Devoxx BE 24 - Deep Dive LangChain4J and Quarkus LangChain4J

Transcript

1. LangChain4j Deep Dive Georgios Andrianakis, Principal Software Engineer, Red Hat Eric Deandrea, Java Champion & Dev Advocate, Red Hat Clement Escoffier, Java Champion & Distinguished Engineer, Red Hat
2. What are we going to see? How to build AI-Infused applications in Java - Some examples - Main concepts - Chat Models - Ai Services - Memory management - RAG - Function calling - Guardrails - Image models - The almost-all-in-one demo - Plain LangChain4j & Quarkus - Remote model (Open AI) & Local models (Ollama, Podman AI Studio)
3. Some examples of AI-Infused applications
4. Some examples Summarizer Chatbot Text Extraction from Image
5. AI-Infused applications
6. What are Large Language Models (LLMs)? Neural Networks • Transformer based • Recognize, Predict, and Generate text • Trained on a VERY large corpuses of text • Deduce the statistical relationships between tokens • Can be fine-tuned A LLM predicts the next token based on its training data and statistical deduction
7. The L of LLM means Large LLama 3: - 70B parameters - Trained on 15000B of tokens - 4.7Gb on disk Granite: - 34B parameters - Trained on 3500B of tokens - 3.8 Gb of RAM, 4.8Gb on disk More on: An idea of the size
8. More parameters means more capabilities https://research.google/blog/pathways-language-model-palm-scaling-to-540-billion-parameters-for-breakthrough-performance/
9. Model and Model Serving Model Model Serving - Run the model - CPU / GPU - Expose an API - REST - gRPC - May support multiple models
10. Prompt and Prompt Engineering Model Input (Prompt) Output Input: - Prompt (text) - Instructions to give to the model - Taming a model is hard Output: - Depends on the modality of the model
11. Application Model AI-infused application |ˌeɪˌaɪ ˈɪnˌfjuːzd ˌæplɪˈkeɪʃən| noun (Plural AI-Infused applications) A software program enhanced with artificial intelligence capabilities, utilizing AI models to implement intelligent features and functionalities.
12. Using models to build apps on top Dev Ops Release Deploy Operate Monitor Plan Code Build Test Train Evaluate Deploy Collect Evaluate Curate Analyze Data ML APIs
13. Using models to build apps on top Dev Ops Release Deploy Operate Monitor Plan Code Build Test Train Evaluate Deploy Collect Evaluate Curate Analyze Data ML Need some clients and toolkits
14. LangChain (Python, JS) LangChain Chains Agents Prompts Vector Stores Models Document Loaders
15. LangChain4j LangChain4j Chains Agents Prompts Vector Stores Models Document Loaders
16. LangChain4j https://github.com/langchain4j/langchain4j • Toolkit to build AI-Infused Java applications ◦ Provides integration with many LLM/SML providers ◦ Provides building blocks for the most common patterns (RAG, Function calling…) ◦ Abstractions to manipulate prompts, messages, memory, tokens… ◦ Integrate a large variety of vector stores and document loaders
17. LangChain / LangChain4j / Quarkus LangChain4j LangChain LangChain4j Quarkus LangChain4j Inspired By Uses and extends
18. LangChain4j https://github.com/langchain4j/langchain4j AI Service Loaders Splitters Vector Store Embedding Models Language Models Image Models Prompt Function calling Memory Output Parsers Building blocks RAG
19. Quarkus LangChain4j https://docs.quarkiverse.io/quarkus-langchain4j LangChain4j Quarkus LangChain4j Application LLMs Vector stores Embedding Models - Declarative clients - CDI integration - Observability (Otel, Prometheus) - Auditing - Resilience - RAG building blocks - Tool support - Mockable
20. Bootstrapping LangChain4j <dependency> <groupId>dev.langchain4j</ groupId> <artifactId>langchain4j</ artifactId> </dependency> <dependency> <groupId>dev.langchain4j</ groupId> <artifactId>langchain4j-open-ai</ artifactId> </dependency> <dependency> <groupId>io.quarkiverse.langchain4j</ groupId> <artifactId>quarkus-langchain4j-openai</ artifactId> </dependency> Quarkus LangChain4j
21. The basics - Chat Models
