📄️ Chat and Language Models
This page describes a low-level LLM API.
📄️ Chat Memory
Maintaining and managing ChatMessages manually is cumbersome.
📄️ Model Parameters
Depending on the model and provider you choose, you can adjust numerous parameters that will define:
📄️ Response Streaming
This page describes response streaming with a low-level LLM API.
📄️ AI Services
So far, we have been covering low-level components like ChatModel, ChatMessage, ChatMemory, etc.
📄️ Agents
Please note that "Agent" is a very broad term with multiple definitions.
📄️ Tools (Function Calling)
Some LLMs, in addition to generating text, can also trigger actions.
📄️ RAG (Retrieval-Augmented Generation)
LLM's knowledge is limited to the data it has been trained on.
📄️ Structured Outputs
The term "Structured Outputs" is overloaded and can refer to two things:
📄️ Classification
Overview
📄️ Embedding (Vector) Stores
Documentation on embedding stores can be found here.
📄️ Image Models
More info coming soon
📄️ Quarkus Integration
Quarkus provides a superb extension for LangChain4j.
📄️ Spring Boot Integration
LangChain4j provides Spring Boot starters for:
📄️ Helidon Integration
Helidon provides a LangChain4j integration module that simplifies building AI-driven applications while leveraging Helidon’s programming model and style.
📄️ Kotlin Support
Kotlin is a statically-typed language targeting the JVM (and other platforms), enabling concise and elegant code with seamless interoperability with Java libraries.
📄️ Logging
LangChain4j uses SLF4J for logging,
📄️ Observability
Chat Model Observability
📄️ Customizable HTTP Client
Some LangChain4j modules (currently OpenAI and Ollama) support customizing the HTTP clients used
📄️ Testing and Evaluation
Examples
📄️ Model Context Protocol (MCP)
LangChain4j supports the Model Context Protocol (MCP) to communicate with