Model allowlist and blocklists #446
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
for more information, see https://pre-commit.ci
krassowski
reviewed
Nov 8, 2023
|
@meeseeksdev please backport to 1.x |
meeseeksmachine
pushed a commit
to meeseeksmachine/jupyter-ai
that referenced
this pull request
Nov 8, 2023
JasonWeill
added a commit
that referenced
this pull request
Nov 8, 2023
Co-authored-by: david qiu <david@qiu.dev> Co-authored-by: Jason Weill <93281816+JasonWeill@users.noreply.github.com>
dbelgrod
pushed a commit
to dbelgrod/jupyter-ai
that referenced
this pull request
Jun 10, 2024
* implement model allow/blocklist in UI * skip extension tests due to local flakiness * implement model allow/blocklists in config manager * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
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Outdated suggestions cannot be applied.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.
Implements model-level allowlist and blocklist traits on the root
AiExtensionclass. These mostly behave as expected:Noneif they are forbidden by the provider/model allow/blocklists.The only unexpected outcome of this PR I'm aware of is that
allowed_modelsis ignored whenallowed_providersis set. This is because of the implementation of the provider allowlist established by #415, where it filters out blocked LM & EM providers before passing them to theConfigManager. This means that if I haveallowed_providers=["openai"]andallowed_models=["cohere:medium"], then"cohere:medium"will not be shown in the UI, nor will the ConfigManager allow setting the language model to"cohere:medium".While this isn't too hard to handle, I lack the time to fully test the interaction between these traits. I've added a note in the helper text to indicate that 1) this is currently undefined behavior and not intentional, and that 2) this is subject to change in a future non-major release.
Next steps
$JUPYTER_DATA_DIR.