I see, so trying to zero in here there are … with a bit more technical details.
- @mentioning
@gpt3.5-bot
would select the first prioritized persona… that would usually be forum helper but you could change it. - We would also supply context (lets say 1000 tokens of previous chat messages) so it would be lined up. (is this configurable or not? configurable by persona or not?)
- We clearly need to restrict the group of people who can
@mention
in chat, so we would need a site setting for it. - We would need to think about auditability, an easy minimum here would be to ship a data explorer query.
- Given recent chat refactors, we can open “unlimited” new discussions with a bot, so we could design something there for sure.
- If we allow @mentioning in chat… why not also allow it in forum posts to the same group? different group.
Given all of this… my V0 suggestion would be:
- Add site setting
ai_bot_chat_enabled_groups
- Hard code 1000 tokens of context for now - choose first prioritized persona
- Only do
@mention
support for V0
V1
- Streaming and cancel support
V2
- Add optional support for “Group DMs with ai bots”
- Ensure we also have a nice UI to find all this stuff and minimize overhead of doing this.
V3
-
Optionally allow personas to also stage a dedicated user with a dedicated avatar. Then you can interact with multiple bots in chat. In this mode persona would have a user/model selected as well.
-
Also move some configuration to persona UI … which persona is enabled for chat?
V4
- Think about limits - maximum token usage per day per user, stuff like that
V5
- Think about also adding some of this into standard topics - (needs site setting, etc…) eg:
@summary_bot summarize this topic up till now
Overall I like a lot of this, just need to figure out how we line this stuff into our roadmap.