Java Standalone

LangChain4j Agent Memory

LangChain4j sample that stores agent memory, transcripts, and hybrid retrieval data in Oracle AI Database.

#AI#Java#JSON#Oracle Text#Vector Search
What this sample helps you learn

This module demonstrates how Oracle AI Database can serve as both **durable agent memory** and an **append-only conversation transcript store** for a LangChain4j assistant. The sample combines:

Highlights

  • LangChain4j tools and chat orchestration with gpt-5-nano
  • text-embedding-3-small embeddings stored in an Oracle AI Database VECTOR column
  • Oracle Text over a native JSON memory document with json_textcontains
  • hybrid memory retrieval that fuses semantic similarity with exact text relevance