Natural Language Data Access in Java with Hibernate, Quarkus, & LangChain4j
summary
Live demo shows a Quarkus app using Hibernate ORM 7.3 and LangChain4j with a local Ollama/Qwen‑3 model (30B/3B) to convert plain English into HQL generated by LLM, execute it via Hibernate, and serialize results to JSON for a RAG step; an example runs a select/count that returns five USA companies on record. The module named Hibernate Assistant emits a JSON metamodel of entities, the LLM emits queries validated by HQL, ~20 lines of core glue code run on a laptop, and the service can be exposed as an MCP tool.
AI-written summary · about
chapters (12)
- 0:00Introduction and speaker intro
- 1:26Quick recap of ORM and Hibernate
- 5:57Challenges with AI and structured data
- 8:27Demo of natural language queries
- 13:09Security concerns with AI and databases
- 16:00Retrieval augmented generation with Hibernate
- 19:11Hibernate Assistant module features
- 22:27Code walkthrough and implementation
- 26:23Model Context Protocol integration
- 31:20Benefits and use cases summary
- 32:47How to try the new module
- 34:12Q&A session begins
related talks
42mCrafting Intelligent Applications in Java with Quarkus / LangChain4j
36mCrafting Intelligent Cloud Native applications with Quarkus
43mCrafting Intelligent Applications with Quarkus/LangChain4j
01h 01mCreate #AI Infused #Java Apps with #LangChain4j
50mDeveloping AI applications in Java with Quarkus and Langchain4j
48mAgentic AI with Quarkus, LangChain4j and vLLM
44mUnlocking the Future of Java: LLM Integration Unveiled by Quarkus & LangChain4j
44mCrafting Intelligent Supersonic Subatomic applications with Quarkus