Guillaume Laforge glaforge

Our Favorite Codelabs

AI Agent Development & Evaluation

Build a Location Intelligence ADK Agent with MCP servers for BigQuery and Google Maps
https://codelabs.developers.google.com/adk-mcp-bigquery-maps
Evaluating Agents with ADK
https://codelabs.developers.google.com/adk-eval/instructions
Build AI Agents with Agent Development Kit for Java
https://codelabs.developers.google.com/adk-java-getting-started
Analyze ADK Agent execution with the BigQuery Agent Analytics Plugin

Slides of the presentation

Quarkus A2A Demo

A2A demo by Emmanuel Bernard

Okay, here's a breakdown of how to create a new LangChain4j embedding store module for Google Cloud Firestore, along with the key steps and considerations, mirroring the structure of existing modules like langchain4j-milvus.

Project Structure

Your project structure should follow the established pattern. I'll create a simplified version based on the most relevant parts from the provided file listing. The full structure would be much larger (like the main langchain4j project), but this captures the essentials:

langchain4j/
└── langchain4j-embedding-store-google-firestore/  (or similar name)
    ├── pom.xml                                     (Your module's Maven build file)

	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8" />
	<meta name="viewport" content="width=device-width, initial-scale=1.0" />
	<title>Reciprocal Rank Fusion Simulator</title>
	<script>
	// Avoids a flash of the wrong theme.
	if (localStorage.getItem('theme') === 'dark' \|\| (!('theme' in localStorage) && window.matchMedia('(prefers-color-scheme: dark)').matches)) {
	document.documentElement.classList.add('dark')

	import com.google.adk.agents.BaseAgent;
	import com.google.adk.agents.LlmAgent;
	import com.google.adk.tools.BaseTool;
	import com.google.adk.tools.mcp.McpToolset;
	import com.google.adk.tools.mcp.SseServerParameters;
	import com.google.adk.tools.mcp.StreamableHttpServerParameters;
	import com.google.adk.web.AdkWebServer;

	import java.util.List;

	## Google: Market Research Report (Q2 2025)

	Executive Summary:

	This report provides an overview of Google, its recent performance,
	and current market position. Google, a subsidiary of Alphabet Inc.,
	continues to be a dominant force in the technology industry, driven
	by its core search engine, cloud services, and advancements in
	artificial intelligence. Recent financial results for Q2 2025
	exceeded expectations, demonstrating strong growth across key

	var companyProfiler = LlmAgent.builder()
	.name("company-profiler")
	.description(
	"Provides a general overview of a company.")
	.instruction("""
	Your role is to provide a brief overview of the
	given company.
	Include its mission, headquarters, and current CEO.
	Use the Google Search Tool to find this information.
	""")

	package agents;

	import static java.nio.charset.StandardCharsets.UTF_8;
	import java.util.Scanner;

	import com.google.adk.agents.BaseAgent;
	import com.google.adk.agents.LlmAgent;
	import com.google.adk.events.Event;
	import com.google.adk.runner.InMemoryRunner;
	import com.google.adk.sessions.Session;

	import dev.langchain4j.agent.tool.ToolExecutionRequest;
	import dev.langchain4j.mcp.McpToolProvider;
	import dev.langchain4j.mcp.client.DefaultMcpClient;
	import dev.langchain4j.mcp.client.McpClient;
	import dev.langchain4j.mcp.client.transport.McpTransport;
	import dev.langchain4j.mcp.client.transport.http.HttpMcpTransport;
	import dev.langchain4j.model.vertexai.VertexAiGeminiChatModel;
	import dev.langchain4j.service.AiServices;
	import dev.langchain4j.service.SystemMessage;
	import dev.langchain4j.service.tool.ToolProvider;

	public class SentenceWindowRetrieval {
	public static void main(String[] args) throws IOException {

	Document capitalDocument = Document.from("...");

	VertexAiEmbeddingModel embeddingModel = VertexAiEmbeddingModel.builder()
	.project(System.getenv("GCP_PROJECT_ID"))
	.endpoint(System.getenv("GCP_VERTEXAI_ENDPOINT"))
	.location(System.getenv("GCP_LOCATION"))
	.publisher("google")