BBoilerShelf·7m agoRAG Evaluation Metrics: How to Test a RAG Chatbot Before You Ship ItHow to evaluate a retrieval-augmented chatbot: separate retrieval from generation, build a real test set, choose checks you can repeat, and report results honestly.6 min read·boilershelf.hashnode.dev
AAI Studio·9h agoDebug Your RAG Chunks From the Failures BackwardCollect the questions your RAG bot gets wrong, read the chunks it retrieved, and match each failure to a chunking fix.8 min read·aistudio-video.hashnode.dev
SSantosh·11h agoRAG Explained: Retrieve the Right Evidence Before Generating an AnswerLearn RAG ingestion, chunking, search, grounding, and separate retrieval evaluation through a reproducible lexical-search failure.6 min read·blog.sant.sh2
HHu Jin·16h agoChunking Strategies for RAG: Matching Split Rules to Document TypesHow to chunk Markdown, PDFs, code, tickets, and tables so retrieval keeps meaning—size, overlap, structure, and metadata that actually help.4 min read·whoai.hashnode.dev
MMuhammad Ahmad·16h agoFixing the Vercel AI SDK Bug That Dropped Gemini File Search Citations in streamTextWhy streamText in @ai-sdk/google dropped Gemini File Search and RAG citations, how the merged fix dedupes sources by identity, and how to upgrade.12 min read·mahmadmanzoor.hashnode.dev
BBuzzspot·19h agoWill My AI Chatbot Make Things Up? What Every Founder Should Ask Before Putting One on Their WebsiteWill an AI chatbot make things up on your site? Plain-English answers on hallucinations, RAG, RAGAS and testing, with real 2023 to 2026 numbers.24 min read·buzzspot-blog.hashnode.dev
VVashni Roy·1d agoEmbeddings vs LLMs: Why Does RAG Need Both?I separated retrieval and generation in a small RAG experiment to see what embeddings and LLMs actually do, and why both matter.3 min read·vashniroy.hashnode.dev
VVishnu Singh·1d agoGraphRAG: Bridging LLMs and Knowledge Graphs for Accurate, Production-Ready AIHow to overcome the limits of naive vector search using Parent Document Retrievers, Text2Cypher, and Agentic RAG.9 min read·system-design-for-begeinners.hashnode.dev
RRounak Show·1d agoAdvanced Embeddings from Scratch — Part 1: Why Do We Need Multimodal Embeddings?In our original Understanding LLM Embeddings from Scratch series, we learned how text becomes vectors, how those vectors learn semantic relationships, and how sentence embedding models represent entir14 min read·rounakshow.hashnode.dev1
Ttarini sunil·1d agoBuilding DocPilot — Part 3: From Markdown Documents to Searchable ChunksLearn how I built DocPilot's Markdown-aware chunking pipeline with Python, code-block handling, metadata, and pytest tests.16 min read·ai-content-utilties.hashnode.dev