22. Chat Models • Text to Text ◦ Text in -> Text out ◦ NLP • Prompt ◦ Set of instructions explaining what the model must generate ◦ Use plain English (or other language) ◦ There are advanced prompting technique ▪ Prompt depends on the model ▪ Prompt engineering is an art ChatLanguageModel modelA = OpenAiChatModel.withApiKey(System.getenv("...")); String answerA = modelA.generate("Say Hello World"); @Inject ChatLanguageModel model; String answer = model.generate("Say Hello"); LangChain4j Quarkus LangChain4j - Chat Model Quarkus LangChain4j - AI Service @RegisterAiService interface PromptA { String ask(String prompt); } @Inject PromptA prompt; String answer = prompt.ask("Say Hello");
23. Messages Application Role=User (prompt) Role=Assistant (response) LLM
24. Messages Application Role=User Role=Assistant (response) Role=System LLM Define the Context and scope (higher priority)
25. var system = new SystemMessage( "You are Georgios, all your answers should be using the Java language using greek letters "); var user = new UserMessage("Say Hello World" ); var response = model.generate(system, user); // Pass a list of messages System.out.println( "Answer: " + response.content().text()); Messages Context or Memory
26. Memory, well, the absence of memory Application LLM (stateless)
27. Manual Memory List<ChatMessage> memory = new ArrayList<>(); memory.addAll(List.of( new SystemMessage( "You are a useful AI assistant." ), new UserMessage("Hello, my name is Clement." ), new UserMessage("What is my name?" ) )); var response = model.generate( memory); System.out.println( "Answer 1: " + response.content().text()); memory.add(response.content()); memory.add(new UserMessage("What's my name again?" )); response = model.generate( memory); System.out.println( "Answer 2: " + response.content().text()); var m = new UserMessage("What's my name again?" ); response = model.generate(m); // No memory System.out.println( "Answer 3: " + response.content().text());
28. Messages and Memory Application LLM (stateless) Size limit
29. Messages and Memory Model Context Output Message Models are stateless - Pass a set of messages named context - These messages are stored in a memory - Context size is limited (eviction strategy) Context = (Stored input messages + Output messages) + New input
30. Chat Memory var memory = MessageWindowChatMemory .builder() .id("user-id") .maxMessages( 3) // Only 3 messages will be stored .build(); memory.add(new SystemMessage( "You are a useful AI assistant." )); memory.add(new UserMessage("Hello, my name is Clement and I live in Valence, France" )); memory.add(new UserMessage("What is my name?" )); var response = model.generate(memory.messages()); System.out.println("Answer: " + response.content().text());
31. Context Limit & Pricing Number of tokens - Depends on the model and model serving (provider) - Tokens are not words Context size is not in terms of messages, but in number of tokens This_talk_is_really_ boring._Hopefully,_it_will _be_over_soon. [2500, 838, 2082, 15224, 3067, 2146, 1535, 7443, 2697, 127345, 46431, 278, 3567, 492, 40729, 34788, 62, 84908, 13] https://platform.openai.com/tokenizer
32. Token Usage var memory = MessageWindowChatMemory .builder() .id("user-id") .maxMessages( 3) // Only 3 messages will be stored .build(); memory.add(new SystemMessage( "You are a useful AI assistant." )); memory.add(new UserMessage("Hello, my name is Clement and I live in Valence, France" )); memory.add(new UserMessage("What is my name?" )); var response = model.generate(memory.messages()); System.out.println("Answer 1: " + response.content().text()); System.out.println("Input token: " + response.tokenUsage().inputTokenCount()); System.out.println("Output token: " + response.tokenUsage().outputTokenCount()); System.out.println("Total token: " + response.tokenUsage().totalTokenCount());
33. AI Services
34. LangChain4j AI Services Map LLM interaction to Java interfaces - Declarative model - You define the API the rest of the code uses - Mapping of the output - Parameterized prompt - Abstract/Integrate some of the concepts we have seen public int run() { Assistant assistant = AiServices.create(Assistant.class, model); System.out.println( assistant.answer("Say Hello World") ); return 0; } // Represent the interaction with the LLM interface Assistant { String answer(String question); }
