Tag: genai
All the articles with the tag "genai".
- Vision-language modelsComputer visionGenAI
Vision-language models in practice: from building one to retrieval-augmented visual QA
A hands-on deep dive into vision-language models: building a LLaVA-style VLM from scratch, comparing local and cloud VLMs on document extraction and visual question answering, and finding that in visual RAG the retriever, not the generator, is usually the bottleneck.
- AgentsAgentic AIGenAI
One platform, many agents: designing a hybrid enterprise AI architecture
A high-level enterprise AI architecture for an engineering and construction company: one shared platform that combines agents, retrieval and traditional ML, proven on three very different use cases.
RAGDocument AIGenAIBeyond text RAG: document intelligence for tenders with hundreds of pages, tables and CAD drawings
Three RAG experiments on a real 450-page EPC tender showed that document coverage and query intelligence, not the LLM, limit tender analysis. Multimodal ingestion, query decomposition and role-based retrieval close the gap.
- AgentsAgentic AIGenAI
Before you build an agent: climbing the ladder from one LLM call to agents
Most tasks don't need an agent. A practical ladder from a single LLM call to workflows, routing, evaluator loops and agents, with two of my own projects on the first rungs.
- AzureLLMOpsDocument AI
Underwriter AI engine: reading medical records to triage health insurance proposals
How we built an OCR and LLM pipeline on Azure that reads proposal forms and messy medical documents, extracts pre-existing diseases, and sorts health insurance proposals into high, medium and low risk for medical underwriters.