AÖAhmet Özelinahmetozel.hashnode.dev·3d ago · 15 min readEvaluating RAG: From Golden Datasets to LLM-as-JudgeA Retrieval-Augmented Generation system can produce a fluent answer while failing in several independent ways. It may retrieve the wrong evidence, omit a required document, misread correct context, an00
AÖAhmet Özelinahmetozel.hashnode.dev·Aug 5 · 30 min readBeyond Vector Search: Knowledge Graphs, Structured Retrieval, and Intelligent RoutingVector search is an effective way to retrieve passages that are semantically similar to a question. It is not a universal interface to every kind of knowledge. Exact identifiers, deterministic calcula10
AÖAhmet Özelinahmetozel.hashnode.dev·Jul 21 · 34 min readThe Anatomy of Production-Grade RetrievalRetrieval-Augmented Generation is often summarized as a three-step workflow: split documents, embed the chunks, and send the nearest results to a language model. That description is useful for a proto10
AÖAhmet Özelinahmetozel.hashnode.dev·Jul 16 · 40 min readBuilding a Local-First OCR + LLM Pipeline for Structured Business DocumentsTurning a scanned business document into reliable structured data is not a single-model problem. Optical character recognition is only one stage in a longer system that must handle image quality, page13M
AÖAhmet Özelinahmetozel.hashnode.dev·Jun 8 · 2 min readOne MCP server for Jira, Confluence and Bitbucket: 61 tools under one configIf you want an AI agent to work with Atlassian, you quickly hit a practical annoyance: Jira, Confluence and Bitbucket are three products, and the usual answer is three separate MCP servers with three 00
