.tar.gz
+          echo "$(pwd)/quarto-1.5.23/bin/" >> $GITHUB_PATH
       - name: quarto run
         run: |
           quarto render .

diff --git a/notebook/agentchat_RetrieveChat.ipynb b/notebook/agentchat_RetrieveChat.ipynb
@@ -5,12 +5,6 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<!--\n",
-    "tags: [\"RAG\"]\n",
-    "description: |\n",
-    "    Explore the use of AutoGen's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning.\n",
-    "-->\n",
-    "\n",
     "# Using RetrieveChat for Retrieve Augmented Code Generation and Question Answering\n",
     "\n",
     "AutoGen offers conversable agents powered by LLM, tool or human, which can be used to perform tasks collectively via automated chat. This framework allows tool use and human participation through multi-agent conversation.\n",
@@ -3020,6 +3014,10 @@
   }
  ],
  "metadata": {
+  "front_matter": {
+    "tags": ["RAG"],
+    "description": "Explore the use of AutoGen's RetrieveChat for tasks like code generation from docstrings, answering complex questions with human feedback, and exploiting features like Update Context, custom prompts, and few-shot learning."
+  },
   "kernelspec": {
    "display_name": "Python 3 (ipykernel)",
    "language": "python",
@@ -3036,8 +3034,8 @@
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
    "version": "3.10.12"
-},
-"test_skip": "Requires interactive usage"
+  },
+  "skip_test": "Requires interactive usage"
  },
  "nbformat": 4,
  "nbformat_minor": 4

diff --git a/notebook/agentchat_auto_feedback_from_code_execution.ipynb b/notebook/agentchat_auto_feedback_from_code_execution.ipynb
@@ -8,12 +8,6 @@
     }
    },
    "source": [
-    "<!--\n",
-    "tags: [\"code generation\", \"debugging\"]\n",
-    "description: |\n",
-    "    Use conversable language learning model agents to solve tasks and provide automatic feedback through a comprehensive example of writing, executing, and debugging Python code to compare stock price changes.\n",
-    "-->\n",
-    "\n",
     "# Task Solving with Code Generation, Execution and Debugging\n",
     "\n",
     "AutoGen offers conversable LLM agents, which can be used to solve various tasks with human or automatic feedback, including tasks that require using tools via code.\n",
@@ -1098,6 +1092,13 @@
   }
  ],
  "metadata": {
+  "front_matter": {
+    "tags": [
+      "code generation",
+      "debugging"
+    ],
+    "description": "Use conversable language learning model agents to solve tasks and provide automatic feedback through a comprehensive example of writing, executing, and debugging Python code to compare stock price changes."
+  },
   "kernelspec": {
    "display_name": "Python 3",
    "language": "python",

diff --git a/notebook/agentchat_function_call_async.ipynb b/notebook/agentchat_function_call_async.ipynb
@@ -5,12 +5,6 @@
    "id": "ae1f50ec",
    "metadata": {},
    "source": [
-    "<!--\n",
-    "tags: [\"code generation\", \"function call\", \"async\"]\n",
-    "description: |\n",
-    "    Learn how to implement both synchronous and asynchronous function calls using AssistantAgent and UserProxyAgent in AutoGen, with examples of their application in individual and group chat settings for task execution with language models.\n",
-    "-->\n",
-    "\n",
     "# Task Solving with Provided Tools as Functions (Asynchronous Function Calls)\n"
    ]
   },
@@ -366,6 +360,10 @@
   }
  ],
  "metadata": {
+  "front_matter": {
+    "tags": ["code generation", "function call", "async"],
+    "description": "Learn how to implement both synchronous and asynchronous function calls using AssistantAgent and UserProxyAgent in AutoGen, with examples of their application in individual and group chat settings for task execution with language models."
+  },
   "kernelspec": {
    "display_name": "flaml_dev",
    "language": "python",

diff --git a/notebook/agentchat_groupchat.ipynb b/notebook/agentchat_groupchat.ipynb
@@ -5,12 +5,6 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<!--\n",
-    "tags: [\"orchestration\", \"group chat\"]\n",
-    "description: |\n",
-    "    Explore the utilization of large language models in automated group chat scenarios, where agents perform tasks collectively, demonstrating how they can be configured, interact with each other, and retrieve specific information from external resources.\n",
-    "-->\n",
-    "\n",
     "# Group Chat\n",
     "\n",
     "AutoGen offers conversable agents powered by LLM, tool or human, which can be used to perform tasks collectively via automated chat. This framework allows tool use and human participation through multi-agent conversation.\n",
@@ -223,6 +217,10 @@
   }
  ],
  "metadata": {
+  "front_matter": {
+    "tags": ["orchestration", "group chat"],
+    "description": "Explore the utilization of large language models in automated group chat scenarios, where agents perform tasks collectively, demonstrating how they can be configured, interact with each other, and retrieve specific information from external resources."
+  },
   "kernelspec": {
    "display_name": "flaml",
    "language": "python",

