mirror of
https://github.com/microsoft/autogen.git
synced 2026-02-11 09:25:46 -05:00
74298cda2c
* update intro * update intro * tutorial * update notebook * update notebooks * update * merge * add conversation patterns * rename; delete unused files. * Reorganize new guides * Improve intro, fix typos * add what is next * outline for code executor * initiate chats png * Improve language * Improve language of human in the loop tutorial * update * update * Update group chat * code executor * update convsersation patterns * update code executor section to use legacy code executor * update conversation pattern * redirect * update figures * update whats next * Break down chapter 2 into two chapters * udpate * fix website build * Minor corrections of typos and grammar. * remove broken links, update sidebar * code executor update * Suggest changes to the code executor section * update what is next * reorder * update getting started * title * update navbar * Delete website/docs/tutorial/what-is-next.ipynb * update conversable patterns * Improve language * Fix typo * minor fixes --------- Co-authored-by: Jack Gerrits <jack@jackgerrits.com> Co-authored-by: gagb <gagb@users.noreply.github.com> Co-authored-by: Joshua Kim <joshua@spectdata.com> Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
1.8 KiB
1.8 KiB
What is Next?
Now that you have learned the basics of AutoGen, you can start to build your own agents. Here are some ideas to get you started without going to the advanced topics:
- Chat with LLMs: In Human in the Loop we covered the basic human-in-the-loop usage. You can try to hook up different LLMs using proxy servers like Ollama, and chat with them using the human-in-the-loop component of your human proxy agent.
- Prompt Engineering: In Code Executors we covered the simple two agent scenario using GPT-4 and Python code executor. To make this scenario work for different LLMs and programming languages, you probably need to tune the system message of the code writer agent. Same with other scenarios that we have covered in this tutorial, you can also try to tune system messages for different LLMs.
- Complex Tasks: In ConversationPatterns we covered the basic conversation patterns. You can try to find other tasks that can be decomposed into these patterns, and leverage the code executors to make the agents more powerful.
Dig Deeper
- Read the topic docs to learn more
- Read the examples and guides in the notebooks section
Get Help
If you have any questions, you can ask in our GitHub Discussions, or join our Discord Server.
Get Involved
- Contribute your work to our gallery
- Follow our contribution guide to make a pull request to AutoGen
- You can also share your work with the community on the Discord server.