Python: Fix HTML-like tags being dropped in ChatHistory.from_rendered_prompt#13659
Open
jgarrison929 wants to merge 1 commit intomicrosoft:mainfrom
Open
Python: Fix HTML-like tags being dropped in ChatHistory.from_rendered_prompt#13659jgarrison929 wants to merge 1 commit intomicrosoft:mainfrom
jgarrison929 wants to merge 1 commit intomicrosoft:mainfrom
Conversation
…_prompt When a prompt contained valid XML elements like <p>, <div>, etc., the XML parser in from_rendered_prompt treated them as elements but silently discarded their content because they weren't recognized as chat message tags (message, history). This fix serializes unrecognized elements back to their XML string representation using tostring(), preserving both the tags and their content in the final prompt text. Added regression tests for: - Single HTML-like tag (<p>) - Nested HTML-like tags (<div><p>...</p></div>) Fixes microsoft#13632
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation and Context
Fixes #13632
When a prompt contains valid XML elements like
<p>,<div>,<b>, etc., the XML parser inChatHistory.from_rendered_prompttreats them as elements but silently discards their content.Description
This PR fixes the issue by serializing unrecognized XML elements back to their string representation using
tostring().After the fix:
Contribution Checklist