A programming framework for agentic AI
Split apart ecosystem page, update sidebar, other website tweaks (#1812)
Jack Gerrits97923eeed848
diff --git a/website/docs/Ecosystem.md b/website/docs/Ecosystem.mddeleted file mode 100644index 88e3236dd..000000000--- a/website/docs/Ecosystem.md+++ /dev/null@@ -1,29 +0,0 @@-# Ecosystem-This page lists libraries that have integrations with Autogen for LLM applications using multiple agents in alphabetical order. Including your own integration to this list is highly encouraged. Simply open a pull request with a few lines of text, see the dropdown below for more information.---## MemGPT + AutoGen-----MemGPT enables LLMs to manage their own memory and overcome limited context windows. You can use MemGPT to create perpetual chatbots that learn about you and modify their own personalities over time. You can connect MemGPT to your own local filesystems and databases, as well as connect MemGPT to your own tools and APIs. The MemGPT + AutoGen integration allows you to equip any AutoGen agent with MemGPT capabilities.--- [MemGPT + AutoGen Documentation with Code Examples](https://memgpt.readme.io/docs/autogen)---## Microsoft Fabric + AutoGen----[Microsoft Fabric](https://learn.microsoft.com/en-us/fabric/get-started/microsoft-fabric-overview) is an all-in-one analytics solution for enterprises that covers everything from data movement to data science, Real-Time Analytics, and business intelligence. It offers a comprehensive suite of services, including data lake, data engineering, and data integration, all in one place. In this notenook, we give a simple example for using AutoGen in Microsoft Fabric.--- [Microsoft Fabric + AutoGen Code Examples](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_microsoft_fabric.ipynb)--## Ollama + AutoGen----[Ollama](https://ollama.com/) allows the users to run open-source large language models, such as Llama 2, locally. Ollama bundles model weights, configuration, and data into a single package, defined by a Modelfile. It optimizes setup and configuration details, including GPU usage.--- [Ollama + AutoGen instruction](https://ollama.ai/blog/openai-compatibility)diff --git a/website/docs/FAQ.md b/website/docs/FAQ.mdxsimilarity index 87%rename from website/docs/FAQ.mdrename to website/docs/FAQ.mdxindex 9d6df09e0..ee9266917 100644--- a/website/docs/FAQ.md+++ b/website/docs/FAQ.mdx@@ -1,24 +1,8 @@+import TOCInline from '@theme/TOCInline';+# Frequently Asked Questions-- [Install the correct package - `pyautogen`](#install-the-correct-package---pyautogen)-- [Set your API endpoints](#set-your-api-endpoints)- - [Use the constructed configuration list in agents](#use-the-constructed-configuration-list-in-agents)- - [Unexpected keyword argument 'base_url'](#unexpected-keyword-argument-base_url)- - [How does an agent decide which model to pick out of the list?](#how-does-an-agent-decide-which-model-to-pick-out-of-the-list)- - [Can I use non-OpenAI models?](#can-i-use-non-openai-models)-- [Handle Rate Limit Error and Timeout Error](#handle-rate-limit-error-and-timeout-error)-- [How to continue a finished conversation](#how-to-continue-a-finished-conversation)-- [How do we decide what LLM is used for each agent? How many agents can be used? How do we decide how many agents in the group?](#how-do-we-decide-what-llm-is-used-for-each-agent-how-many-agents-can-be-used-how-do-we-decide-how-many-agents-in-the-group)-- [Why is code not saved as file?](#why-is-code-not-saved-as-file)-- [Code execution](#code-execution)- - [Enable Python 3 docker image](#enable-python-3-docker-image)- - [Agents keep thanking each other when using `gpt-3.5-turbo`](#agents-keep-thanking-each-other-when-using-gpt-35-turbo)-- [ChromaDB fails in codespaces because of old version of sqlite3](#chromadb-fails-in-codespaces-because-of-old-version-of-sqlite3)-- [How to register a reply function](#how-to-register-a-reply-function)-- [How to get last message?](#how-to-get-last-message)-- [How to get each agent message?](#how-to-get-each-agent-message)-- [When using autogen docker, is it always necessary to reinstall modules?](#when-using-autogen-docker-is-it-always-necessary-to-reinstall-modules)-- [Agents are throwing due to docker not running, how can I resolve this?](#agents-are-throwing-due-to-docker-not-running-how-can-i-resolve-this)+<TOCInline toc={toc} />## Install the correct package - `pyautogen`diff --git a/website/docs/img/ecosystem-fabric.png b/website/docs/ecosystem/img/ecosystem-fabric.pngsimilarity index 100%rename from website/docs/img/ecosystem-fabric.pngrename