feat: add i18n, multilingual ML, and OpenAI-like API support#134
Open
reg2005 wants to merge 5 commits into
Open
feat: add i18n, multilingual ML, and OpenAI-like API support#134reg2005 wants to merge 5 commits into
reg2005 wants to merge 5 commits into
Conversation
|
Important Review skippedToo many files! This PR contains 277 files, which is 127 over the limit of 150. To get a review, narrow the scope: ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (277)
You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
reg2005
changed the title
Owner
|
@reg2005 Thank you so much for your contribution. I'll review it next week and get back to you! |
Log model routing, OpenAI-like request/response metadata, and chat fallback details so empty browser responses can be traced safely. Also preserve dev container node_modules mounts and update exiftool-vendored past the high-severity advisory. Co-Authored-By: Claude <noreply@anthropic.com>
Add English and Russian i18n resources, language settings, and localized UI text across the app. Wire the selected app language through settings, background jobs, transcription, location lookup, search suggestions, and scene/vector text generation. Switch text embeddings and search normalization toward multilingual Russian/English workflows, including localized suggestions, Russian metadata-based scene descriptions, and canonical filter handling.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Add first-class English/Russian internationalization across the web app and wire the selected language through the backend/ML pipeline.
This introduces an i18n layer with EN/RU resource bundles, a language preference setting, localized UI copy across the main product surfaces, and shared language typing so app routes, jobs, settings, and services can consistently resolve the active locale.
The ML/search pipeline is updated for multilingual workflows as well. Text embeddings now use the multilingual
Xenova/paraphrase-multilingual-mpnet-base-v2model, Russian search queries are normalized into canonical metadata filters without losing the original semantic query, suggestions can display localized text while preserving canonical backend values, and scene/vector descriptions can be generated in Russian from detected metadata. Transcription and reverse-geocoding also receive the selected language so language-specific results are produced closer to the source.This also adds OpenAI-like API support for chat/model providers, including diagnostics that make provider configuration, routing, and compatibility issues easier to debug.
Reviewer notes: