Best approach for reading unstructured data (PDFs, screenshots) in Qlik Cloud SaaS

[Ksenia1]

Hi everyone,

We are currently working in Qlik Cloud SaaS and are exploring the best options for reading and processing unstructured data, such as:

• PDF documents
• Screenshots or image files
• Other non‑tabular document formats

Our objective is to extract usable data (text or structured fields) from these sources so it can be consumed in Qlik applications.

We we would really appreciate guidance on:

• Native capabilities within Qlik Cloud (if any)
• Recommended OCR or document‑processing tools that integrate well with Qlik Cloud
• Typical architectures (e.g. pre-processing outside Qlik, APIs, third‑party services)
• Any best practices or lessons learned from similar use cases

If you have implemented something similar, we’d be very interested to hear what worked well for you.

Thanks in advance for your help.

[Greg_Taffer]

The best approach for reading unstructured data (PDFs, screenshots) in Qlik Cloud is using Qlik Answers, a GenAI-powered solution that ingests, indexes, and queries unstructured documents (PDFs, text) using RAG. For document-specific extraction, the new AI Parse Document feature in LakeFlow leverages multimodal models to convert screenshots/tables into structured data.