Monitoring in Power Pages and why telemetry is essential
Why modernizing a user interface without supporting telemetry data is an unpredictable risk, and how to add Azure Application Insights.
Power Pages in detail.
Architecture, React and enterprise practice on Microsoft Power Pages.
Technical deep dives, security boundaries and proven implementation patterns from real client projects.
Excel integration in Power Pages for bulk editing without overhead
Learn how to build Excel files programmatically with ExcelJS and process them directly in Power Pages through automated workflows.
Chunking, Qdrant and retrieval without duplicate RAG search results
I check the new path from worker to search so that a long capture is not only processed, but also appears cleanly as one result.
How I split the embedding workflow in Qdrant into clear steps
I rebuilt the worker so that one capture produces multiple token chunks, each chunk is embedded individually, and storage in Qdrant remains completely isolated.
Why I set the chunk size in my RAG system to 1500 tokens
The migration to bge-m3 brought an 8192-token limit. Nevertheless, I deliberately set the chunk limit to 1500 tokens to preserve semantic focus.
Why my chunking still failed despite tokenization
I had already implemented text splitting, but the context error kept appearing. Only when I accounted for the token budget and special tokens did the cause become clear.
What should your portal do?
Describe your workflow. Together, we will identify the right next step.
Discuss your workflow