# Retrieval-augmented generation

Nicholas Hopper has used Retrieval-augmented generation in his work at APX Stream, Plotr and ForeFlight Hackathon.

- **Category:** Agents and retrieval
- **Also called:** RAG
- **Used at:** [APX Stream](https://nicholashopper.com/work/apx-stream.md), [Plotr](https://nicholashopper.com/work/plotr.md), ForeFlight Hackathon
- **Updated:** November 17, 2026

## Where Nicholas Hopper has used Retrieval-augmented generation

- Built retrieval end to end: OCR and layout-aware document parsing, chunking, pgvector hybrid search, reranking, a knowledge graph and grounded citations. ([AI Engineer, APX Stream](https://nicholashopper.com/work/apx-stream.md))
- Added a plan-then-draft gate so the model judges which retrieved sources are relevant before drafting, and refuses when none are. ([AI Engineer, APX Stream](https://nicholashopper.com/work/apx-stream.md))
- Indexed entire storefronts into Pinecone vector embeddings for retrieval-augmented chat with LangChain and the OpenAI SDK. ([AI Engineer, Plotr](https://nicholashopper.com/work/plotr.md))
- Nicholas Hopper won the Innovation Award at the 2025 ForeFlight Hackathon for an AI-driven interface to the ForeFlight iOS app, which put a 600-page reference PDF in a RAG database behind a text-to-action interface. (Innovation Award, ForeFlight Hackathon)

---

Canonical page: https://nicholashopper.com/skills/rag  
Last updated: 2026-11-17  
Index of all pages: https://nicholashopper.com/llms.txt
