Extract all PDF content in one field

[Pawan Somwanshi]

Hi, I have use case Where I have to compare 2 pdf attachments for matching content and return matching score. I have implemented AI agent with prompt. It identifying 2 attachment and getting base64 data to compare by decoding it. its working for small base64 data like if I attach text files. but when it came for pdf files which have larg amount of data it get failed. AI agent need input to compare so giving attachment sys_id's to instruct ti get data and compare didn't worked. hence I have to Extract data in text format and pass as input using tools (Subflow, Flow action Or script). but Servicenow didnt support PDF extract in single field. I tried using Document intelligence to extract data but it only allow to get key data and map with target fields to extract using document task. Could you please help me to Extract full pdf data in single field?  

[Ankur Bawiskar]

@Pawan Somwanshi 

may be a limitation to handle large file.

💡 If my response helped, please mark it as correct ✅ and close the thread 🔒— this helps future readers find the solution faster! 🙏

[Pawan Somwanshi]

I sort it out to extract pdf in single field. but have limitations small pdf can be extracted don't know length but tried with 3 page with successful but with 10 page it failed, Also some images contains may extract but not all. and all in text format. This might required external integration with high extract capability.