Improve ETL Pipeline and add initial Use Cases

Signed-off-by: Thomas Vitale <[email protected]>

05-document-readers/document-readers-text-ollama/README.md → 00-use-cases/question-answering-with-documents/README.md

@@ -1,6 +1,6 @@
-# Text Document Readers: Ollama
+# Question Answering With Documents
 
-Reading and vectorizing text documents with LLMs via Ollama.
+Ask questions about documents with LLMs via Ollama.
 
 ## Running the application
 

05-document-readers/document-readers-pdf-ollama/src/main/java/com/thomasvitale/ai/spring/ChatController.java → 00-use-cases/question-answering-with-documents/src/main/java/com/thomasvitale/ai/spring/ChatController.java

@@ -15,7 +15,7 @@ class ChatController {
 
     @PostMapping("/chat/doc")
     String chatWithDocument(@RequestBody String input) {
-        return chatService.chatWithDocument(input).getContent();
+        return chatService.chatWithDocument(input);
     }
 
 }

00-use-cases/question-answering-with-documents/src/main/java/com/thomasvitale/ai/spring/ChatService.java

@@ -0,0 +1,48 @@
+package com.thomasvitale.ai.spring;
+
+import org.springframework.ai.chat.ChatClient;
+import org.springframework.ai.chat.messages.UserMessage;
+import org.springframework.ai.chat.prompt.SystemPromptTemplate;
+import org.springframework.ai.document.Document;
+import org.springframework.ai.vectorstore.SearchRequest;
+import org.springframework.ai.vectorstore.VectorStore;
+import org.springframework.stereotype.Service;
+
+import java.util.List;
+import java.util.Map;
+import java.util.stream.Collectors;
+
+@Service
+class ChatService {
+
+    private final ChatClient chatClient;
+    private final VectorStore vectorStore;
+
+    ChatService(ChatClient chatClient, VectorStore vectorStore) {
+        this.chatClient = chatClient;
+        this.vectorStore = vectorStore;
+    }
+
+    String chatWithDocument(String message) {
+        var systemPromptTemplate = new SystemPromptTemplate("""
+                You are a helpful assistant, conversing with a user about the subjects contained in a set of documents.
+                Use the information from the DOCUMENTS section to provide accurate answers. If unsure or if the answer
+                isn't found in the DOCUMENTS section, simply state that you don't know the answer and do not mention
+                the DOCUMENTS section.
+                
+                DOCUMENTS:
+                {documents}
+                """);
+
+        List<Document> similarDocuments = vectorStore.similaritySearch(SearchRequest.query(message).withTopK(5));
+        String content = similarDocuments.stream().map(Document::getContent).collect(Collectors.joining(System.lineSeparator()));
+
+        Map<String,Object> model = Map.of("documents", content);
+        var systemMessage = systemPromptTemplate.createMessage(model);
+
+        var userMessage = new UserMessage(message);
+
+        return chatClient.call(systemMessage, userMessage);
+    }
+
+}

05-document-readers/document-readers-text-ollama/src/main/java/com/thomasvitale/ai/spring/DocumentInitializer.java → 00-use-cases/question-answering-with-documents/src/main/java/com/thomasvitale/ai/spring/DocumentEtlPipeline.java

@@ -6,6 +6,7 @@
 import org.springframework.ai.document.Document;
 import org.springframework.ai.reader.TextReader;
 import org.springframework.ai.vectorstore.SimpleVectorStore;
+import org.springframework.ai.vectorstore.VectorStore;
 import org.springframework.beans.factory.annotation.Value;
 import org.springframework.core.io.Resource;
 import org.springframework.stereotype.Component;
@@ -15,38 +16,38 @@
 import java.util.List;
 
 @Component
-public class DocumentInitializer {
+public class DocumentEtlPipeline {
 
-    private static final Logger log = LoggerFactory.getLogger(DocumentInitializer.class);
-    private final SimpleVectorStore vectorStore;
+    private static final Logger logger = LoggerFactory.getLogger(DocumentEtlPipeline.class);
+    private final VectorStore vectorStore;
 