to website/docs/ecosystem/img/ecosystem-fabric.pngdiff --git a/website/docs/img/ecosystem-memgpt.png b/website/docs/ecosystem/img/ecosystem-memgpt.pngsimilarity index 100%rename from website/docs/img/ecosystem-memgpt.pngrename to website/docs/ecosystem/img/ecosystem-memgpt.pngdiff --git a/website/docs/img/ecosystem-ollama.png b/website/docs/ecosystem/img/ecosystem-ollama.pngsimilarity index 100%rename from website/docs/img/ecosystem-ollama.pngrename to website/docs/ecosystem/img/ecosystem-ollama.pngdiff --git a/website/docs/ecosystem/memgpt.md b/website/docs/ecosystem/memgpt.mdnew file mode 100644index 000000000..076b0c1d9--- /dev/null+++ b/website/docs/ecosystem/memgpt.md@@ -0,0 +1,7 @@+# MemGPT++++MemGPT enables LLMs to manage their own memory and overcome limited context windows. You can use MemGPT to create perpetual chatbots that learn about you and modify their own personalities over time. You can connect MemGPT to your own local filesystems and databases, as well as connect MemGPT to your own tools and APIs. The MemGPT + AutoGen integration allows you to equip any AutoGen agent with MemGPT capabilities.++- [MemGPT + AutoGen Documentation with Code Examples](https://memgpt.readme.io/docs/autogen)diff --git a/website/docs/ecosystem/microsoft-fabric.md b/website/docs/ecosystem/microsoft-fabric.mdnew file mode 100644index 000000000..d0593a4a7--- /dev/null+++ b/website/docs/ecosystem/microsoft-fabric.md@@ -0,0 +1,7 @@+# Microsoft Fabric++++[Microsoft Fabric](https://learn.microsoft.com/en-us/fabric/get-started/microsoft-fabric-overview) is an all-in-one analytics solution for enterprises that covers everything from data movement to data science, Real-Time Analytics, and business intelligence. It offers a comprehensive suite of services, including data lake, data engineering, and data integration, all in one place. In this notenook, we give a simple example for using AutoGen in Microsoft Fabric.++- [Microsoft Fabric + AutoGen Code Examples](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_microsoft_fabric.ipynb)diff --git a/website/docs/ecosystem/ollama.md b/website/docs/ecosystem/ollama.mdnew file mode 100644index 000000000..f2ffaa81e--- /dev/null+++ b/website/docs/ecosystem/ollama.md@@ -0,0 +1,7 @@+# Ollama++++[Ollama](https://ollama.com/) allows the users to run open-source large language models, such as Llama 2, locally. Ollama bundles model weights, configuration, and data into a single package, defined by a Modelfile. It optimizes setup and configuration details, including GPU usage.++- [Ollama + AutoGen instruction](https://ollama.ai/blog/openai-compatibility)diff --git a/website/docs/installation/Installation.mdx b/website/docs/installation/Installation.mdxindex b4bce027d..3421b7504 100644--- a/website/docs/installation/Installation.mdx+++ b/website/docs/installation/Installation.mdx@@ -81,7 +81,7 @@ pip install pyautogen## Code execution with Docker (default)-Even if you install AutoGen locally, we highly recommend using Docker for [code execution](FAQ.md#code-execution).+Even if you install AutoGen locally, we highly recommend using Docker for [code execution](FAQ.mdx#code-execution).The default behaviour for code-execution agents is for code execution to be performed in a docker container.diff --git a/website/docusaurus.config.js b/website/docusaurus.config.jsindex 4a6579229..c4a7d95a3 100644--- a/website/docusaurus.config.js+++ b/website/docusaurus.config.js@@ -50,7 +50,7 @@ module.exports = {type: "doc",docId: "reference/agentchat/conversable_agent",position: "left",- label: "SDK",+ label: "API",},{ to: "blog", label: "Blog", position: "left" },{@@ -76,18 +76,9 @@ module.exports = {// label: "Notebooks",// },{- label: "Resources",- type: "dropdown",- items: [- {- type: "doc",- docId: "Ecosystem",- },- {- type: "doc",- docId: "Gallery",- },- ],+ type: "doc",+ position: "left",+ docId: "Gallery",},{label: "Other Languages",@@ -195,6 +186,14 @@ module.exports = {to: "/docs/llm_configuration/",from: ["/docs/llm_endpoint_configuration/"],},+ {+ to: "/docs/ecosystem/memgpt/",+ from: ["/docs/Ecosystem"],+ },+ {+ to: "/docs/Getting-Started",+ from: ["/docs/"],+ },],},]diff --git a/website/sidebars.js b/website/sidebars.jsindex 5b1b9d689..70f07465b 100644--- a/website/sidebars.js+++ b/website/sidebars.js@@ -26,6 +26,7 @@{'Use Cases': [{type: 'autogenerated', dirName: 'Use-Cases'}]},'Contribute','Research',+ {'Ecosystem': [{type: 'autogenerated', dirName: 'ecosystem'}]},'Migration-Guide'],// pydoc-markdown auto-generated markdowns from docstrings