diff --git a/notebook/agentchat_groupchat_RAG.ipynb b/notebook/agentchat_groupchat_RAG.ipynb
@@ -1,17 +1,5 @@
 {
  "cells": [
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<!--\n",
-    "tags: [\"group chat\", \"orchestration\", \"RAG\"]\n",
-    "description: |\n",
-    "    Implement and manage a multi-agent chat system using AutoGen, where AI assistants retrieve information, generate code, and interact collaboratively to solve complex tasks, especially in areas not covered by their training data.\n",
-    "-->"
-   ]
-  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -1120,6 +1108,10 @@
   }
  ],
  "metadata": {
+ "front_matter": {
+    "tags": ["group chat", "orchestration", "RAG"],
+    "description": "Implement and manage a multi-agent chat system using AutoGen, where AI assistants retrieve information, generate code, and interact collaboratively to solve complex tasks, especially in areas not covered by their training data."
+  },
   "kernelspec": {
    "display_name": "flaml",
    "language": "python",
@@ -1135,7 +1127,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.11.7"
   }
  },
  "nbformat": 4,

diff --git a/notebook/agentchat_groupchat_finite_state_machine.ipynb b/notebook/agentchat_groupchat_finite_state_machine.ipynb
@@ -5,13 +5,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<!--\n",
-    "tags: [\"orchestration\"]\n",
-    "description: |\n",
-    "    Explore the demonstration of the Finite State Machine implementation, which allows the user to input speaker transition contraints.\n",
-    "-->\n",
-    "\n",
-    "# FSM - User can input speaker transition contraints.\n",
+    "# FSM - User can input speaker transition constraints\n",
     "\n",
     "AutoGen offers conversable agents powered by LLM, tool, or human, which can be used to perform tasks collectively via automated chat. This framework allows tool use and human participation through multi-agent conversation.\n",
     "Please find documentation about this feature [here](https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat).\n",
@@ -597,6 +591,12 @@
   }
  ],
  "metadata": {
+  "front_matter": {
+   "description": "Explore the demonstration of the Finite State Machine implementation, which allows the user to input speaker transition constraints.",
+   "tags": [
+    "orchestration"
+   ]
+  },
   "kernelspec": {
    "display_name": "Python 3 (ipykernel)",
    "language": "python",

diff --git a/notebook/agentchat_logging.ipynb b/notebook/agentchat_logging.ipynb
@@ -4,12 +4,6 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<!--\n",
-    "tags: [\"logging\", \"debugging\"]\n",
-    "description: |\n",
-    "    Provide capabilities of runtime logging for debugging and performance analysis.\n",
-    "-->\n",
-    "\n",
     "# Runtime Logging with AutoGen \n",
     "\n",
     "AutoGen offers utilities to log data for debugging and performance analysis. This notebook demonstrates how to use them. \n",
@@ -294,6 +288,13 @@
   }
  ],
  "metadata": {
+  "front_matter": {
+   "description": "Provide capabilities of runtime logging for debugging and performance analysis.",
+   "tags": [
+    "logging",
+    "debugging"
+   ]
+  },
   "kernelspec": {
    "display_name": "autog",
    "language": "python",
@@ -309,7 +310,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.11.7"
   }
  },
  "nbformat": 4,

