workaround of #187 (just return instead of raise)

[nishio]

see #187

Summary by CodeRabbit

• Bug Fixes
  • Improved error handling in the translation pipeline to prevent crashes and ensure smoother batch processing.

[coderabbitai]

Walkthrough

The translate_batch function in scatter/pipeline/steps/translation.py was modified to handle errors differently. Instead of raising an exception when an error occurs, the function now returns the batch. This change aims to improve error handling and ensure the function's execution continues smoothly.

Changes

Files	Change Summary
scatter/pipeline/steps/translation.py	Replaced raise e with return batch in translate_batch function

Poem

In the world of code so bright,
A change was made to ease the plight.
No more errors shall arise,
Just returning batches, wise.
Translation flows with grace anew,
For smoother paths, we bid adieu. 🌟

---

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

Share

• X
• Mastodon
• Reddit
• LinkedIn

Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai generate interesting stats about this repository and render them as a table.
  • @coderabbitai show all the console.log statements in this repository.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (invoked as PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Additionally, you can add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.

CodeRabbit Configration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[coderabbitai]

Actionable comments posted: 0

Outside diff range and nitpick comments (2)

scatter/pipeline/steps/translation.py (2)

Line range hint 7-7: Remove unused import.

- from langchain.schema import AIMessage

This import is unused and should be removed to clean up the code.

---

Line range hint 4-4: Remove duplicate imports.

- import pandas as pd
- import json
- from tqdm import tqdm

These imports are redefined later in the file. Removing these lines will prevent confusion and potential issues with multiple imports.

Also applies to: 8-10

Review details

Configuration used: CodeRabbit UI
Review profile: CHILL

Commits

Files that changed from the base of the PR and between 661a209 and c1f39a4.

Files selected for processing (1)

• scatter/pipeline/steps/translation.py (1 hunks)

Additional context used

Ruff

scatter/pipeline/steps/translation.py

7-7: langchain.schema.AIMessage imported but unused

---

8-8: Redefinition of unused pd from line 4

---

9-9: Redefinition of unused json from line 2

---

10-10: Redefinition of unused tqdm from line 3

Additional comments not posted (1)

scatter/pipeline/steps/translation.py (1)

129-129: Change in error handling from raising an exception to returning the batch.

This change aligns with the PR's objective to provide a workaround for issue #187. Ensure that downstream code can handle the returned batch correctly, especially in scenarios where an exception would have previously been raised.

[brittneygallagher]

Thanks for the PR @nishio!

Agreed that this is a better resolution for now than raising the error again since the error isn't caught further up.

Would you mind adding a print statement there that outputs Retries exhausted. Returning last batch... before returning?

After that we can merge.