Local RAG Pipeline

Current Talk

This talk explores building efficient Retrieval-Augmented Generation (RAG) pipelines that run entirely on local infrastructure. We'll cover local LLM integration, vector database setup, chunking strategies, and optimization techniques for privacy-focused AI applications. Learn how to deploy production-ready RAG systems without relying on external APIs.

Explore Past Talks

Beyond the Prompt: A Deep Dive into RAG

Technical Conference 2024 • Multiple Venues

This talk explores Retrieval-Augmented Generation (RAG) as a powerful solution to the limitations of traditional LLM prompting, such as hallucination and outdated knowledge. Covers RAG architecture from data ingestion and chunking to vector embedding, retrieval, and generation. Advanced retrieval techniques like hybrid and re-ranking search, optimization strategies, real-world applications, and the future of RAG.

Experience IoT Development using ESP32

D2D Conference 2024 • Delhi Technological University, Delhi

Comprehensive session on IoT development using ESP32 microcontrollers, covering hardware integration, sensor interfacing, wireless communication protocols, and real-world applications in smart devices and automation systems.

How the Internet Works: A Deep Dive

Winterlude Conference 2023 • Multiple GDSCs, Delhi NCR

Technical session explaining internet protocols, data transmission, networking fundamentals, and backend infrastructure. Covered HTTP/HTTPS, TCP/IP, DNS, and modern web architecture patterns for developers.

Building Next-Gen Supply Chain Management with Blockchain, IoT & AI

GDG DevFest 2022 • GDG Noida

Advanced session on implementing blockchain-based supply chain solutions with IoT tracking and AI optimization. Covered distributed ledger technology, real-time asset tracking, predictive analytics, and smart contract implementation for supply chain resilience.

Interested in having me speak at your event?

Get In Touch