Skip to content
This repository was archived by the owner on Jun 24, 2025. It is now read-only.

LLM integration, part 4#2181

Merged
eliandoran merged 19 commits intodevelopfrom
feat/llm-change-to-single-provider
Jun 7, 2025
Merged

LLM integration, part 4#2181
eliandoran merged 19 commits intodevelopfrom
feat/llm-change-to-single-provider

Conversation

@perfectra1n
Copy link
Copy Markdown
Member

@perfectra1n perfectra1n commented Jun 5, 2025 •
edited
Loading

  • Resolve duplicated text when responses are streamed
  • Resolve headers being modified when response has already been sent
  • Have API keys be optional for OpenAI (but still show that they aren't set in the "warnings" container in the UI)
  • Remove functions that were deprecated, consolidate logic
  • Use getOrCreate design patterns instead of the mess of initialization() patterns and race conditions
  • Put listeners on Settings updates - so that LLM providers are created/destroyed when settings are changed
  • Add endpoints for starting/stopping embeddings

perfectra1n added 11 commits June 4, 2025 20:13
@perfectra1n
feat(llm): change from using precedence list to using a sing specifie…
a20e36f 
…d provider for either chat and/or embeddings
@perfectra1n
fix(llm): have the model_selection_stage use the instance of the aiSe…
fe15a03 
…rviceManager
@perfectra1n
feat(llm): automatically fetch models when provider settings change
3dee462
@perfectra1n
feat(llm): also add embeddings options for embedding creation
63722a2
@perfectra1n
feat(llm): also have the embedding provider settings be changeable
5bc2c3a
@perfectra1n
fix(llm): fix the buggy embedding selection dropdown
5db514e
@perfectra1n
Merge branch 'develop' into feat/llm-change-to-single-provider
a084805
@perfectra1n
feat(llm): create endpoints for starting/stopping embeddings
49e123f
@perfectra1n
feat(llm): also add functions to clear/unregister embedding providers
c1b10d7
@perfectra1n
feat(llm): transition from initializing LLM providers, to creating th…
bb8a374 
…em on demand
@perfectra1n
feat(llm): embeddings work and are created when launching for the fir…
3a4bb47 
…st ever time
@perfectra1n perfectra1n added the llm label Jun 5, 2025
@github-actions
Copy link
Copy Markdown

github-actions bot commented Jun 5, 2025 •
edited
Loading

Folder/File Previous size New size Difference
/upload/TriliumNextNotes-Server-2181-merge-linux-x64.tar.xz 67.76MB +67.76MB (+100.00%)
TOTAL +67.76MB

@perfectra1n perfectra1n changed the title Feat/llm change to single provider LLM integration, part 4 Jun 7, 2025
@perfectra1n perfectra1n marked this pull request as ready for review June 7, 2025 00:36
@dosubot dosubot bot added the size:XXL This PR changes 1000+ lines, ignoring generated files. label Jun 7, 2025
@eliandoran eliandoran added this to the v0.94.1 milestone Jun 7, 2025
@eliandoran eliandoran merged commit 9ead5ab into develop Jun 7, 2025
11 checks passed
@eliandoran eliandoran deleted the feat/llm-change-to-single-provider branch June 7, 2025 08:38
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Reviewers

1 more reviewer

@eliandoran eliandoran eliandoran approved these changes

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

llm size:XXL This PR changes 1000+ lines, ignoring generated files.

Projects

None yet

Milestone

v0.94.1

Development

Successfully merging this pull request may close these issues.

2 participants

@perfectra1n @eliandoran