35. LangChain4j AI Services - System Message - @SystemMessage annotation - Or System message provider public int run() { Assistant assistant = AiServices.create(Assistant.class, model); System.out.println( assistant.answer("Say Hello World") ); return 0; } interface Assistant { @SystemMessage("You are a Shakespeare, all your response must be in iambic pentameter.") String answer(String question); } var rapper = AiServices.builder(Friend.class) .chatLanguageModel( model) .systemMessageProvider( chatMemoryId -> "Your a west coast rapper, all your response must be in rhymes." ) .build();
36. LangChain4j AI Services - User Message and Parameters public int run() { Poet poet = AiServices.create(Poet.class, model); System.out.println(poet.answer("Devoxx")); return 0; } interface Poet { @SystemMessage ("You are Shakespeare, all your response must be in iambic pentameter." ) @UserMessage("Write a poem about {{topic}}. It should not be more than 5 lines long." ) String answer(@V("topic") String topic); }
37. LangChain4j AI Services - Structured Output AI Service methods are not limited to returning String - Primitive types - Enum - JSON Mapping TriageService triageService = … System.out.println(triageService.triage( "It was a great experience!" )); System.out.println(triageService.triage( "It was a terrible experience!" )); // … enum Sentiment { POSITIVE, NEGATIVE,} record Feedback(Sentiment sentiment, String summary) {} interface TriageService { @SystemMessage("You are an AI that need to triage user feedback." ) @UserMessage(""" Analyze the given feedback, and determine i it is positive, or negative. Then, provide a summary of the feedback: {{feedback}} """) Feedback triage(@V("feedback") String feedback); }
38. LangChain4j AI Services - Chat Memory - You can plug a ChatMemory to an AI service to automatically add and evict messages var memory = MessageWindowChatMemory .builder() .id( "user-id") .maxMessages( 3) .build(); var assistant = AiServices.builder(Assistant.class) .chatLanguageModel( model) .chatMemory( memory) .build();
39. Quarkus AI Services
40. What’s the difference between these? Application Database Application Service CRUD application Microservice Application Model AI-Infused application
41. What’s the difference between these? Application Database Application Service CRUD application Microservice Application Model AI-Infused application Integration Points
42. What’s the difference between these? Application Database Application Service CRUD application Microservice Application Model AI-Infused application Integration Points Observability (metrics, tracing, auditing) Fault-Tolerance (timeout, circuit-breaker, non-blocking, fallbacks…)
43. Quarkus AI Services Application Component AI Service - Define the API (Interface) - Configure the prompt for each method - Configure the tools, memory… Chat Model Tools Memory Retriever Audit Moderation Model (RAG) (Observability) (Agent) Inject and invoke (Manage the context using CDI scopes)
44. Quarkus AI Services Map LLM interaction to Java interfaces - Based on LangChain4j AI Service - Made CDI aware - Injectable - Scope - Dev UI, Templating… - Metrics, Audit, Tracing… @Inject Assistant assistant; @ActivateRequestContext public int run() { println(assistant.answer("My name is Clement, can you say \"Hello World\" in Greek?")); println(assistant.answer( "What's my name?")); return 0; } @RegisterAiService interface Assistant { String answer(String question); } Injectable bean, Request scope by default
45. Quarkus AI Services - Scopes and memory Request scope by default - Overridable - Keep messages for the duration of the scope - Request - the request only - Application - the lifetime of the application - Because it’s risky, you need a memory id - Session - the lifetime of the websocket session @RegisterAiService @RequestScoped interface ShortMemoryAssistant { String answer(String question); } @RegisterAiService @ApplicationScoped interface LongMemoryAssistant { String answer(@MemoryId int id, @UserMessage String question); } @RegisterAiService @SessionScoped interface ConversationalMemoryAssistant { String answer(String question); }
