Arun Shankar

LLM-Text-to-SQL-Architectures. A collection of architectural patterns leveraging Large Language Models (LLMs) for efficient Text-to-SQL generation.

Agentic-Workflow-Patterns. Repository demonstrating best practices and patterns for implementing agentic workflows in Python, featuring modular, scalable, and reusable design patterns for intelligent automation.

react-from-scratch. This repo compiles a collection of examples that demonstrate the effective use of the ReAct pattern in LLM prompting. It includes variations and implementations of agents that leverage the ReAct pattern, optimized for Gemini.

AgenticSearch. AgenticSearch operates within an agentic workflow, utilizing Gemini 2.0 and an extensive tool registry to handle complex questions. By integrating and synthesizing data from multiple APIs, it delivers cohesive and detailed answers, enabling a robust and intelligent search system.

Python-Design-Patterns-for-AI. A repository showcasing Python design patterns specifically adapted for building robust and efficient AI workflows.

VertexAI-Semantic-Caching. Repository dedicated to enhancing data retrieval and processing efficiencies in Google Cloud's Vertex AI by implementing a semantic caching layer with MemoryStore, Vertex AI Vector Search, and Gemini, focusing on GenAI applications.

VAIS-RAG-Patterns. Architectural Blueprints for RAG Automation: Advanced Document Understanding using Vertex AI Search

genai-transport-protocols. GenAI with Google Gemini: 5 transport approaches REST → Streaming → SSE → WebSockets → gRPC

VertexAI-Document-Discovery. Python pipeline that automates URL batching for creating search apps with Google Cloud's Vertex AI Search.

AgenticAppBuilder. A multi-agent system that collaboratively ideates and constructs lightweight web applications, leveraging a curated set of public APIs.

VAI-FineTuning-LLMs. "Clean and comprehensive examples for fine-tuning LLMs supported by Vertex AI, including proprietary, open-source, and third-party models."

VertexAI-Grounding. Collection of examples showcasing different types of Grounding LLM Responses using Vertex AI.

TimesFM-Examples. Examples showcasing TimesFM’s time-series forecasting capabilities.

interactive-react-agent-gcp. An interactive ReAct agent deployed on Google Cloud Run with a Streamlit UI client.