Notice of removal of LLM feature #8797
Replies: 2 comments 3 replies
-
|
I understand the reason of this. Have you guys ever considered implementing two way markdown sync instead of direct ai implementation? AI already works great with markdown files. If there was a option for syncing trillium db with markdown files, ai cli tools could easily work on them. So if something were to change in trillium it would also update the markdown export in realtime. And if a file were to be added or changed externally then it could auto import it from markdown. Since export/import options already exist only thing that needs to be added and maintained is sync logic. |
Beta Was this translation helpful? Give feedback.
-
|
cli-anything -make agent native cli for existing app like gimp, OBS studio, etc ... I put some info here: https://github.com/orgs/TriliumNext/discussions/9087 |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Hello everyone,
Some time ago we've introduced beta support for LLM. Unfortunately, due to time constraints and due to the complexity of the task, there simply weren't enough development resources for us to keep working on it so we took the decision of reverting the work out of the Trilium core.
At some point in time, maybe this LLM integration will be maintained as an external script (especially if we implement a plugin repository), but we're not there yet.
We've modified the LLM documentation accordingly, including some alternative options regarding MCP servers: https://docs.triliumnotes.org/user-guide/llm
Starting v0.102.0 (upcoming major version), the LLM integration will be removed.
Thanks to @perfectra1n for his titanic efforts on bringing LLMs to Trilium!
Beta Was this translation helpful? Give feedback.
All reactions