46. Quarkus AI Services - Custom Memory Memory Provider - You can implement a custom memory provider - Can implement persistence - Conversation represented by MemoryId - For session - it’s the WS session ID. @ApplicationScoped public class MyMemoryStore implements ChatMemoryStore { public List<ChatMessage> getMessages( Object memoryId) { // … } public void updateMessages(Object memoryId, List<ChatMessage> messages) // … } public void deleteMessages( Object memoryId){ // … } }
47. Quarkus AI Services - Parameter and Structured Output Prompt can be parameterized - Use Qute template engine - Can contain logic Structured output - Based on Jackson @UserMessage(""" What are the {number}th last teams in which {player} played? Only return the team names. """) List<String> ask(int number, String player); @UserMessage(""" What are the last team in which {question.player} played? Return the team and the last season. """) Entry ask(MyHttpEndpoint.Question question); record Entry(String team, String years) {} Single {}
48. Quarkus AI Services - Complex templating @SystemMessage(""" Given the following conversation and a follow-up question, rephrase the follow-up question to be a standalone question. Context: {#for m in chatMessages} {#if m.type.name() == "USER"} User: {m.text()} {/if} {#if m.type.name() == "AI"} Assistant: {m.text()} {/if} {/for} """) public String rephrase(List<ChatMessage> chatMessages, @UserMessage String question);
49. Quarkus AI Services Application Component AI Service Quarkus Extended with Quarkus capabilities (REST client, Metrics, Tracing…)
50. Quarkus AI Services - Observability Collect metrics - Exposed as Prometheus OpenTelemetry Tracing - Trace interactions with the LLM <dependency> <groupId>io.quarkus</groupId> <artifactId> quarkus-opentelemetry </artifactId> </dependency> <dependency> <groupId>io.quarkus</groupId> <artifactId> quarkus-micrometer-registry-prometheus </artifactId> </dependency>
51. Quarkus AI Services - Tracing
52. Quarkus AI Services - Tracing
53. Quarkus AI Services - Auditing Audit Service - Allow keeping track of interactions with the LLM - Can be persisted - Implemented by the application code @Override public void initialMessages( Optional<SystemMessage> systemMessage, UserMessage userMessage ) { } @Override public void addLLMToApplicationMessage ( Response<AiMessage> response) {} @Override public void onFailure(Exception e) {} @Override public void onCompletion(Object result) {}
54. Quarkus AI Services - Fault Tolerance Retry / Timeout / Fallback / Circuit Breaker / Rate Limiting… - Protect against error - Graceful recovery There are other resilience patterns (guardrails) @UserMessage("…") @Retry(maxRetries = 2) @Timeout(value = 1, unit = MINUTES) @Fallback(fallbackMethod = "fallback") Entry ask(Question question); default Entry fallback(Question question) { return new Entry("Unknown", "Unknown"); } <dependency> <groupId>io.quarkus</groupId> <artifactId> quarkus-smallrye-fault-tolerance </artifactId> </dependency>
55. RAG
56. Retrieval Augmented Generation (RAG) Enhance LLM knowledge by providing relevant information in real-time from other sources – Dynamic data that changes frequently Fine-tuning is expensive! 2 stages Indexing / Ingestion Retrieval / Augmentation
57. Indexing / Ingestion
58. Indexing / Ingestion FileSystemDocumentLoader UrlDocumentLoader AmazonS3DocumentLoader AzureBlobStorageDocumentLoader GitHubDocumentLoader TencentCosDocumentLoader
59. Indexing / Ingestion TextDocumentParser ApachePdfBoxDocumentParser ApachePoiDocumentParser ApacheTikaDocumentParser
60. Indexing / Ingestion What do I need to think about? What is the representation of the data? How do I want to split? Per document? Chapter? Sentence? How many tokens do I want to end up with?
