PinnedInGoogle Cloud - CommunitybyArun Shankar·Aug 23, 2025Engineering Transport Layers for GenAI: REST, WebSockets, gRPC, and Beyondtldr: Modern GenAI applications are unlike traditional web services. They don’t just fetch data; they hold conversations, stream responses…A response icon2A response icon2
PinnedInGoogle Cloud - CommunitybyArun Shankar·Oct 25, 2024Designing Cognitive Architectures: Agentic Workflow Patterns from Scratchtldr: The rapid evolution of Large Language Models (LLMs) and Artificial Intelligence (AI) agents has sparked the development of…A response icon5A response icon5
PinnedInGoogle Cloud - CommunitybyArun Shankar·Oct 12, 2024Building ReAct Agents from Scratch: A Hands-On Guide using Geminitldr: ReAct (Reason + Act) is a powerful framework for building AI agents that seamlessly integrates reasoning and decision-making with…A response icon17A response icon17
PinnedInGoogle Cloud - CommunitybyArun Shankar·Nov 12, 2023Architectural Patterns for Text-to-SQL: Leveraging LLMs for Enhanced BigQuery InteractionsTLDR: This article deep dives into the Text-to-SQL domain, demonstrating the growing reliance on Large Language Models (LLMs) for this…A response icon13A response icon13
PinnedInITNEXTbyArun Shankar·Feb 13, 2023ChatGPT Decoded: An expert guide to mastering the technology and building domain-specific…In this comprehensive guide, we will decode the steps taken by OpenAI to create ChatGPT. Our goal is to replicate these steps for a…A response icon6A response icon6
InGoogle Cloud - CommunitybyArun Shankar·Jan 16, 2025Agentic Search in Action: A Practical Guide to Building from ScratchtldrAgentic workflows, powered by advancements in Generative AI, are transforming enterprise solutions by enabling innovative architectures…A response icon1A response icon1
InITNEXTbyArun Shankar·Aug 20, 2024Python Design Patterns Every AI Developer Should KnowImage generated using Google Imagen 3
InGoogle Cloud - CommunitybyArun Shankar·Jun 13, 2024Implementing Semantic Caching: A Step-by-Step Guide to Faster, Cost-Effective GenAI WorkflowsTLDR: This article is a focused, in-depth exploration of semantic caching, its intricate implementation process, its relationship to LLMs…A response icon5A response icon5
InGoogle Cloud - CommunitybyArun Shankar·May 20, 2024Architectural Blueprints for RAG Automation: Advanced Document Understanding using Vertex AI SearchThis post deep dives into using Vertex AI Search to streamline the creation and evaluation of retrieval-augmented generation (RAG)…A response icon1A response icon1
InGoogle Cloud - CommunitybyArun Shankar·Mar 7, 2024Intelligent Document Discovery with Vertex AI SearchIn this post, we will explore the capabilities of Vertex AI Search, specifically, website search — a standout feature within Google…