Open
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #173
📝 Description
This PR resolves the issue where the PDF filler was "hallucinating" repeating values (e.g., repeating the name in every field).
🛠️ Key Changes
main.py: Restored the use ofdescriptive_fieldswhen calling the controller. By passing human-readable labels instead of generic PDF widget IDs (liketextbox_0_0), the LLM now has the necessary semantic context to extract accurate, distinct values from the transcript.llm.py(Loop Fix): Removed the.keys()call inmain_loop(). Since the target fields are passed as alist, calling.keys()was causing a runtime crash.🧪 Quality Check
📸 Evidence
Before Fix (Hallucination):
{ "textbox_0_0": "John Doe", "textbox_0_1": "John Doe", "textbox_0_2": "managing director" }