61. Indexing / Ingestion DocumentByParagraphSplitter DocumentByLineSplitter DocumentBySentenceSplitter DocumentByWordSplitter DocumentByCharacterSplitter DocumentByRegexSplitter DocumentSplitters.recursive()
62. Indexing / Ingestion Compute an embedding (numerical vector) representing semantic meaning of each segment. Requires an embedding model In-process/Onnx, Amazon Bedrock, Azure OpenAI, Cohere, DashScope, Google Vertex AI, Hugging Face, Jine, Jlama, LocalAI, Mistral, Nomic, Ollama, OpenAI, OVHcloud, Voyage AI, Cloudfare Workers AI, Zhipu AI
63. Store embedding alone or together with segment. Requires a vector store In-memory, Chroma, Elasticsearch, Milvus, Neo4j, OpenSearch, Pinecone, PGVector, Redis, Vespa, Weaviate, Qdrant Indexing / Ingestion
65. Indexing / Ingestion var ingestor = EmbeddingStoreIngestor.builder() .embeddingModel(embeddingModel) .embeddingStore(embeddingStore) // Add userId metadata entry to each Document to be able to filter by it later .documentTransformer(document -> { document.metadata().put("userId", "12345"); return document; }) // Split each Document into TextSegments of 1000 tokens each with a 200-token overlap .documentSplitter(DocumentSplitters.recursive(1000, 200)) // Add the name of the Document to each TextSegment to improve the quality of search .textSegmentTransformer(textSegment -> TextSegment.from( textSegment.metadata().getString("file_name") + "\n" + textSegment.text(), textSegment.metadata() ) ) .build(); // Get the path of where the documents are and load them recursively Path path = Path.of(...); List<Document> documents = FileSystemDocumentLoader.loadDocumentsRecursively(path); // Ingest the documents into the embedding store ingestor.ingest(documents);
67. Retrieval / Augmentation
68. Retrieval / Augmentation Compute an embedding (numerical vector) representing semantic meaning of the query. Requires an embedding model.
69. Retrieval / Augmentation Retrieve & rank relevant content based on cosine similarity or other similarity/distance measures.
70. Retrieval / Augmentation Augment input to the LLM with related content. What do I need to think about? Will I exceed the max number of tokens? How much chat memory is available?
71. Retrieval / Augmentation public class RagRetriever { @Produces @ApplicationScoped public RetrievalAugmentor create(EmbeddingStore store, EmbeddingModel model) { var contentRetriever = EmbeddingStoreContentRetriever. builder() .embeddingModel(model) .embeddingStore(store) .maxResults( 3) .minScore( 0.75) .filter( metadataKey("userId").isEqualTo("12345")) .build(); return DefaultRetrievalAugmentor. builder() .contentRetriever(contentRetriever) .build(); } }
72. Advanced RAG
73. public class RagRetriever { @Produces @ApplicationScoped public RetrievalAugmentor create(EmbeddingStore store, EmbeddingModel model) { var embeddingStoreRetriever = EmbeddingStoreContentRetriever.builder() .embeddingModel(model) .embeddingStore(store) .maxResults(3) .minScore(0.75) .filter(metadataKey("userId").isEqualTo("12345")) .build(); var googleSearchEngine = GoogleCustomWebSearchEngine.builder() .apiKey(System.getenv("GOOGLE_API_KEY")) .csi(System.getenv("GOOGLE_SEARCH_ENGINE_ID")) .build(); var webSearchRetriever = WebSearchContentRetriever.builder() .webSearchEngine(googleSearchEngine) .maxResults(3) .build(); return DefaultRetrievalAugmentor.builder() .queryRouter(new DefaultQueryRouter(embeddingStoreRetriever, webSearchRetriever)) .build(); } } Advanced RAG https://github.com/cescoffier/langchain4j-deep-dive/blob/main/4-rag/src/main/java/dev/langchain4j/quarkus/deepdive/RagRetriever.java