     @Value("classpath:documents/story1.md")
     Resource textFile1;
 
     @Value("classpath:documents/story2.txt")
     Resource textFile2;
 
-    public DocumentInitializer(SimpleVectorStore vectorStore) {
+    public DocumentEtlPipeline(VectorStore vectorStore) {
         this.vectorStore = vectorStore;
     }
 
     @PostConstruct
     public void run() {
         List<Document> documents = new ArrayList<>();
 
-        log.info("Loading .md files as Documents");
+        logger.info("Loading .md files as Documents");
         var textReader1 = new TextReader(textFile1);
         textReader1.getCustomMetadata().put("location", "North Pole");
         textReader1.setCharset(Charset.defaultCharset());
         documents.addAll(textReader1.get());
 
-        log.info("Loading .txt files as Documents");
+        logger.info("Loading .txt files as Documents");
         var textReader2 = new TextReader(textFile2);
         textReader2.getCustomMetadata().put("location", "Italy");
         textReader2.setCharset(Charset.defaultCharset());
         documents.addAll(textReader2.get());
 
-        log.info("Creating and storing Embeddings from Documents");
+        logger.info("Creating and storing Embeddings from Documents");
         vectorStore.add(documents);
     }
 

00-use-cases/question-answering-with-documents/src/main/java/com/thomasvitale/ai/spring/QuestionAnsweringWithDocuments.java

@@ -0,0 +1,22 @@
+package com.thomasvitale.ai.spring;
+
+import org.springframework.ai.embedding.EmbeddingClient;
+import org.springframework.ai.vectorstore.SimpleVectorStore;
+import org.springframework.ai.vectorstore.VectorStore;
+import org.springframework.boot.SpringApplication;
+import org.springframework.boot.autoconfigure.SpringBootApplication;
+import org.springframework.context.annotation.Bean;
+
+@SpringBootApplication
+public class QuestionAnsweringWithDocuments {
+
+    @Bean
+    VectorStore vectorStore(EmbeddingClient embeddingClient) {
+        return new SimpleVectorStore(embeddingClient);
+    }
+
+    public static void main(String[] args) {
+        SpringApplication.run(QuestionAnsweringWithDocuments.class, args);
+    }
+
+}

00-use-cases/question-answering-with-documents/src/test/java/com/thomasvitale/ai/spring/QuestionAnsweringWithDocumentsTests.java

@@ -0,0 +1,15 @@
+package com.thomasvitale.ai.spring;
+
+import org.junit.jupiter.api.Disabled;
+import org.junit.jupiter.api.Test;
+import org.springframework.boot.test.context.SpringBootTest;
+
+@SpringBootTest
+@Disabled
+class QuestionAnsweringWithDocumentsTests {
+
+    @Test
+    void contextLoads() {
+    }
+
+}

00-use-cases/question-answering-with-documents/src/test/java/com/thomasvitale/ai/spring/TestQuestionAnsweringWithDocuments.java

@@ -0,0 +1,26 @@
+package com.thomasvitale.ai.spring;
+
+import org.springframework.boot.SpringApplication;
+import org.springframework.boot.devtools.restart.RestartScope;
+import org.springframework.boot.test.context.TestConfiguration;
+import org.springframework.boot.testcontainers.service.connection.ServiceConnection;
+import org.springframework.context.annotation.Bean;
+import org.testcontainers.ollama.OllamaContainer;
+import org.testcontainers.utility.DockerImageName;
+
+@TestConfiguration(proxyBeanMethods = false)
+public class TestQuestionAnsweringWithDocuments {
+
+    @Bean
+    @RestartScope
+    @ServiceConnection
+    OllamaContainer ollama() {
+        return new OllamaContainer(DockerImageName.parse("ghcr.io/thomasvitale/ollama-llama3")
+                .asCompatibleSubstituteFor("ollama/ollama"));
+    }
+
+    public static void main(String[] args) {
+        SpringApplication.from(QuestionAnsweringWithDocuments::main).with(TestQuestionAnsweringWithDocuments.class).run(args);
+    }
+
+}