Couple of minor fixes and tweaks to the table merger. #963
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
1. I observed the LLM sometimes having issues distinguishing where one table ended and the next started, so I added headers - either ELEMENT 1/ELEMENT 2 or DOCUMENT 1/DOCUMENT 2 in the llm_query transform. 2. Added a default implementation for preprocess_element and postprocess_element in the ElementMerger base class. This just reduces code in some simple sub-classes. 3. Added code to update the table_continuation to be True or False. This is because I ended up getting better results when asking the LLM to explain its reasoning in some cases, but I didn't want all of the output carried along in the element. 4. Minor fix to address an invalid escape character warning in a comment.
dhruvkaliraman7
approved these changes
Oct 21, 2024
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Outdated suggestions cannot be applied.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.
I observed the LLM sometimes having issues distinguishing where one table ended and the next started, so I added headers - either ELEMENT 1/ELEMENT 2 or DOCUMENT 1/DOCUMENT 2 in the llm_query transform.
Added a default implementation for preprocess_element and postprocess_element in the ElementMerger base class. This just reduces code in some simple sub-classes.
Added code to update the table_continuation to be True or False. This is because I ended up getting better results when asking the LLM to explain its reasoning in some cases, but I didn't want all of the output carried along in the element.
Minor fix to address an invalid escape character warning in a comment.