plugins {

    id 'java'

    id 'org.springframework.boot' version '3.4.1' // Use latest stable

    id 'io.spring.dependency-management' version '1.1.7'

}

​

group = 'com.planetlearning'

version = '0.0.1-SNAPSHOT'

​

java {

    toolchain {

        languageVersion = JavaLanguageVersion.of(21)

    }

}

​

repositories {

    mavenCentral()

    maven { url '[https://repo.spring.io/milestone](https://repo.spring.io/milestone)' }

    maven { url '[https://repo.spring.io/snapshot](https://repo.spring.io/snapshot)' }

}

​

ext {

    set('springAiVersion', "1.0.0-M5") // Check for latest Milestone

}

​

dependencies {

    implementation 'org.springframework.boot:spring-boot-starter-web'

    implementation 'org.springframework.boot:spring-boot-starter-data-jpa'

    // AI & Vector Store

    implementation 'org.springframework.ai:spring-ai-starter-model-google-genai'

    implementation 'org.springframework.ai:spring-ai-starter-vector-store-pgvector'

    // Tika Reader - Reads PDFs, DOCX, PPT, TXT automatically

    implementation 'org.springframework.ai:spring-ai-tika-document-reader'

    // Database

    runtimeOnly 'org.postgresql:postgresql'

    compileOnly 'org.projectlombok:lombok'

    annotationProcessor 'org.projectlombok:lombok'

    testImplementation 'org.springframework.boot:spring-boot-starter-test'

}

​

dependencyManagement {

    imports {

        mavenBom "org.springframework.ai:spring-ai-bom:${springAiVersion}"

    }

}

spring.application.name=SpringAiRag

​

# --- Database Config ---

spring.datasource.url=jdbc:postgresql://localhost:5432/vectordb

spring.datasource.username=postgres

spring.datasource.password=password

spring.datasource.driver-class-name=org.postgresql.Driver

​

# --- AI Config ---

spring.ai.google.genai.api-key=YOUR_GOOGLE_GEMINI_KEY_HERE

spring.ai.google.genai.chat.options.model=gemini-1.5-flash

​

# --- Vector Store Config ---

# This tells Spring to create the table structure automatically

spring.ai.vectorstore.pgvector.initialize-schema=true

# Dimension for Gemini Embeddings (Important!)

spring.ai.vectorstore.pgvector.dimensions=768

package com.planetlearning.rag.service;

​

import jakarta.annotation.PostConstruct;

import org.slf4j.Logger;

import org.slf4j.LoggerFactory;

import org.springframework.ai.document.Document;

import org.springframework.ai.reader.tika.TikaDocumentReader;

import org.springframework.ai.transformer.splitter.TokenTextSplitter;

import org.springframework.ai.vectorstore.VectorStore;

import org.springframework.beans.factory.annotation.Value;

import org.springframework.core.io.Resource;

import org.springframework.stereotype.Service;

​

import java.util.List;

​

@Service

public class EtlService {

​

    private static final Logger logger = LoggerFactory.getLogger(EtlService.class);

​

    private final VectorStore vectorStore;

​

    // Load files from the "resources" folder

    @Value("classpath:docs/company_policy.pdf")

    private Resource pdfResource;

​

    @Value("classpath:docs/notes.txt")

    private Resource txtResource;

​

    public EtlService(VectorStore vectorStore) {

        this.vectorStore = vectorStore;

    }

​

    // You can call this manually via an endpoint, or on startup

    public void ingestFiles() {

        logger.info("--- Starting ETL Pipeline ---");

​

        List<Resource> resources = List.of(pdfResource, txtResource);

​

        // 1. Transformer: Split long text into small AI-readable chunks

        TokenTextSplitter splitter = new TokenTextSplitter();

​

        for (Resource resource : resources) {

            if (!resource.exists()) {

                logger.warn("File not found: {}", resource.getFilename());

                continue;

            }

​

            logger.info("Processing: {}", resource.getFilename());

​

            // 2. Extract: Use Tika to read ANY file type (PDF, DOCX, TXT)

            TikaDocumentReader reader = new TikaDocumentReader(resource);

            List<Document> rawDocs = reader.get();

​

            // 3. Transform: Split docs into chunks

            List<Document> splitDocs = splitter.apply(rawDocs);

​

            // 4. Load: Store embeddings in Postgres

            vectorStore.add(splitDocs);

            logger.info("Saved {} chunks for file: {}", splitDocs.size(), resource.getFilename());

        }

        logger.info("--- ETL Pipeline Completed ---");

    }

}

package com.planetlearning.rag.controller;

​

import com.planetlearning.rag.service.EtlService;

import org.springframework.ai.chat.client.ChatClient;

import org.springframework.ai.chat.client.advisor.QuestionAnswerAdvisor;

import org.springframework.ai.vectorstore.VectorStore;

import org.springframework.web.bind.annotation.*;

​

@RestController

@RequestMapping("/api/v1/rag")

public class RagController {

​

    private final ChatClient chatClient;

    private final EtlService etlService;

​

    // We inject VectorStore to pass it to the Advisor

    public RagController(ChatClient.Builder builder, VectorStore vectorStore, EtlService etlService) {

        this.etlService = etlService;

        // Build the ChatClient with the RAG Advisor

        this.chatClient = builder

                .defaultSystem("You are a smart assistant. You must answer questions ONLY based on the provided documents. If the answer is not in the documents, say 'I don't know'.")

                .defaultAdvisors(new QuestionAnswerAdvisor(vectorStore)) // <--- The Magic Line

                .build();

    }

​

    // Endpoint to trigger data loading

    @PostMapping("/ingest")

    public String ingestData() {

        etlService.ingestFiles();

        return "Documents parsed and stored in database!";

    }

​

    // Endpoint to chat

    @GetMapping("/chat")

    public String chat(@RequestParam String query) {

        return chatClient.prompt()

                .user(query)

                .call()

                .content();

    }

}