Build AI-infused applications with Quarkus

Transcript

1. Supersonic, Subatomic intelligent applications. Build AI-Infused applications with Quarkus Kevin Dubois(@kevindubois) Principal Developer Advocate
2. quarkus.langchain4j.openai.api-key=xxx https://redhat-developer-demos.github.io/quarkus-tutorial put this in your application.properties when the tutorial asks for it: Get Started Here:
3. Kevin Dubois ★ Principal Developer Advocate at Red Hat ★ Based in Belgium 󰎐 ★ 🗣 Speak English, Dutch, French, Italian ★ Open Source Contributor (Quarkus, Camel, Knative, ..) @kevindubois@mastodon.social youtube.com/@thekevindubois linkedin.com/in/kevindubois github.com/kdubois @kevindubois.com
5. Left / Right of the model
6. Set goals App developer IT operations Data engineer Data scientists ML engineer Gather and prepare data Develop model Integrate models in app dev Model monitoring & management Retrain models Business leadership AI as a team initiative
7. Some Definitions
8. Boring Stuff Artificial Intelligence Artificial Intelligence “Ability of a machine to imitate human intelligent behaviour”
9. Machine Learning Artificial Intelligence “Application of AI to automatically learn and improve from experience” Machine Learning
10. Boring Stuff Deep Learning Artificial Intelligence “Vast volumes of data and complex algorithms to train a model using Neural Networks.” Machine Learning Deep Learning
11. Boring Stuff Generative AI Artificial Intelligence “Focuses on creating new and original content ” Machine Learning Deep Learning Generative AI
12. ▸ Transformers (recognize, predict and generate human language) ▸ Trained in a huge amount of data (trillions of tokens) ▸ Relationship between words and phrases ▸ Fine-tuned for specific domains What are Large Language Models (LLMs)?
14. LLM Langchain4j
15. Dependency <dependency> <groupId>io.quarkiverse.langchain4j</groupId> <artifactId>quarkus-langchain4j-openai</artifactId> <version>0.13.1</version> </dependency>
16. Prompts ▸ Interacting with the model for asking questions ▸ Interpreting messages to get important information ▸ Populating Java classes from natural language ▸ Structuring output
17. @RegisterAiService interface Assistant { String chat(String message); } @Inject private final Assistant assistant; quarkus.langchain4j.openai.api-key=sk-... Configure API key Define Ai Service Create the instance
18. Prompting @SystemMessage("You are a professional poet") @UserMessage(""" Write a poem about {topic}. The poem should be {lines} lines long. """) String writeAPoem(String topic, int lines); Add a context on the calls Chat message Placeholder
19. class TransactionInfo { @Description("full name") public String name; @Description("IBAN value") public String iban; @Description("Date of the transaction") public LocalDate transactionDate; @Description("Amount in dollars of the transaction") public double amount; } interface TransactionExtractor { @UserMessage("Extract information about a transaction from {{it}}") TransactionInfo extractTransaction(String text); } Marshalling objects
20. Chains & Memory ▸ Create conversations ▸ Refer to past answers ▸ Manage concurrent interactions
21. @Inject private final ChatLanguageModel model; ConversationalChain chain = ConversationalChain.builder() .chatLanguageModel(model) .build(); String userMessage1 = "Can you give a brief explanation of Kubernetes, 3 lines max?"; String answer1 = chain.execute(userMessage1); String userMessage2 = "Can you give me a YAML example to deploy an application for that?"; String answer2 = chain.execute(userMessage2); Conversation like chat Remember previous interactions
22. Tools ▸ Mixing business code with model ▸ Delegating to external services
23. @RegisterAiService(tools = EmailService.class) public interface MyAiService { @SystemMessage("You are a professional poet") @UserMessage("Write a poem about {topic}. Then send this poem by email.") String writeAPoem(String topic); @ApplicationScoped public class EmailService { @Inject Mailer mailer; @Tool("send the given content by email") public void sendAnEmail(String content) { mailer.send(Mail.withText("letter@quarkus.io", "A poem", content)); } } Describe when to use the tool Register the tool Need to run code
24. Embedding Documents ▸ Adding terms of use rules into the model ▸ Asking questions of legal documents ▸ Natural queries
25. @Inject RedisEmbeddingStore store; @Inject EmbeddingModel embeddingModel; public void ingest(List<Document> documents) { EmbeddingStoreIngestor ingestor = EmbeddingStoreIngestor.builder() .embeddingStore(store) .embeddingModel(embeddingModel) .documentSplitter(recursive(500, 0)) .build(); ingestor.ingest(documents); } Loaded document from CSV, Spreadsheet, text.. Ingested documents stored in Redis Ingest documents
26. @ApplicationScoped public class DocumentRetrieverExample implements Retriever<TextSegment> { private final EmbeddingStoreRetriever retriever; DocumentRetrieverExample(RedisEmbeddingStore store, EmbeddingModel model) { retriever = EmbeddingStoreRetriever.from(store, model, 20); } @Override public List<TextSegment> findRelevant(String s) { return retriever.findRelevant(s); } } CDI injection Augmentation interface
27. @RegisterAiService( retrieverSupplier = RegisterAiService.BeanRetrieverSupplier.class ) public interface MyAiService {. } Look for the Retriever bean
28. or… much easier: Easy RAG! quarkus extension add langchain4j-easy-rag quarkus.langchain4j.easy-rag.path=src/main/resources/catalog Path to documents to analyze
29. Local Models ▸ Use models on-prem ▸ Evolve a model privately ▸ Sentiment Analysis of private data
30. Run LLMs locally and build AI applications podman-desktop.io Download now at: Supported platforms: From getting started with AI, to experimenting with models and prompts, Podman AI Lab enables you to bring AI into your applications without depending on infrastructure beyond your laptop. Podman AI Lab
31. Let’s get started! red.ht/jprime24
32. 32 Free Developer e-Books!