<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Technical Posts on Hitesh Pattanayak</title><link>/posts/</link><description>Recent content in Technical Posts on Hitesh Pattanayak</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 29 Mar 2026 21:14:59 -0700</lastBuildDate><atom:link href="/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>Retrieval Pipelines, Re-Ranking, and Grounding: Building Production RAG</title><link>/posts/retrieval-pipelines-re-ranking-and-grounding-building-production-rag/</link><pubDate>Sun, 29 Mar 2026 21:14:59 -0700</pubDate><guid>/posts/retrieval-pipelines-re-ranking-and-grounding-building-production-rag/</guid><description>A practical guide for software engineers on building production-grade RAG systems using hybrid retrieval, re-ranking, and grounding techniques to reduce hallucinations and improve answer quality.</description></item><item><title>Vector Embeddings &amp; Similarity: The Foundation of RAG</title><link>/posts/vector-embeddings-similarity-the-foundation-of-rag/</link><pubDate>Sun, 29 Mar 2026 21:14:51 -0700</pubDate><guid>/posts/vector-embeddings-similarity-the-foundation-of-rag/</guid><description>A practical deep-dive into vector embeddings and cosine similarity — the mathematical foundation that makes retrieval in RAG systems actually work.</description></item><item><title>Vector Databases, ANN, and Chunking: Storing Knowledge for Retrieval</title><link>/posts/vector-databases-ann-and-chunking-storing-knowledge-for-retrieval/</link><pubDate>Sun, 29 Mar 2026 21:11:47 -0700</pubDate><guid>/posts/vector-databases-ann-and-chunking-storing-knowledge-for-retrieval/</guid><description>A practical guide for software engineers covering how vector databases use Approximate Nearest Neighbor algorithms to search millions of embeddings efficiently, and how to chunk documents intelligently so your RAG pipeline actually retrieves useful, precise context.</description></item><item><title>Page-Aware AI Chat: Floating Widget and Per-Page Context</title><link>/posts/page-aware-ai-chat-floating-widget-and-per-page-context/</link><pubDate>Fri, 27 Mar 2026 14:48:36 -0700</pubDate><guid>/posts/page-aware-ai-chat-floating-widget-and-per-page-context/</guid><description>A practical walkthrough of adding per-page context awareness to a floating AI chat widget built with Hugo and Netlify Functions, covering layout overrides, slug injection, priority chunk labeling, and the prompt engineering fix that made summarise-this-post actually work.</description></item><item><title>Building an AI Chat Assistant for a Static Blog — No Vector DB Required</title><link>/posts/building-an-ai-chat-assistant-for-a-static-blog-no-vector-db-required/</link><pubDate>Fri, 27 Mar 2026 12:54:33 -0700</pubDate><guid>/posts/building-an-ai-chat-assistant-for-a-static-blog-no-vector-db-required/</guid><description>A practical walkthrough of building a conversational AI assistant for a Hugo static site using TF-IDF retrieval over a flat JSON knowledge base — no vector database, no backend server, no embeddings infrastructure required.</description></item><item><title>TCP/IP, DNS, and Data Transmission Protocols Explained</title><link>/posts/tcpip-dns-and-data-transmission-protocols-explained/</link><pubDate>Sun, 22 Mar 2026 17:22:27 -0700</pubDate><guid>/posts/tcpip-dns-and-data-transmission-protocols-explained/</guid><description>A practical, code-illustrated guide to how TCP/IP, DNS, and modern data transmission protocols work under the hood — from handshakes and packet routing to WebSockets, gRPC, and QUIC.</description></item><item><title>AI Prompting Techniques: System Prompts, Few-Shot, CoT, and Structured Output</title><link>/posts/ai-prompting-techniques-system-prompts-few-shot-cot-and-structured-output/</link><pubDate>Sun, 22 Mar 2026 12:32:36 -0700</pubDate><guid>/posts/ai-prompting-techniques-system-prompts-few-shot-cot-and-structured-output/</guid><description>A practical engineering guide to four core LLM prompting techniques—system prompts, few-shot examples, chain-of-thought reasoning, and structured output—covering real failure modes and production-ready patterns.