Spring AI

Expose the GoodMem RAG memory API as Spring AI tools that a ChatClient-driven LLM can call to store and retrieve memories.

Stable· Java (Maven/Gradle)

io.github.bashareid:goodmem-spring-ai

Overview

GoodMem is a retrieval-augmented generation (RAG) memory layer that chunks, embeds, and indexes documents server-side so an agent can pull back the most relevant passages on any question. The Spring AI integration wraps the GoodMem API as Spring AI tools: register them with a ChatClient and the model can create spaces, store text or files, and run semantic retrieval — with optional reranking and an LLM-generated summary — against a running GoodMem server.

Installation

<dependency>
    <groupId>io.github.bashareid</groupId>
    <artifactId>goodmem-spring-ai</artifactId>
    <version>0.1.0</version>
</dependency>

Spring AI 1.0 or later is required and must be on the classpath. The artifact is published on Maven Central under a personal groupId (io.github.bashareid), which may change.

Configuration

Variable	Description
`GOODMEM_BASE_URL`	Base URL of the GoodMem API server (default `https://your-goodmem-server.example.com`).
`GOODMEM_API_KEY`	API key sent as the `X-API-Key` header.
`GOODMEM_VERIFY_SSL`	Set to `false` to skip TLS verification for self-signed dev certs (default: `true`).

The same values can be passed in code through GoodMemClient.builder() (baseUrl, apiKey, verifySsl) if you prefer not to rely on the environment.

Quick start

import ai.pairsys.goodmem.springai.GoodMemClient;
import ai.pairsys.goodmem.springai.GoodMemTools;
import org.springframework.ai.chat.client.ChatClient;

GoodMemClient client = GoodMemClient.builder()
    .baseUrl(System.getenv("GOODMEM_BASE_URL"))
    .apiKey(System.getenv("GOODMEM_API_KEY"))
    .build();

GoodMemTools tools = new GoodMemTools(client);

String reply = ChatClient.builder(chatModel)
    .defaultSystem("You have access to a GoodMem semantic memory store. "
        + "Use the goodmem tools to store facts the user shares and to "
        + "retrieve them when answering questions.")
    .build()
    .prompt()
    .user("What was our Q2 launch deadline again?")
    .tools(tools)
    .call()
    .content();

Every tool returns a Map<String, Object> with success: true and operation-specific fields on success, or success: false and an error field on failure.

Local development. The example above uses a TLS-verified production URL. If you are running GoodMem locally with a self-signed certificate, use https://localhost:8080 and disable TLS verification with the client's verify-SSL option (see the Configuration table above). Keep TLS verification enabled for any deployed server.

Retrieval post-processing

GoodMem's retrieval call accepts these optional post-processing parameters (each framework exposes them under its own naming convention):

Parameter	Range	Description
`reranker_id`	UUID	Reranker model that reorders matched chunks by relevance.
`llm_id`	UUID	LLM that generates a contextual answer (`abstractReply`) alongside the chunks.
`relevance_threshold`	0–1	Minimum relevance score for a result to be included.
`llm_temperature`	0–2	Sampling temperature for the LLM post-processor.
`max_results`	integer	Maximum number of results to return.
`chronological_resort`	boolean	Re-sort the final results by creation time instead of relevance.

Learn more

The full README, examples, and API reference live in the upstream repository: PAIR-Systems-Inc/goodmem-spring-ai.