74. public class RagRetriever { @Produces @ApplicationScoped public RetrievalAugmentor create(EmbeddingStore store, EmbeddingModel model, ChatLanguageModel chatModel) { var embeddingStoreRetriever = ... var webSearchRetriever = ... var queryRouter = LanguageModelQueryRouter.builder() .chatLanguageModel(chatModel) .fallbackStrategy(FallbackStrategy.ROUTE_TO_ALL) .retrieverToDescription( Map.of( embeddingStoreContentRetriever, “Local Documents”, webSearchContentRetriever, “Web Search” ) ) .build(); return DefaultRetrievalAugmentor.builder() .queryRouter(queryRouter) .build(); } } Advanced RAG https://github.com/cescoffier/langchain4j-deep-dive/blob/main/4-rag/src/main/java/dev/langchain4j/quarkus/deepdive/RagRetriever.java
76. application.properties quarkus.langchain4j.easy-rag.path=path/to/files quarkus.langchain4j.easy-rag.max-segment-size=1000 quarkus.langchain4j.easy-rag.max-overlap-size=200 quarkus.langchain4j.easy-rag.max-results=3 quarkus.langchain4j.easy-rag.ingestion-strategy=on|off quarkus.langchain4j.easy-rag.reuse-embeddings=true|false pom.xml <dependency> <groupId>io.quarkiverse.langchain4j</groupId> <artifactId>quarkus-langchain4j-easy-rag</artifactId> <version>${quarkus-langchain4j.version}</version> </dependency> <!-- Need an extension providing an embedding model --> <dependency> <groupId>io.quarkiverse.langchain4j</groupId> <artifactId>quarkus-langchain4j-openai</artifactId> <version>${quarkus-langchain4j.version}</version> </dependency> <!-- Also need an extension providing a vector store --> <!-- Otherwise an in-memory store is provided automatically --> <dependency> <groupId>io.quarkiverse.langchain4j</groupId> <artifactId>quarkus-langchain4j-pgvector</artifactId> <version>${quarkus-langchain4j.version}</version> </dependency> Easy RAG!
77. Function Calling, Agents and Tools
78. Agent and Tools A tool is a function that the model can call: - Tools are parts of CDI beans - Tools are defined and described using the @Tool Prompt (Context) Extend the context with tool descriptions Invoke the model The model asks for a tool invocation (name + parameters) The tool is invoked (on the caller) and the result sent to the model The model computes the response using the tool result Response
79. <~~ My prompt <~~ Tool invocation request <~~ Tool invocation response <~~ Model Response
80. Tools - A tool is just a method - It can access databases, or invoke a remote service - It can also use another LLM Tools require memory Application
81. Using tools with LangChain4j Assistant assistant = AiServices.builder(Assistant.class) .chatLanguageModel( model) .tools(new Calculator()) .chatMemory( MessageWindowChatMemory .withMaxMessages(10)) .build(); static class Calculator { @Tool("Calculates the length of a string") int stringLength(String s) { return s.length(); } @Tool("Calculates the square root of a number" ) double sqrt(int x) { System.out.println("Called sqrt() with x=" + x); return Math.sqrt(x); } } Objects to use as tools Declare an tool method (description optional)
82. Using tools with Quarkus LangChain4j @RegisterAiService interface Assistant { @ToolBox(Calculator.class) String chat(String userMessage ); } @ApplicationScoped static class Calculator { @Tool("Calculates the length of a string" ) int stringLength(String s) { return s.length(); } } Class of the bean declaring tools Declare an tool method (description optional) Must be a bean (singleton and dependant supported) Tools can be listed in the `tools` attribute
83. Giving access to database (Quarkus Panache) @ApplicationScoped public class BookingRepository implements PanacheRepository<Booking> { @Tool("Cancel a booking" ) @Transactional public void cancelBooking(long bookingId, String customerFirstName , String customerLastName ) { var booking = getBookingDetails( bookingId, customerFirstName, customerLastName); delete(booking); } @Tool("List booking for a customer" ) public List<Booking> listBookingsForCustomer (String customerName , String customerSurname ) { var found = Customer.find("firstName = ?1 and lastName = ?2", customerName, customerSurname).singleResultOptional(); return list("customer", found.get()); } }
