FIX: Split content for translation before sending #249
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
nattsw
force-pushed
the
split-raw-before-translate
branch
from
7580b96 to
32fae6d
Compare
tgxworld
reviewed
Mar 11, 2025
| text = text_for_translation(translatable) | ||
| chunks = DiscourseTranslator::ContentSplitter.split(text) | ||
| chunks | ||
| .map { |chunk| ::DiscourseAi::Translator.new(chunk, target_locale_sym).translate } |
Contributor
There was a problem hiding this comment.
Not sure if you considered it but I'm wondering if we should translate chunks in parallel.
Contributor
Author
There was a problem hiding this comment.
I did ... 🤔 but we may hit rate limits
Contributor
Author
|
I'll add some limits to the splitter. |
xfalcox
force-pushed
the
split-raw-before-translate
branch
from
bb3d1f3 to
d9a0322
Compare
xfalcox
approved these changes
Mar 25, 2025
nattsw
added a commit
to discourse/discourse-ai
that referenced
this pull request
Jun 23, 2025
In discourse/discourse-translator#249 we introduced splitting content (post.raw) prior to sending to translation as we were using a sync api. Now that we're streaming thanks to #1424, we'll chunk based on the LlmModel.max_output_tokens.
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Outdated suggestions cannot be applied.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.
Requires: #248
We are seeing a lot of
Timeouts may happen when we send large chunks over to our LLM for translation. Timeouts may also happen in two ways:
This PR solves (2). (1) will be handled in a different PR. We will loosely split content up into chunks. Example post raw is meta's /t/354449.