</description></item><item><title>The Evolution: Beyond Transformers</title><link>/posts/the-evolution-beyond-transformers/</link><pubDate>Sun, 22 Mar 2026 11:43:37 -0700</pubDate><guid>/posts/the-evolution-beyond-transformers/</guid><description>A practical walkthrough of how the Transformer architecture evolved from encoder-decoder to decoder-only models, why attention&amp;rsquo;s quadratic scaling became a hard wall, and how Mamba&amp;rsquo;s state space machines are being absorbed into hybrid architectures that dominate production today.</description></item><item><title>Training for Greatness: Speed, BLEU Records, and the Multimodal Vision</title><link>/posts/training-for-greatness-speed-bleu-records-and-the-multimodal-vision/</link><pubDate>Sat, 21 Mar 2026 12:20:48 -0700</pubDate><guid>/posts/training-for-greatness-speed-bleu-records-and-the-multimodal-vision/</guid><description>A practical deep-dive into how the original Transformer model shattered translation benchmarks, slashed training costs, and laid the architectural foundation for every major LLM that followed.</description></item><item><title>Inside the Machine: Encoders, Decoders, and Masking</title><link>/posts/inside-the-machine-encoders-decoders-and-masking/</link><pubDate>Sat, 21 Mar 2026 12:19:38 -0700</pubDate><guid>/posts/inside-the-machine-encoders-decoders-and-masking/</guid><description>A practical deep-dive into how the Transformer&amp;rsquo;s encoder and decoder stacks work, covering residual connections, positional encoding, masked self-attention, and cross-attention with code examples throughout.</description></item><item><title>The End of the RNN Era &amp; The Query, Key, Value Revolution</title><link>/posts/the-end-of-the-rnn-era-the-query-key-value-revolution/</link><pubDate>Sat, 21 Mar 2026 12:06:03 -0700</pubDate><guid>/posts/the-end-of-the-rnn-era-the-query-key-value-revolution/</guid><description>A practical walkthrough of why RNNs hit a fundamental wall with sequential processing and long-range dependencies, and how the Query-Key-Value attention mechanism solves both problems in one elegant step.</description></item><item><title>Gradient Descent in Neural Networks: Understanding How Machines Learn</title><link>/posts/gradient-descent/</link><pubDate>Sun, 20 Oct 2024 00:00:00 +0000</pubDate><guid>/posts/gradient-descent/</guid><description>Learn how Gradient Descent helps neural networks improve predictions through gradual optimization of weights and biases. Discover the core mechanics of machine learning.</description></item><item><title>Understanding Neural Networks: Weights, Biases, and Activations</title><link>/posts/deep-learning/</link><pubDate>Sat, 12 Oct 2024 00:00:00 +0000</pubDate><guid>/posts/deep-learning/</guid><description>This article breaks down the key mathematical concepts behind neural networks, including weights, biases, and activations, with an example of handwritten digit recognition.</description></item><item><title>Orchestrating workflows in the Cloud</title><link>/posts/workflow-orchestration/</link><pubDate>Thu, 10 Oct 2024 00:00:00 +0000</pubDate><guid>/posts/workflow-orchestration/</guid><description>AWS Step Functions vs Azure Logic Apps vs Azure Durable Functions vs Temporal</description></item><item><title>Sub-Word Tokenization: Breaking Words Like a Pro</title><link>/posts/tokenization/</link><pubDate>Wed, 02 Oct 2024 00:00:00 +0000</pubDate><guid>/posts/tokenization/</guid><description>Take a detour before diving into transformers and explore sub-word tokenization techniques like Byte-Pair Encoding, WordPiece, and Unigram models. Learn how they handle rare words, reduce vocabulary size, and make models more efficient!</description></item><item><title>N-Grams Uncovered: A Key Component of Large Language Models</title><link>/posts/n-grams/</link><pubDate>Sun, 29 Sep 2024 00:00:00 +0000</pubDate><guid>/posts/n-grams/</guid><description>Decoding N-Grams: The Heart of Large Language Models</description></item><item><title>Beginner’s Guide to AI: Diving Into My First AI Blog Post</title><link>/posts/first-ai-post/</link><pubDate>Sat, 28 Sep 2024 00:00:00 +0000</pubDate><guid>/posts/first-ai-post/</guid><description>Why am I writing these AI blogs? Discover my journey into AI and LLMs!</description></item><item><title>Tricky gRPC load balancing</title><link>/posts/grpc-load-balancing/</link><pubDate>Wed, 24 May 2023 00:00:00 +0000</pubDate><guid>/posts/grpc-load-balancing/</guid><description>Emulates and resolves load balancing problems with gRPC</description></item></channel></rss>