Highlights
A preliminary TeachableAgent is added to allow users to teach their assistant facts, preferences, and tasks unrelated to code generation. Example notebook: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_teachability.ipynb
Conversational assistants based on LLMs can remember the current chat with the user, and can even demonstrate in-context learning of things that the user teaches the assistant during the chat. But these memories and learnings are lost once the chat is over, or when a single chat grows too long. In subsequent chats, the user is forced to repeat any necessary instructions over and over.
TeachableAgent addresses these limitations by persisting user teachings across chat boundaries in long-term memory (a vector database). Memory is saved to disk at the end of each chat, then loaded from disk at the start of the next. Instead of copying all of memory into the context window, which would eat up valuable space, individual memories (called memos) are retrieved into context as needed. This allows the user to teach frequently used facts, preferences and skills to the agent just once, and have the agent remember them in later chats.
This release also contains an update about openai models and pricing, and restricts the openai package dependency version. In v0.2 we will switch to openai>=1.
Thanks to @rickyloynd-microsoft @kevin666aa and all the other contributors!
What's Changed
- doc: Update FAQ.md by @haseeb-xd in #282
- Fix format and links in documentations by @thinkall in #310
- update openai models and pricing by @kevin666aa in #316
- guidance for contribution by @sonichi in #320
- TeachableAgent by @rickyloynd-microsoft in #278
- add downloads stats in readme by @sonichi in #334
- bump version to 0.1.13 by @sonichi in #333
New Contributors
- @haseeb-xd made their first contribution in #282
- @rickyloynd-microsoft made their first contribution in #278
Full Changelog: v0.1.12...v0.1.13