LLM

A modern, full-stack app connecting real-time NOAA space weather data with Google Gemini to generate travel routes for aurora sightings deployed to the global edge via Vercel. Demonstrate secure AI integration with a dual-layer identity ecosystem (Auth0 M2M) to securely isolate end-user authentication from the Gemini AI inference agent, enforcing strict API quotas and telemetry ingestion via Upstash Redis. Provides scalable edge-routing within a consumer-facing product.

RAG (Retrieval Augmented Generation) is an AI framework that allows developers to add external information without retraining the LLM, improving the accuracy of its answers. As of 2026, it is a widely known technology. The concept is roughly as follows: First, vectorize external information (the data you want the LLM to know) using an embedding model and store it. After a user enters a prompt, the prompt is also vectorized using the same embedding model. It is then compared against the previously stored vectors to retrieve the most similar pieces of data. These are then integrated by the LLM to generate a response for the user. This approach allows the LLM to answer using specific knowledge integrated by developers without the need for retraining.

Conversational AI app demonstrating accurate LLM inference with RAG over complex datasets. Tech stack: Serverless FastAPI backend on GCP (provisioned via Terraform), local ONNX embeddings, Firestore vector search, and LangChain orchestration.