~/talk

AI-driven Unstructured Data Extraction Using Apache Camel and LangChain4J

on YouTube 20m
Talkat JCON EUROPE 2026 · 2026-04-20..04-23· [ai-assisted-development, java]

speaker

name:Alexandre Gallice
links:none on file

resources

video:https://youtu.be/tcCUTs0S_ZA
slides:none on file

summary

Prototype converts conversation transcripts to POJOs using Apache Camel Quarkus + LangChain4j prototype and a local Ollama-hosted model, Granite 4 3B on Ollama (local CPU). It extracts entities, relations and composite fields (customer.name, customer.birthday), resolves coreferences including a name-change trap, and returns structured JSON via a JSON-schema-like output. Inference runs about 15 seconds on a small machine, yields a reasonable demo accuracy, and highlights the need for confidence scoring and closed vs open extraction choices.

AI-written summary · about

chapters (13)

  1. 0:00Introduction to AI data extraction
  2. 1:19What is unstructured data
  3. 3:07Demo setup and challenges
  4. 5:37Code walkthrough introduction
  5. 7:00LangChain4J configuration
  6. 8:23Defining extraction targets
  7. 9:48Prompt and contract setup
  8. 10:51Apache Camel integration
  9. 12:18Execution and results
  10. 14:27Key learnings and tips
  11. 16:33Next steps and accuracy
  12. 18:21Handling extraction errors
  13. 19:44Conclusion and Q&A

related talks

~/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.