--- title: "#rag articles | Hashnode" description: "Explore 2,274 articles tagged #rag on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/rag" --- Tag # #rag 2,274 posts · 71 followers [BoilerShelf](https://hashnode.com/@boilershelf) · [17m ago](https://hashnode.com/posts/rag-evaluation-metrics-how-to-test-a-rag-chatbot-before-you-ship-it/6af7eb0139a0e29447ff2b1d) ### [RAG Evaluation Metrics: How to Test a RAG Chatbot Before You Ship It](https://boilershelf.hashnode.dev/rag-evaluation-metrics-how-to-test-a-rag-chatbot-before-you-ship-it?utm_source=hashnode&utm_medium=feed) How 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](https://boilershelf.hashnode.dev/rag-evaluation-metrics-how-to-test-a-rag-chatbot-before-you-ship-it?utm_source=hashnode&utm_medium=feed) [AI Studio](https://hashnode.com/@aistudio-video) · [10h ago](https://hashnode.com/posts/debug-rag-chunks-from-failures-backward/6af761208f465c67b94c421c) ### [Debug Your RAG Chunks From the Failures Backward](https://aistudio-video.hashnode.dev/debug-rag-chunks-from-failures-backward?utm_source=hashnode&utm_medium=feed) Collect 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](https://aistudio-video.hashnode.dev/debug-rag-chunks-from-failures-backward?utm_source=hashnode&utm_medium=feed) [Santosh](https://hashnode.com/@sant-sh) · [11h ago](https://hashnode.com/posts/rag-that-preserves-evidence/6af74c69755061d03670c56e) ### [RAG Explained: Retrieve the Right Evidence Before Generating an Answer](https://blog.sant.sh/rag-that-preserves-evidence?utm_source=hashnode&utm_medium=feed) Learn RAG ingestion, chunking, search, grounding, and separate retrieval evaluation through a reproducible lexical-search failure. 6 min read · [blog.sant.sh](https://blog.sant.sh/rag-that-preserves-evidence?utm_source=hashnode&utm_medium=feed) [Hu Jin](https://hashnode.com/@whoai) · [16h ago](https://hashnode.com/posts/chunking-strategies-for-rag-matching-split-rules-to-document-types/6af709367d376ea48770cb6f) ### [Chunking Strategies for RAG: Matching Split Rules to Document Types](https://whoai.hashnode.dev/chunking-strategies-for-rag-matching-split-rules-to-document-types?utm_source=hashnode&utm_medium=feed) How 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](https://whoai.hashnode.dev/chunking-strategies-for-rag-matching-split-rules-to-document-types?utm_source=hashnode&utm_medium=feed) [Muhammad Ahmad](https://hashnode.com/@mahmadmanzoor) · [16h ago](https://hashnode.com/posts/fixing-the-vercel-ai-sdk-bug-that-dropped-gemini-file-search-citations-in-streamtext/6af70509aa71f2c49b36ffe4) ### [Fixing the Vercel AI SDK Bug That Dropped Gemini File Search Citations in streamText](https://mahmadmanzoor.hashnode.dev/fixing-the-vercel-ai-sdk-bug-that-dropped-gemini-file-search-citations-in-streamtext?utm_source=hashnode&utm_medium=feed) Why 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](https://mahmadmanzoor.hashnode.dev/fixing-the-vercel-ai-sdk-bug-that-dropped-gemini-file-search-citations-in-streamtext?utm_source=hashnode&utm_medium=feed) [Buzzspot](https://hashnode.com/@buzzspot) · [19h ago](https://hashnode.com/posts/will-my-ai-chatbot-make-things-up-what-every-founder-should-ask-before-putting-one-on-their-website/6af6d96dbc9ff87336df2eef) ### [Will My AI Chatbot Make Things Up? What Every Founder Should Ask Before Putting One on Their Website](https://buzzspot-blog.hashnode.dev/will-my-ai-chatbot-make-things-up-what-every-founder-should-ask-before-putting-one-on-their-website?utm_source=hashnode&utm_medium=feed) Will 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](https://buzzspot-blog.hashnode.dev/will-my-ai-chatbot-make-things-up-what-every-founder-should-ask-before-putting-one-on-their-website?utm_source=hashnode&utm_medium=feed) [Vashni Roy](https://hashnode.com/@vashniroy) · [1d ago](https://hashnode.com/posts/embeddings-vs-llms-why-does-rag-need-both/6af5e77ce71b647cd77b2009) ### [Embeddings vs LLMs: Why Does RAG Need Both?](https://vashniroy.hashnode.dev/embeddings-vs-llms-why-does-rag-need-both?utm_source=hashnode&utm_medium=feed) 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](https://vashniroy.hashnode.dev/embeddings-vs-llms-why-does-rag-need-both?utm_source=hashnode&utm_medium=feed) [Vishnu Singh](https://hashnode.com/@vishnu8989) · [1d ago](https://hashnode.com/posts/graphrag-bridging-llms-and-knowledge-graphs-for-accurate-production-ready-ai/6af5ef7cc66793b7a971418d) ### [GraphRAG: Bridging LLMs and Knowledge Graphs for Accurate, Production-Ready AI](https://system-design-for-begeinners.hashnode.dev/graphrag-bridging-llms-and-knowledge-graphs-for-accurate-production-ready-ai?utm_source=hashnode&utm_medium=feed) How 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](https://system-design-for-begeinners.hashnode.dev/graphrag-bridging-llms-and-knowledge-graphs-for-accurate-production-ready-ai?utm_source=hashnode&utm_medium=feed) [Rounak Show](https://hashnode.com/@ShowRounak) · [1d ago](https://hashnode.com/posts/why-do-we-need-multimodal-embeddings/6af574626c71095c8801b398) ### [Advanced Embeddings from Scratch — Part 1: Why Do We Need Multimodal Embeddings?](https://rounakshow.hashnode.dev/why-do-we-need-multimodal-embeddings?utm_source=hashnode&utm_medium=feed) 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 entir 14 min read · [rounakshow.hashnode.dev](https://rounakshow.hashnode.dev/why-do-we-need-multimodal-embeddings?utm_source=hashnode&utm_medium=feed) [tarini sunil](https://hashnode.com/@tarinisunil) · [1d ago](https://hashnode.com/posts/building-docpilot-part-3-from-markdown-documents-to-searchable-chunks/6af601f67e155c8935ee15b6) ### [Building DocPilot — Part 3: From Markdown Documents to Searchable Chunks](https://ai-content-utilties.hashnode.dev/building-docpilot-part-3-from-markdown-documents-to-searchable-chunks?utm_source=hashnode&utm_medium=feed) Learn 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](https://ai-content-utilties.hashnode.dev/building-docpilot-part-3-from-markdown-documents-to-searchable-chunks?utm_source=hashnode&utm_medium=feed)