diff --git a/notebook/agentchat_multi_task_async_chats.ipynb b/notebook/agentchat_multi_task_async_chats.ipynb
@@ -9,12 +9,6 @@
     }
    },
    "source": [
-    "<!--\n",
-    "tags: [\"sequential chat\"]\n",
-    "description: |\n",
-    "    Use conversational agents to solve a set of tasks with a sequence of async chats.\n",
-    "-->\n",
-    "\n",
     "# Solving Multiple Tasks in a Sequence of Async Chats\n",
     "\n",
     "This notebook showcases how to use the new chat interface of conversational agents in AutoGen: a_initiate_chats, to conduct a series of tasks. Similar to \"notebook/agentchat_microsoft_fabric.ipynb\", this new interface allows one to pass multiple tasks and their corresponding dedicated agents and execute concurrently. Depending on the prerequisite task(s), the tasks will be solved concurrently, with the summaries from prerequisite task(s) provided to subsequent tasks as context, if the `summary_method` argument is specified.\n",
@@ -1484,6 +1478,10 @@
   }
  ],
  "metadata": {
+  "front_matter": {
+    "tags": ["sequential chat"],
+    "description": "Use conversational agents to solve a set of tasks with a sequence of async chats."
+  },
   "kernelspec": {
    "display_name": "Python 3",
    "language": "python",
@@ -1499,7 +1497,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.8"
+   "version": "3.11.7"
   },
   "vscode": {
    "interpreter": {

diff --git a/notebook/agentchat_multi_task_chats.ipynb b/notebook/agentchat_multi_task_chats.ipynb
@@ -9,12 +9,6 @@
     }
    },
    "source": [
-    "<!--\n",
-    "tags: [\"sequential chat\"]\n",
-    "description: |\n",
-    "    Use conversational agents to solve a set of tasks with a sequence of chats.\n",
-    "-->\n",
-    "\n",
     "# Solving Multiple Tasks in a Sequence of Chats\n",
     "\n",
     "This notebook showcases how to use the new chat interface of conversational agents in AutoGen: initiate_chats, to conduct a series of tasks. This new interface allows one to pass multiple tasks and their corresponding dedicated agents. Once initiate_chats is invoked, the tasks will be solved sequentially, with the summaries from previous tasks provided to subsequent tasks as context, if the `summary_method` argument is specified.\n",
@@ -1536,6 +1530,12 @@
   }
  ],
  "metadata": {
+  "front_matter": {
+   "description": "Use conversational agents to solve a set of tasks with a sequence of chats.",
+   "tags": [
+    "sequential chat"
+   ]
+  },
   "kernelspec": {
    "display_name": "Python 3",
    "language": "python",

diff --git a/notebook/agentchat_nestedchat.ipynb b/notebook/agentchat_nestedchat.ipynb
@@ -9,12 +9,6 @@
     }
    },
    "source": [
-    "<!--\n",
-    "tags: [\"nested chat\"]\n",
-    "description: |\n",
-    "    Solve complex tasks with one or more sequence chats nested as inner monologue.\n",
-    "-->\n",
-    "\n",
     "# Solving Complex Tasks with Nested Chats\n",
     "\n",
     "This notebook shows how you can leverage \"nested chats\" to solve complex task with AutoGen. Nested chats allow AutoGen agents to use other agents as their inner monologue to accomplish tasks. This abstraction is powerful as it allows you to compose agents in rich ways. This notebook shows how you can nest a pretty complex sequence of chats among _inner_ agents inside an _outer_ agent.\n",
@@ -814,6 +808,10 @@
   }
  ],
  "metadata": {
+  "front_matter": {
+    "tags": ["nested chat"],
+    "description": "Solve complex tasks with one or more sequence chats nested as inner monologue."
+  },
   "kernelspec": {
    "display_name": "Python 3",
    "language": "python",

diff --git a/notebook/agentchat_society_of_mind.ipynb b/notebook/agentchat_society_of_mind.ipynb
@@ -5,12 +5,6 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<!--\n",
-    "tags: [\"orchestration\"]\n",
-    "description: |\n",
-    "    Explore the demonstration of the SocietyOfMindAgent in the AutoGen library, which runs a group chat as an internal monologue, but appears to the external world as a single agent, offering a structured way to manage complex interactions among multiple agents and handle issues such as extracting responses from complex dialogues and dealing with context window constraints.\n",
-    "-->\n",
-    "\n",
     "# SocietyOfMindAgent\n",
     "\n",
     "This notebook demonstrates the SocietyOfMindAgent, which runs a group chat as an internal monologue, but appears to the external world as a single agent. This confers three distinct advantages:\n",
@@ -362,6 +356,10 @@
   }
  ],
  "metadata": {
+  "front_matter": {
+    "tags": ["orchestration"],
+    "description": "Explore the demonstration of the SocietyOfMindAgent in the AutoGen library, which runs a group chat as an internal monologue, but appears to the external world as a single agent, offering a structured way to manage complex interactions among multiple agents and handle issues such as extracting responses from complex dialogues and dealing with context window constraints."
+  },
   "kernelspec": {
    "display_name": "Python 3 (ipykernel)",
    "language": "python",