initial prompt and translate function for l10n #6700
Merged
Conversation
This file contains hidden or 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
escattone
force-pushed
the
initial-l10n
branch
6 times, most recently
from
f66915e to
6a23d5f
Compare
escattone
force-pushed
the
initial-l10n
branch
6 times, most recently
from
8e06d96 to
3f6a86e
Compare
akatsoulas
approved these changes
Jun 11, 2025
kitsune/llm/l10n/wiki/translator.py
Outdated
| """ | ||
| llm = get_llm("gemini-2.5-pro-preview-05-06") | ||
|
|
||
| translation_chain = translation_prompt | llm | translation_parser |
There was a problem hiding this comment.
Not for this PR, but I am wondering if there's a way to extract this logic which is similar with the classifier to a method to make it more DRY. Maybe it's worth capturing an issue about it
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Outdated suggestions cannot be applied.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.
mozilla/sumo#2355
Notes
gemini-2.5-pro-preview-05-06model provides consistently excellent results given my "kitchen-sink" test case, whilegemini-2.5-flash-preview-04-17frequently makes mistakes, which makes sense given the increased logical complexity of the task relative to the spam and topic classification tasks.gemini-2.5-pro-preview-05-06model to the KB article'scontentonly, and use the cheaper/fastergemini-2.5-flash-preview-04-17model for the much simpler task of translating thekeywords,summary, andtitle. I haven't done that in this PR.