84. Function Calling - Tracing
85. Function Calling - Tracing
86. Web Search Tools (Tavily) @UserMessage(""" Search for information about the user query: {query}, and answer the question. """) @ToolBox(WebSearchTool.class) String chat(String query); Provided by quarkus-langchain4j-tavily Can also be used with RAG
87. Risks • Things can go wrong quickly • Risk of prompt injection ◦ Access can be protected in Quarkus • Audit is very important to check the parameters • Distinction between read and write beans Application
88. Guardrails
89. https://www.upworthy.com/prankster-tricks-a-gm-dealership-chatbot-to-sell-him-a-76000-chevy-tahoe-for-1-rp3 https://www.cbsnews.com/news/aircanada-chatbot-discount-customer https://www.bbc.com/news/technology-35902104 https://www.spiceworks.com/tech/artificial-intelligence/news/meta-blender-bot-3-controversy
90. Guardrails - Functions used to validate the input and output of the model - Detect invalid input - Detect prompt injection - Detect hallucination - Chain of guardrails - Sequential - Stop at first failure Quarkus LangChain4j only (for now)
91. Retry and Reprompt Output guardrails can have 4 different outcomes: - Success - the response is passed to the caller or next guardrail - Fatal - we stop and throw an exception - Retry - we call the model again with the same context (we never know ;-) - Reprompt - we call the model again with another message in the model indicating how to fix the response
92. Implement an input guardrail @ApplicationScoped public class UppercaseInputGuardrail implements InputGuardrail { @Override public InputGuardrailResult validate(UserMessage userMessage ) { var message = userMessage.singleText(); var isAllUppercase = message.chars().filter(Character::isLetter) .allMatch( Character::isUpperCase); if (isAllUppercase) { return success(); } else { return failure("The input must be in uppercase." ); } } } CDI beans Interface to implement Can also access the chat memory and the augmentation results OK Failure
93. Implement an output guardrail @ApplicationScoped public class UppercaseOutputGuardrail implements OutputGuardrail { @Override public OutputGuardrailResult validate(OutputGuardrailParams params ) { System.out.println("response is: " + params.responseFromLLM().text() + " / " + params.responseFromLLM().text().toUpperCase()); var message = params.responseFromLLM().text(); var isAllUppercase = message.chars().filter(Character::isLetter).allMatch(Character::isUpperCase); if (isAllUppercase) { return success(); } else { return reprompt("The output must be in uppercase." , "Please provide the output in uppercase." ); } } CDI beans Interface to implement Can also access the chat memory and the augmentation results OK Reprompt
94. Declaring guardrails @RegisterAiService public interface Assistant { @InputGuardrails(UppercaseInputGuardrail .class) @OutputGuardrails(UppercaseOutputGuardrail .class) String chat(String userMessage ); } Both can receive multiple values
95. Images
96. Process or Generate images Image Model - Image Models are specialized for … Images - Can generate images from text - Can process images from input (like the OCR demo) - Chat Model: GPT4-o | Image Model: Dall-e - Important: Not every model serving provider provides image support (as it needs specialized models)
