Redo config and customization #22
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
When loading ~/.granite-code/config.yaml or ~/granite.code/assistants/*.yaml, add our models and the default context providers to the config.
Having the extra transformers.js embedding model around confuses selection; since there is supposed to be a local Ollama for our operation, using that for embeddings will probably provide better performance in any case.
Rather than take the user to config.yaml, pop up the "Add Models" form that you would normally get from the bottom of the model model menu (we're removing the option from that menu, and will hide the menu entirely unless there is more than one chat model available)
…owns Model selection: - Don't show unless more than one model - Remove the "Add chat model" option - you can get to that from the model section of the lump toolbar. Assistant selection: - Don't show unless than more than one model - Remove the "New Assistant" option, which takes you to hub.continue.dev; local assistants can be created by manually adding files within ~/.granite-code/assistants/.
Since we no longer have code to merge our config into config.json, just ignore config.json files - trying to support the legacy config file format for Continue doesn't make sense.
owtaylor
force-pushed
the
owtaylor/redo-customization
branch
from
8698c05 to
70a9464
Compare
|
Update: I don't understand what I did wrong but I was obviously not running the proper branch. It looks fine actually |
|
We should prolly hide the rerank selector: 
|
|
ok so after I finally got the proper build working, we can ignore my last comment. As discussed with @owtaylor, there are a couple issues to address, but I think it's fine to merge this PR first and address them in a follow up, as it would make the base branch usable again. things to address next:
|
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
A grab-bag of changes to get us back to a similar state after merging the new UI
frequencyPenalty: 0.1which is no longer supported in config.yaml - where that came from is unclear, and there's no standard recommendation to use it with Granite.This roughly corresponds to a discussion I had with @allanday about how we should adjust to the new UI