LangChain is a framework for developing applications powered by language models. Here are a few posts about building Retrieval-Augmented Generation (RAG) applications and agents using LangChain on Google Cloud.
At TEQNation 2024, I demonstrated how to build a complex LLM app using RAG and ReAct, grounded in over 20 million Hacker News comments, and explained how I did data scraping, indexing, and implementation with LangChain and Cloud Run.
Learn to build a Retrieval-Augmented Generation (RAG) app with LangChain and Gemini on Cloud Run, using a vector database to answer questions from Cloud Run release notes.
At Cloud Next 2024, I joined LangChain's founder and others to show how to build generative AI applications on Google Cloud using LangChain. I've included a demo of L'Oreal's internal GPT and a hands-on guide to building a LangChain app from scratch.
A hands-on look at how rebaseable container images are structured on Cloud Run, using Docker and FROM scratch.
Dumping verbose test logs into an AI coding agent wastes context window space. Wrapping test commands in a silent Make macro suppresses noise on success while preserving full stack traces on failure.
Deterministic directory hashing calculates unique local port numbers from absolute filesystem paths, preventing port collisions in Git worktrees without manual configuration.