97. Using Image Model to generate pictures @Inject ImageModel model; @Override public int run(String... args) throws IOException { var prompt = "Generate a picture of a rabbit software developers coming to Devoxx" ; var response = model.generate(prompt); System.out.println(response.content().url()); return 0; } Image Model (can also be created with a builder) Response<Image> quarkus.langchain4j.openai.timeout =1m quarkus.langchain4j.openai.image-model.size =1024x1024 quarkus.langchain4j.openai.image-model.quality =standard quarkus.langchain4j.openai.image-model.style =vivid quarkus.langchain4j.openai.image-model.persist =true Print the persisted image
98. Generating images from AI Services @RegisterAiService @ApplicationScoped public interface ImageGenerator { Image generate(String userMessage ); } Indicate to use the image model to generate the picture var prompt = "Generate a picture of a rabbit going to Devoxx. The rabbit should be wearing a Quarkus tee-shirt." ; var response = generator.generate(prompt); var file = new File("rabbit-at-devoxx.jpg" ); Files.copy(response.url().toURL().openStream(), file.toPath(), StandardCopyOption.REPLACE_EXISTING);
99. Processing picture from AI Services @RegisterAiService @ApplicationScoped public interface ImageDescriber { @UserMessage(""" Describe the given message. """) String describe(Image image); } Indicate to the model to use the image
100. The almost-all-in-one demo
101. The almost-all-in-one demo - React - Quarkus WebSockets.NEXT - Quarkus Quinoa - Ollama - RAG - Ingest data from filesystem - Tools - Update database - Send email - Observability - OpenTelemetry
102. Conclusion
103. What did we see? How to Build AI-Infused applications in Java https://docs.quarkiverse.io/ quarkus-langchain4j https://docs.langchain4j.dev Code Slides Langchain4J Quarkus Chat Models RAG PROMPT MESSAGES AI SERVICE MEMORY CONTEXT TOOLS FUNCTION CALLING GUARDRAILS IMAGE MODELS OBSERVABILITY audit TRACING agent
105. Other Quarkus & LangChain4j sessions • Developing Cloud-Native Java AI applications with DJL and LangChain4j - Monday, 09:30, Room 9 • Project Leyden & Quarkus - Monday, 12:35, Room 6 • Squeezing Performance out of Quarkus - Monday, 16:50, BOF 2 • jbang - Unleash the power of Java - Monday, 18:20, Room 8 • Java meets AI: Build LLM-Powered Apps with LangChain4j - Tuesday, 09:30, Room 9 • Create AI-Infused Apps with LangChain4j: Insights from the Quarkus Developers - Tuesday, 13:30, BOF 1 • Crafting intelligent GitHub Bots - Wednesday, 12:00, Room 4 • Pushing LLMs over the Edge: Exploring the Limits of the Possible - Wednesday, 16:40, Room 6 • Quarkus Community BOF - Wednesday, 19:00, BOF 2 • Panel Discussion: LangChain4j, a year later. - Thursday, 11:50, Room 10 • Crafting Intelligent Applications with Quarkus/LangChain4j - Thursday, 12:50, Room 5 • Introduction to Quarkus Security - Thursday, 15:00, Room 9 • Zero Waste, Radical Magic, and Italian Graft – Quarkus Efficiency Secrets - Thursday, 17:40, Room 6
106. Other Quarkus & LangChain4j sessions • Developing Cloud-Native Java AI applications with DJL and LangChain4j - Monday, 09:30, Room 9 • Project Leyden & Quarkus - Monday, 12:35, Room 6 • Squeezing Performance out of Quarkus - Monday, 16:50, BOF 2 • jbang - Unleash the power of Java - Monday, 18:20, Room 8 • Java meets AI: Build LLM-Powered Apps with LangChain4j - Tuesday, 09:30, Room 9 • Create AI-Infused Apps with LangChain4j: Insights from the Quarkus Developers - Tuesday, 13:30, BOF 1 • Crafting intelligent GitHub Bots - Wednesday, 12:00, Room 4 • Pushing LLMs over the Edge: Exploring the Limits of the Possible - Wednesday, 16:40, Room 6 • Quarkus Community BOF - Wednesday, 19:00, BOF 2 • Panel Discussion: LangChain4j, a year later. - Thursday, 11:50, Room 10 • Crafting Intelligent Applications with Quarkus/LangChain4j - Thursday, 12:50, Room 5 • Introduction to Quarkus Security - Thursday, 15:00, Room 9 • Zero Waste, Radical Magic, and Italian Graft – Quarkus Efficiency Secrets - Thursday, 17:40, Room 6