<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>BitBanter: learn AI engineering</title><description>Learn AI engineering with tested, simple explanations. Free courses, notes and code in Python and JavaScript, from the BitBanter videos.</description><link>https://www.bitbanter.in/</link><language>en</language><item><title>Agentic RAG vs Traditional RAG: What Changes, What It Costs</title><link>https://www.bitbanter.in/blog/agentic-rag-vs-rag/</link><guid isPermaLink="true">https://www.bitbanter.in/blog/agentic-rag-vs-rag/</guid><description>Traditional RAG searches once. Agentic RAG lets the model search as often as it needs. A real retrieval test, a 40-line agent loop, and when each one wins.</description><pubDate>Fri, 20 Nov 2026 00:00:00 GMT</pubDate><category>rag</category><category>agentic-rag</category><category>agents</category><category>architecture</category></item><item><title>RAG Pipeline: Architecture, Steps and Real Numbers</title><link>https://www.bitbanter.in/blog/rag-pipeline/</link><guid isPermaLink="true">https://www.bitbanter.in/blog/rag-pipeline/</guid><description>The 9 steps of a RAG pipeline, from loading docs to the final answer, with a framework-free build, measured costs, and the bug each step can cause.</description><pubDate>Fri, 20 Nov 2026 00:00:00 GMT</pubDate><category>rag</category><category>rag-pipeline</category><category>architecture</category><category>embeddings</category><category>chunking</category></item><item><title>RAG from Zero, episode 2: Embeddings: how AI knows “refund” = “paisa wapas”</title><link>https://www.bitbanter.in/resources/rag/ep2-embeddings/</link><guid isPermaLink="true">https://www.bitbanter.in/resources/rag/ep2-embeddings/</guid><description>Text becomes numbers that capture meaning. We build the idea from a 2-number toy map to 3,072 dimensions, then test it on DocBot&apos;s real data, where one model puts a Hinglish question in the wrong place.</description><pubDate>Thu, 19 Nov 2026 00:00:00 GMT</pubDate><category>embeddings</category><category>cosine similarity</category><category>matryoshka</category><category>multilingual</category></item><item><title>RAG from Zero, episode 1: What is RAG? Why AI never read your docs</title><link>https://www.bitbanter.in/resources/rag/ep1-what-is-rag/</link><guid isPermaLink="true">https://www.bitbanter.in/resources/rag/ep1-what-is-rag/</guid><description>Your company&apos;s docs were never in the model&apos;s training data. RAG fixes that without training anything: search first, then ask. We open the exact message our demo bot sends and run the same question with and without RAG.</description><pubDate>Sun, 15 Nov 2026 00:00:00 GMT</pubDate><category>rag</category><category>retrieval</category><category>fine-tuning</category><category>prompt</category></item></channel></rss>