API Based RAG using Apideck’s Filestorage API, LangChain, Ollama, and Streamlit
This article walks through building a Retrieval-Augmented Generation (RAG) pipeline that goes beyond static vector stores. Instead of pre-indexed documents, it uses API-based retrieval to access live files from Box via Apideck’s unified file storage API. You'll see how to authenticate users securely with Vault, fetch and download files, and summarize them in real-time with a local LLM using LangChain and Ollama.