From afe29e88b49b1292e692eb848d531a79341728c5 Mon Sep 17 00:00:00 2001 From: Jack Gerrits Date: Wed, 28 Feb 2024 14:00:13 -0500 Subject: [PATCH 1/3] Split apart ecosystem page, update sidebar --- website/docs/Ecosystem.md | 29 ------------------ website/docs/{FAQ.md => FAQ.mdx} | 22 ++----------- .../{ => ecosystem}/img/ecosystem-fabric.png | Bin .../{ => ecosystem}/img/ecosystem-memgpt.png | Bin .../{ => ecosystem}/img/ecosystem-ollama.png | Bin website/docs/ecosystem/memgpt.md | 7 +++++ website/docs/ecosystem/microsoft-fabric.md | 7 +++++ website/docs/ecosystem/ollama.md | 7 +++++ website/docusaurus.config.js | 21 +++++-------- website/sidebars.js | 1 + 10 files changed, 33 insertions(+), 61 deletions(-) delete mode 100644 website/docs/Ecosystem.md rename website/docs/{FAQ.md => FAQ.mdx} (87%) rename website/docs/{ => ecosystem}/img/ecosystem-fabric.png (100%) rename website/docs/{ => ecosystem}/img/ecosystem-memgpt.png (100%) rename website/docs/{ => ecosystem}/img/ecosystem-ollama.png (100%) create mode 100644 website/docs/ecosystem/memgpt.md create mode 100644 website/docs/ecosystem/microsoft-fabric.md create mode 100644 website/docs/ecosystem/ollama.md diff --git a/website/docs/Ecosystem.md b/website/docs/Ecosystem.md deleted file mode 100644 index 88e3236ddf50..000000000000 --- 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 Example](img/ecosystem-memgpt.png) - -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 - -![Fabric Example](img/ecosystem-fabric.png) - -[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 Example](img/ecosystem-ollama.png) - -[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.mdx similarity index 87% rename from website/docs/FAQ.md rename to website/docs/FAQ.mdx index 9d6df09e02b7..ee9266917173 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) + ## Install the correct package - `pyautogen` diff --git a/website/docs/img/ecosystem-fabric.png b/website/docs/ecosystem/img/ecosystem-fabric.png similarity index 100% rename from website/docs/img/ecosystem-fabric.png rename to website/docs/ecosystem/img/ecosystem-fabric.png diff --git a/website/docs/img/ecosystem-memgpt.png b/website/docs/ecosystem/img/ecosystem-memgpt.png similarity index 100% rename from website/docs/img/ecosystem-memgpt.png rename to website/docs/ecosystem/img/ecosystem-memgpt.png diff --git a/website/docs/img/ecosystem-ollama.png b/website/docs/ecosystem/img/ecosystem-ollama.png similarity index 100% rename from website/docs/img/ecosystem-ollama.png rename to website/docs/ecosystem/img/ecosystem-ollama.png diff --git a/website/docs/ecosystem/memgpt.md b/website/docs/ecosystem/memgpt.md new file mode 100644 index 000000000000..076b0c1d97c6 --- /dev/null +++ b/website/docs/ecosystem/memgpt.md @@ -0,0 +1,7 @@ +# MemGPT + +![MemGPT Example](img/ecosystem-memgpt.png) + +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.md new file mode 100644 index 000000000000..d0593a4a7d04 --- /dev/null +++ b/website/docs/ecosystem/microsoft-fabric.md @@ -0,0 +1,7 @@ +# Microsoft Fabric + +![Fabric Example](img/ecosystem-fabric.png) + +[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.md new file mode 100644 index 000000000000..f2ffaa81e2ca --- /dev/null +++ b/website/docs/ecosystem/ollama.md @@ -0,0 +1,7 @@ +# Ollama + +![Ollama Example](img/ecosystem-ollama.png) + +[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/docusaurus.config.js b/website/docusaurus.config.js index 4a6579229e15..559c0ee91f26 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 +186,10 @@ module.exports = { to: "/docs/llm_configuration/", from: ["/docs/llm_endpoint_configuration/"], }, + { + to: "/docs/llm_configuration/", + from: ["/docs/ecosystem/memgpt/"], + }, ], }, ] diff --git a/website/sidebars.js b/website/sidebars.js index 5b1b9d6896bb..70f07465baee 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 From 8140acc60b5d66c99a28d53a26196ef15ef9a2a4 Mon Sep 17 00:00:00 2001 From: Jack Gerrits Date: Wed, 28 Feb 2024 14:02:47 -0500 Subject: [PATCH 2/3] fix docs 404 --- website/docusaurus.config.js | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/website/docusaurus.config.js b/website/docusaurus.config.js index 559c0ee91f26..e24c539bc3e4 100644 --- a/website/docusaurus.config.js +++ b/website/docusaurus.config.js @@ -190,6 +190,10 @@ module.exports = { to: "/docs/llm_configuration/", from: ["/docs/ecosystem/memgpt/"], }, + { + to: "/docs/Getting-Started", + from: ["/docs/"], + }, ], }, ] From 40ba9e0cb61c887e03cc95d86dfb26bb9eba5ab3 Mon Sep 17 00:00:00 2001 From: Jack Gerrits Date: Wed, 28 Feb 2024 14:08:21 -0500 Subject: [PATCH 3/3] fix redirect and link --- website/docs/installation/Installation.mdx | 2 +- website/docusaurus.config.js | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/website/docs/installation/Installation.mdx b/website/docs/installation/Installation.mdx index b4bce027d35a..3421b7504f0a 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.js index e24c539bc3e4..c4a7d95a31a4 100644 --- a/website/docusaurus.config.js +++ b/website/docusaurus.config.js @@ -187,8 +187,8 @@ module.exports = { from: ["/docs/llm_endpoint_configuration/"], }, { - to: "/docs/llm_configuration/", - from: ["/docs/ecosystem/memgpt/"], + to: "/docs/ecosystem/memgpt/", + from: ["/docs/Ecosystem"], }, { to: "/docs/Getting-Started",