Agentic RAG takes Retrieval-Augmented Generation one step further. In traditional RAG, retrieval is a fixed step — fetching context from a knowledge base before generating a response. In Agentic RAG, however, the data source itself becomes a tool in the agent’s toolkit. The agent autonomously decides when and how to query it based on the conversation history, user intent, and reasoning chain, alongside other tools like summarizers or planners. This transforms RAG from a static retrieval process into a dynamic, decision-driven system. ...
Classic map-reduce-filter pattern process data step-by-step. For example, a map-filter-collect on an array of numbers would first transform each number, then filter out the one’s that meet a condition, and finally collect the results. However, in real-time applications, we often need data to be processed as it becomes available. Imagine an LLM agent that summarizes paragraphs from search one by one. Instead of waiting for all sections to finish, it can start streaming summaries to the frontend immediately, giving users faster, progressive feedback. ...
When I was 23, I developed an inguinal hernia on the left side of my groin while doing overhead presses in the gym. At first, it was very painful and hard to get the bulge in. A little research revealed it was a hernia — and everything online said hernia = surgery. I also read that after surgery, one should avoid lifting weights. That was discouraging, so I stopped training altogether. ...
Custom GPT Actions let us expose an API that ChatGPT calls on behalf of users. We build the backend — ChatGPT handles the frontend: web, mobile, voice, message history, auth. But a production-grade RAG backend needs more than basic vector search. This article covers building a high-performance Custom GPT in Go, along with the interesting parts: hybrid search with Reciprocal Rank Fusion, chunk stitching for contiguous context, query-focused summarization with SLMs, and decoupled embedding strategies for A/B testing. ...