Four hard-earned lessons from turning a promising GenAI claims demo into a production-ready solution—from defining meaningful measurements and managing technical debt to building effective engineering and domain-expert feedback loops.
Processing scanned claim PDFs used to be “good enough” if the text was mostly readable. In the GenAI era, that’s no longer true: if OCR misses a checkbox, scrambles a table, or loses layout context, the document becomes unreliable for extraction, retrieval, and automated decisions. Insurance makes this worse—many documents are old, low-quality scans with handwriting and dense forms—so we need evaluation that reflects real usability, not just character-perfect transcription.
DSPy is powerful, but many enterprise environments can’t call public LLM endpoints directly. This guide shows a minimal, practical way to plug an internal (non-standard) LLM service into DSPy by writing a custom dspy.BaseLM adapter.
In this post, I explore how modern web apps like RAGflow handle long-running tasks (such as OCR or keyword extraction) without relying on time-limited HTTP API methods. Instead, tasks are processed in the background by worker processes, with progress updates communicated to the frontend via Redis. I demonstrate this design with a simple app built using FastAPI, Vue 3, and Redis, where tasks are submitted, processed in the background, and their statuses are periodically updated on the frontend...
If you’ve found your way here, you’re probably already excited about the potential of the RAGFlow project and eager to see it in action. I was in the same position, so I delved into the codebase to see how it could work with custom large language models (LLMs). This post will walk you through my findings and show you how to get RAGFlow running with your own LLM.