John Alexander (MSFT)

icon indicating a website link https://aka.ms/ai-apps-docs

icon company Microsoft icon location My Microsoft related repo Content Lead, - Azure AI Foundry - Dev Exp - Azure AI App Dev - AI Tools Personal Repo: https://github.com/jralexander

Results 2 comments of John Alexander (MSFT)
trafficstars

Custom ingestion. Html tables generated too wordy and inefficient.

> Yeah, makes sense. This is the method that would need changing: > **> DocumentAnalysisParser.table_to_html() in pdfparser.py** > > You could put a table_to_csv() in there and try that instead....

Custom ingestion. Html tables generated too wordy and inefficient.

I'm playing around with https://github.com/DS4SD/docling. I'll let you know my results