Building AI Applications in Go
summary
Argues that Go can run production gen AI by showing LangChainGo (Go idiomatic LangChain port), live inference against OpenAI, Google Gemini and Olama and Llama 3 8B on-laptop (CPU) models, streaming token handling, structured JSON output, and parallel tool calling used to fetch weather and merge responses. Demonstrates vector DB support, a growth curve with ~100 contributors and active PRs, and previews LangGraphGo agents plus LangSmith observability integration.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 4:45Generative AI ecosystem
- 7:14LangChain and AI tooling
- 10:31Introducing LangChain Go
- 12:56Design principles
- 13:42Live coding demo
- 16:40Structured output and tool calling
- 21:00Vector databases and embeddings
- 24:10Future roadmap
- 26:41Call to action
- 27:43Q&A
related talks
01h 01mBuilding Generative AI Applications in Go- Gari Singh, Google (Part 1)
43mAI and Go: Opportunities and Challenges Panel Discussion
51mBuilding Generative AI Applications in Go- Gari Singh, Google (Part 2)
29mThe Go-to Language for AI: Opportunities and Challenges
31mAI-Driven Development in Go
31mDecoding AI: A Go Programmer's Perspective
02h 49mJava meets AI: Build LLM-Powered Apps with LangChain4j
02h 35mBringing GenAI to the Modern Enterprise. A production use-case. In Serverless Java!