Christopher Speller

@johnsmzr Not seeing the same behavior when I try it. I don't see anything wrong with your configuration. I have merged a few PRs to add some more resiliance and...

There is a UI configuration for this in the latest versions. I think this can be closed? @lhchew please reopen if the timeout configuration is not enough to fix this.

#175 Is our implementation of the suggestions in this issue. It is included in the 0.8.0 release on the repo: https://github.com/mattermost/mattermost-plugin-ai/releases/tag/v0.8.0 @a3957273 and everyone else we would love to hear...

@kaakaa Hey! Thanks for the contribution. Couple of changes to the system console went though. Do you mind fixing the conflicts? Let me know if you need any help.

@kaakaa Thanks! I did noticed that issue while working on another pr and have a partial fix here: https://github.com/mattermost/mattermost-plugin-ai/pull/187/files#diff-efcd221be1d5948ef999c98624dc2d4a15dedc19b0945ca1b819a3d51480c607R142 But yes I need to fix the migration there.

This isn't really about cost it's about token counting for fitting text into the LLM context window. We also can't rely on something like LiteLLM being in the middle for...

This makes a lot of sense as it's a pretty bad experience when you run oft of context at the moment. The annoying part is (at least last time I...

1. Opened a ticket here: https://github.com/mattermost/mattermost-plugin-ai/issues/181 2. Makes sense. Updated. 3. Updated as we discussed. Will now remember your preferences across sections, but not update RHS immediately. 4. Not related,...

1. Only happens on Chrome apparently. Fixed by just making the text field slightly bigger. 2+3. We can make an improvement ticket for those. 4. Haha fixed. 5.  You...

@mickmister @streamer45 It actually would be really great if this part could be done by the calls infrastructure. We already have that setup for generating transcriptions with calls.