CtrlK

Community Documentation Log in Get started

tessl/maven-org-springframework-ai--spring-ai-autoconfigure-model-chat-memory

Spring Boot auto-configuration for chat memory functionality in Spring AI applications

Overview

Eval results

Files

Spring AI Chat Memory Auto Configuration

Name: tessl/maven-org-springframework-ai--spring-ai-autoconfigure-model-chat-memory
Author: tessl

Spring Boot auto-configuration module that automatically configures chat memory functionality for managing conversational context in Spring AI applications. Provides zero-configuration setup for storing and retrieving conversation history with sensible defaults.

Quick Reference

Component	Purpose	Default Implementation
`ChatMemory`	Store and retrieve conversation messages	`MessageWindowChatMemory` (20 messages)
`ChatMemoryRepository`	Persist messages	`InMemoryChatMemoryRepository`
Message Types	User, Assistant, System, Tool	All extend `AbstractMessage`

Installation

Maven:

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-autoconfigure-model-chat-memory</artifactId>
    <version>1.1.2</version>
</dependency>

Gradle:

implementation 'org.springframework.ai:spring-ai-autoconfigure-model-chat-memory:1.1.2'

Core Concepts

Auto-Configuration

When on the classpath, Spring Boot automatically creates:

A ChatMemoryRepository bean (default: in-memory)
A ChatMemory bean (default: 20-message sliding window)

Chat Memory Interface

public interface ChatMemory {
    void add(String conversationId, Message message);
    void add(String conversationId, List<Message> messages);
    List<Message> get(String conversationId);
    void clear(String conversationId);
}

Key Behaviors:

Conversation IDs must not be null or empty
Messages must not be null
System messages are preserved during eviction
Thread-safe implementations required

Message Types

Type	Class	Purpose
User	`UserMessage`	Input from users/developers
Assistant	`AssistantMessage`	AI-generated responses
System	`SystemMessage`	High-level instructions (preserved)
Tool	`ToolResponseMessage`	Function/tool execution results

Repository Implementations

Type	Module	Use Case
In-Memory	Built-in	Development/testing
JDBC	`spring-ai-autoconfigure-model-chat-memory-repository-jdbc`	Relational databases
MongoDB	`spring-ai-autoconfigure-model-chat-memory-repository-mongodb`	Document storage
Cassandra	`spring-ai-autoconfigure-model-chat-memory-repository-cassandra`	Distributed systems
Neo4j	`spring-ai-autoconfigure-model-chat-memory-repository-neo4j`	Graph relationships
Cosmos DB	`spring-ai-autoconfigure-model-chat-memory-repository-cosmos-db`	Azure cloud

Basic Usage

@Service
public class ConversationService {
    @Autowired
    private ChatMemory chatMemory;

    public void addMessage(String conversationId, String content, boolean isUser) {
        Message message = isUser ? 
            new UserMessage(content) : 
            new AssistantMessage(content);
        chatMemory.add(conversationId, message);
    }

    public List<Message> getHistory(String conversationId) {
        return chatMemory.get(conversationId);
    }
}

Customization

Custom Repository

@Configuration
public class ChatMemoryConfig {
    @Bean
    public ChatMemoryRepository chatMemoryRepository(DataSource dataSource) {
        return JdbcChatMemoryRepository.builder()
            .dataSource(dataSource)
            .build();
    }
}

Custom Window Size

@Configuration
public class ChatMemoryConfig {
    @Bean
    public ChatMemory chatMemory(ChatMemoryRepository repository) {
        return MessageWindowChatMemory.builder()
            .chatMemoryRepository(repository)
            .maxMessages(100)
            .build();
    }
}

Configuration Properties

JDBC Repository

spring.ai.chat.memory.repository.jdbc.initialize-schema=always
spring.ai.chat.memory.repository.jdbc.platform=postgresql

MongoDB Repository

spring.ai.chat.memory.repository.mongo.create-indices=true
spring.ai.chat.memory.repository.mongo.ttl=PT24H

Cassandra Repository

spring.ai.chat.memory.repository.cassandra.keyspace=my_keyspace
spring.ai.chat.memory.repository.cassandra.table=chat_memory
spring.ai.chat.memory.repository.cassandra.time-to-live=P30D

Neo4j Repository

spring.ai.chat.memory.repository.neo4j.session-label=ChatSession
spring.ai.chat.memory.repository.neo4j.message-label=ChatMessage

Cosmos DB Repository

spring.ai.chat.memory.repository.cosmosdb.endpoint=https://myaccount.documents.azure.com:443/
spring.ai.chat.memory.repository.cosmosdb.key=your-account-key
spring.ai.chat.memory.repository.cosmosdb.database-name=chat_memory_db

Core Imports

import org.springframework.ai.chat.memory.ChatMemory;
import org.springframework.ai.chat.memory.ChatMemoryRepository;
import org.springframework.ai.chat.memory.InMemoryChatMemoryRepository;
import org.springframework.ai.chat.memory.MessageWindowChatMemory;
import org.springframework.ai.chat.messages.Message;
import org.springframework.ai.chat.messages.UserMessage;
import org.springframework.ai.chat.messages.AssistantMessage;
import org.springframework.ai.chat.messages.SystemMessage;
import org.springframework.ai.chat.messages.ToolResponseMessage;

Key Features

Zero Configuration: Works out-of-box with sensible defaults
Message Window: Automatic eviction of old messages (configurable)
System Message Preservation: System instructions preserved during eviction
Multiple Repositories: Support for various storage backends
Thread-Safe: Concurrent access support
Auto-Detection: Automatic database dialect detection (JDBC)
TTL Support: Time-to-live for conversations (MongoDB, Cassandra)
Schema Management: Automatic schema initialization

Important Notes

⚠️ Production Warning: InMemoryChatMemoryRepository loses data on restart. Use persistent repositories for production.

⚠️ Thread Safety: All repository implementations must be thread-safe for concurrent access.

⚠️ Validation: All methods validate inputs and throw IllegalArgumentException for null/empty values.

⚠️ System Messages: MessageWindowChatMemory replaces old system messages when new ones are added.

Documentation Structure

Guides

Quick Start Guide - Step-by-step getting started
Repository Selection Guide - Choosing the right repository
Configuration Guide - Detailed configuration options

Examples

Real-World Scenarios - Production use cases
Edge Cases - Error handling and advanced scenarios

Reference

ChatMemory API - Complete ChatMemory interface documentation
Repository API - ChatMemoryRepository and implementations
Message Types - All message type specifications
JDBC Repository - JDBC implementation details
MongoDB Repository - MongoDB implementation details
Cassandra Repository - Cassandra implementation details
Neo4j Repository - Neo4j implementation details
Cosmos DB Repository - Cosmos DB implementation details
Builder Patterns - All builder API specifications
Configuration Properties - Complete property reference
Performance - Performance considerations and optimization
Troubleshooting - Common issues and solutions

Package Information

Package Name: spring-ai-autoconfigure-model-chat-memory
Group ID: org.springframework.ai
Package Type: maven
Language: Java
Version: 1.1.2