Building LLM Apps on App Engine
summary
LangChain apps deploy to Cloud Run with a working demo that indexes release notes, calls Gemini on Vertex Endpoints, and returns grounded answers — the demo uses LangServe’s playground, preloads documents, and deploys with one command to bootstrap and a final gcloud run deploy to go live. The stack pairs LangChain + LangServe with Cloud SQL with pgvector (vector storage) and Vertex for inference; a customer (L’Oreal) shows this pattern running in production.
AI-written summary · about
chapters (6)
- 0:00Meet Steren and Wietse
- 1:11What is LangChain?
- 1:47Cloud Run and LangChain
- 3:14LangChain demo explained
- 4:29How can developers get started?
- 5:00Wrap up
related talks
01h 59mLLM applications with LangChain
25mLangChain with Azure AI: Building LLM powered Applications
28mBuilding AI Applications in Go
41mServerless LLM with AWS Lambda and LangChain: A Revolution in Application Development
01h 50mChatGPT & LLMs: A Practical Starter's Guide to Language Chains
01h 04mBuilding LLM powered applications in Ruby
02h 49mJava meets AI: Build LLM-Powered Apps with LangChain4j
02h 35mBringing GenAI to the Modern Enterprise. A production use-case. In Serverless Java!