聊聊Spring AI的ETL Pipeline

public interface DocumentReader extends Supplier<List<Document>> {

	default List<Document> read() {
		return get();
	}

}

public interface DocumentTransformer extends Function<List<Document>, List<Document>> {

	default List<Document> transform(List<Document> transform) {
		return apply(transform);
	}

}

public interface DocumentWriter extends Consumer<List<Document>> {

	default void write(List<Document> documents) {
		accept(documents);
	}

}

@BeforeEach
	void setUp() {
		DocumentReader markdownReader = new MarkdownDocumentReader(this.knowledgeBaseResource,
				MarkdownDocumentReaderConfig.defaultConfig());
		this.knowledgeBaseDocuments = markdownReader.read();
		this.pgVectorStore.add(this.knowledgeBaseDocuments);
	}

	@AfterEach
	void tearDown() {
		this.pgVectorStore.delete(this.knowledgeBaseDocuments.stream().map(Document::getId).toList());
	}

	@Test
	void ragBasic() {
		String question = "Where does the adventure of Anacletus and Birba take place?";

		RetrievalAugmentationAdvisor ragAdvisor = RetrievalAugmentationAdvisor.builder()
			.documentRetriever(VectorStoreDocumentRetriever.builder().vectorStore(this.pgVectorStore).build())
			.build();

		ChatResponse chatResponse = ChatClient.builder(this.openAiChatModel)
			.build()
			.prompt(question)
			.advisors(ragAdvisor)
			.call()
			.chatResponse();

		assertThat(chatResponse).isNotNull();

		String response = chatResponse.getResult().getOutput().getText();
		System.out.println(response);
		assertThat(response).containsIgnoringCase("Highlands");

		evaluateRelevancy(question, chatResponse);
	}