mirror of https://github.com/microsoft/autogen.git synced 2026-04-20 03:02:16 -04:00

Files

Matteo Frattaroli ec4f3c0f19 Fix #2643 - groupchat model registration (#2696 )

* remove unused import statement

* fix #2643: register custom model clients within GroupChat

* add docs for fix #2643

* Update website/docs/topics/groupchat/using_custom_models.md

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* Update website/docs/topics/groupchat/using_custom_models.md

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* fix: removed unnecessary llm_config from checking agent

* fix: handle missing config or "config_list" key in config

* fix: code formatting

* Isolate method for internal agents creation

* Add unit test to verify that internal agents' client actually registers ModelClient class

* fix: function arguments formatting

* chore: prepend "select_speaker_auto_" to llm_config and model_client_cls attributes in GroupChat

* feat: use selector's llm_config for speaker selection agent if none is passed to GroupChat

* Update test/agentchat/test_groupchat.py

* Update groupchat.py - moved class parameters around, added to docstring

* Update groupchat.py - added selector to async select speaker functions

* Update test_groupchat.py - Corrected test cases for custom model client class

* Update test_groupchat.py pre-commit tidy

---------

Co-authored-by: Matteo Frattaroli <m.frattroli97@gmail.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Mark Sze <66362098+marklysze@users.noreply.github.com>

2024-10-11 09:05:23 -07:00

blog

Update links on 0.2 website (#3734 )

2024-10-10 13:16:25 -04:00

docs

Fix #2643 - groupchat model registration (#2696 )

2024-10-11 09:05:23 -07:00

src

Update links on 0.2 website (#3734 )

2024-10-10 13:16:25 -04:00

static

Demo Notebook for Using Gemini with VertexAI (#3032 )

2024-07-07 22:11:35 +00:00

.gitignore

Update the auto_feedback_from_code_execution notebook to use code executor (#2366 )

2024-04-18 07:53:19 +00:00

babel.config.js

web-template

2023-08-27 21:30:54 -04:00

build_website.sh

Extend process_notebooks for testing (#1789 )

2024-02-29 20:47:30 +00:00

docusaurus.config.js

Add announcement bar for 0.4 (#3717 )

2024-10-09 16:41:20 -04:00

package.json

add clarity analytics (#2201 )

2024-03-28 23:26:22 +00:00

process_notebooks.py

Update links on 0.2 website (#3734 )

2024-10-10 13:16:25 -04:00

pydoc-markdown.yml

fix some docstring issues affecting rendering (#1739 )

2024-02-20 22:29:39 +00:00

README.md

add RAG under topics (#1990 )

2024-03-14 00:49:39 +00:00

sidebars.js

Autogenstudio docs (#2890 )

2024-06-10 03:29:34 +00:00

yarn.lock

Bump micromatch from 4.0.5 to 4.0.8 in /website (#3417 )

2024-09-25 15:33:19 +00:00

README.md

Website

This website is built using Docusaurus 3, a modern static website generator.

Prerequisites

To build and test documentation locally, begin by downloading and installing Node.js, and then installing Yarn. On Windows, you can install via the npm package manager (npm) which comes bundled with Node.js:

npm install --global yarn

Installation

pip install pydoc-markdown pyyaml colored
cd website
yarn install

Install Quarto

quarto is used to render notebooks.

Install it here.

Note: Ensure that your quarto version is 1.5.23 or higher.

Local Development

Navigate to the website folder and run:

pydoc-markdown
python ./process_notebooks.py render
yarn start

This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.