~/talk

Codepocalypse Now Lang Chain4j vs Spring Al

Talkat DevFest Toulouse 2025 · on Thursday, 2025-11-13· [ai-assisted-development, java]
slides:none on file

Both frameworks implement the same airline-loyalty assistant (OpenAI APIs, PDF knowledge base, embeddings) and demonstrate LLM calls, conversational memory, RAG, MCP tool-calls and local models. LangChain4j wires memory with one annotation and exposes tools via Dev UI; Spring AI adds advisors (logger + chat-memory max messages 20) and configuration properties. RAG uses in-memory vectors (score ~0.87) from PDF chunks to correct Delta’s outdated MQD info (shows 28,000); both approaches work, LangChain4j feels more configuration-light.

AI-written summary · about

  1. 0:00LangChain4j vs Spring AI
  2. 6:33LLM integration basics
  3. 16:52Conversational memory
  4. 23:06Retrieval augmented generation
  5. 37:17Model Context Protocol
  6. 44:46Local models & closing
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.