perf: preprocess email body before LLM calls to reduce token burn#48
Merged
Conversation
Adds a preprocess_body() function in email_service.py that strips inline data URIs, collapses excessive blank lines, cuts at footer/ unsubscribe markers, and hard-truncates to 3000 characters. All three extraction modules (classifier, flight_extractor, accommodation_extractor) now call preprocess_body() instead of inline slicing, reducing per-email token cost by 60–80% and making it safe to raise INGEST_LIMIT. Closes #39 Co-Authored-By: Claude Sonnet 4.6 <[email protected]> Claude-Session: https://claude.ai/code/session_01R3RsJoMdczuX4mbMuMh78U
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a preprocess_body() function in email_service.py that strips
inline data URIs, collapses excessive blank lines, cuts at footer/
unsubscribe markers, and hard-truncates to 3000 characters. All three
extraction modules (classifier, flight_extractor, accommodation_extractor)
now call preprocess_body() instead of inline slicing, reducing per-email
token cost by 60–80% and making it safe to raise INGEST_LIMIT.
Closes #39