azure-search-openai-demo-csharp
azure-search-openai-demo-csharp copied to clipboard
PDF upload will not generate or index sections if the number of characters on the page is less than 1000
I noticed this whilst testing, but EmbedPDFBlobAsync will not generate sections for pages in the page map that have under 1000 characters.
This is a logic flaw in the CreateSections method that's missing a conditional statement before the while loop and never yields a value (section).