~/talk

Building AI Powered Applications with Java

slides:none on file

Java code wires external LLMs to private data using Spring AI and LangChain4j, vectorizing docs and storing embeddings in a DB (demo writes embeddings into an Oracle vector store via testcontainers). Retrieval-Augmented Generation works but is nondeterministic; parsing matters β€” no Asciidoc parser so results can be wrong. A batch run of 397 documents becomes 2,583 text segments and takes about a minute and a half to encode, illustrating real-world cost and latency.

AI-written summary Β· about

  1. 0:00AI powered Java apps intro
  2. 3:20Why AI matters now
  3. 7:16Start AI in Java
  4. 10:27How LLMs work
  5. 12:13RAG with private data
  6. 13:16Vector DBs for AI
  7. 16:10Testcontainers for local AI
  8. 17:38Live RAG demo: LangChain4j & OpenAI
  9. 21:34Testing AI apps
  10. 24:24Optimize RAG doc processing
  11. 27:33Store embeddings in vector DB
  12. 31:07Model Context Protocol
  13. 34:41AI tools future impact
  14. 35:45Why Java developers should embrace AI tools
  15. 38:32Q&A
~/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 β€” the status bar button does the same
?
this help
esc
close this, then clear every filter β€” 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.