RKRehbar Khaninarshhimself.hashnode.dev·Jul 19 · 4 min readHow I Built a RAG Chatbot Into My Portfolio with LangGraph, PGVector & MCP" published: false description: "A deep dive into the Gen-AI assistant on my portfolio — LangGraph agent, RAG over Postgres/pgvector, Redis memory, and live GitHub data via MCP.Most portfolios have a boring "About Me" paragraph. I replaced mine with something you can talk to — an AI terminal that answers questions about me, pulls my live GitHub activity, and remembers the co00
NANavneet Adarshinnavneetadarsh.hashnode.dev·Jul 16 · 5 min readWhy Do We need RAGLimitations of Using an LLM without External Knowledge Cannot access real time data after training and for that it needs to be train on data and it takes too much costs if you train your LLM two time10
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, page14M
SSSuraj S G Dhanvainsurajsg23.hashnode.dev·Jul 15 · 13 min readRAG Was Great. So Why Did I Fine-Tune My Model?1. How It All Began During our final year of engineering, I built jAIcianVerse, an AI-powered learning platform that I hoped would make studying a little less frustrating. The idea came from something21K
PMPrajwal Minglitch-guy0.hashnode.dev·Jul 15 · 6 min readUnderstanding RAG: A Simple Guide for BeginnersIntroduction: The Problem with LLMs Large Language Models (LLMs) excel at generating text, answering questions, and even writing code. However, they have a critical limitation: they only know what the00
RPRutwik Patilinaws-waf-webapp.hashnode.dev·Jul 15 · 4 min readBeyond Search: Building Knowledge Nexus — The Future of AI-Powered Enterprise IntelligenceHow we built an enterprise-grade RAG platform that turns static PDFs into an interactive Knowledge Graph. In the modern enterprise, information isn’t just power — it’s a massive logistical challenge. 00
Mmatthewtruong81inmatthew-codes.hashnode.dev·Jul 8 · 6 min readRAG or Fine-Tuning? An AI Development Services ComparisonQuick answer: RAG (Retrieval-Augmented Generation) enables the language model to retrieve the most up-to-date information directly from the live knowledge base at query time without retraining. Fine-t00
SDSynfinity Dynamics Pvt Ltdinsynfinitydynamics.hashnode.dev·Jul 6 · 7 min read14 types of RAG (Retrieval-Augmented Generation) Retrieval-Augmented Generation started as a single, simple idea: retrieve relevant documents, stuff them into a prompt, let the LLM answer. That's it. That's "RAG." But as teams pushed RAG into produc10
EBElisé Baraka M.inebmurha.hashnode.dev·Apr 14 · 8 min readBuilding a RAG Engine — Part 2: An Interface to Evaluate ItPart 1 ended with a pipeline operated fully from the command line. I could ingest documents, run a query, and get an answer wired to evidence. What I didn't have was the UI. I needed an interface to t00
CSCheon Sejunineliosdevlog.hashnode.dev·Apr 11 · 3 min readBuilding a High-Precision Travel Guide: Optimizing RAG for a Jeju Island AI ChatbotIntroduction: The Limits of Vanilla LLMs When building a tourism assistant for a specific location like Jeju Island, generic LLMs often fall short. They might hallucinate trail names, provide outdated00
