AI

Build a tiny little RAG for my personal site using Prompt AI API. Running Free, Fast and Private all inside your browser.

Deep dive into running a Large Language Model on an ESP32-S3 microcontroller - exploring llama2.c, SIMD optimizations, and the challenges of streaming inference on embedded hardware.

Building a hybrid RAG chatbot that intelligently routes queries between Chrome's on-device Prompt API and cloud models, achieving 70%+ cost reduction while maintaining privacy and performance.

Learn how to build task-oriented dialogue systems using LLMs and metadata-driven architecture. From lead qualification to government form assistance, discover how low-agency AI achieves higher completion rates than traditional forms at 1/10th the cost.

Learn how to implement effective prompt-based guardrails for AI systems. From pre-search filtering to post-search relevance checks, discover practical approaches to building trust and control in AI applications.

In this third installment of the 'Revolutionizing Search with AI' series, we further delve into the power of semantic search with RAG to elevate search engine capabilities. Explore how we've applied RAG principles to create a more user-friendly search engine experience.

Today's AI, powered by machine learning algorithms, has introduced us to semantic search. Explore how we combined Pinecone and OpenAI to create intelligent, user-friendly AI experiences and unravel the code that powers our demo application.

Artificial Intelligence (AI) has transformed the way we search for information. Learn how we leveraged AI by merging our understanding of Large Language Models (LLM), vector databases, and Retrieval Augmented Generation (RAG), to create an advanced semantic search system.