Chunking user uploads - Githubissues

bahrain-bp / bqa-genai-challenge

This repository will include the BQA GenAI challenge artifacts

0 stars 0 forks source link

Chunking user uploads #149

Closed AmjadShubbar closed 4 months ago

AmjadShubbar commented 4 months ago

This task is to deal with large pdf uploads to successfully run sageMaker and Textract APIs.

AmjadShubbar commented 4 months ago

PDF File splitting, when the user uploads the required document, we chunk the document into smaller parts and have them uploaded again into the s3 bucket. This enables running textract and following its maximum Token without trouble, the flow starts after that.