Generative AI in practice: Concrete LLM use cases in Java, with the PaLM and Gemini APIs

Large language models (LLMs) are a powerful new technology that can be used for a variety of tasks, including generating text, translating languages, and writing different kinds of creative content. However, LLMs can be difficult to use, especially for developers who are not proficient in Python, the lingua franca for AI. So what about us Java developers? How can we make use of Generative AI?

This presentation will go through how to use LLMs in Java without the need for Python. We will use the PaLM and Gemini API, provided by Google Cloud’s Vertex AI services, to perform a variety of tasks, such as searching through documentation, generating kids stories, summarizing content, extracting keywords or entities, and more. In our journey through demos, we’ll discover LangChain4J, a wonderful LLM orchestrator for Java developers that simplifies the implementation of advanced LLM use cases.

Transcript

1. Generative AI in practice: Concrete LLM use cases in Java with PaLM & Gemini Guillaume Laforge Developer Advocate @glaforge@uwyn.net
2. Google Cloud Proprietary & Confidential 01 A few notions and vocabulary 2 @glaforge@uwyn.net
3. Google Cloud Artificial Intelligence NLP 3 Artificial Intelligence, Machine Learning, Data Science, Deep Learning… Data Science Machine Learning — unsupervised, supervised, reinforcement learning Deep Learning — ANN, CNN, RNN… Generative AI — GAN, VAE, Transformers… LLMs — Transformers Image Gen — GAN, VAE
4. Google Cloud 4 Google invented the Transformer architecture Responsible AI at the foundation Google invents Transformer kickstarting LLM revolution Google’s groundbreaking large language model, BERT AlphaFold predicts 3D models of protein structures Text-to-Text Transfer Transformer LLM 10B P model open sourced Google LaMDA model trained to converse Google PaLM single model to generalize across domains Google PaLM 2 model is the SOTA LLM PaLM 2
5. https://ig.ft.com/generative-ai/
6. Google Cloud 6 So what are Large Language Models? • Transformer-based neural network architecture that can recognize, predict, and generate human language • Trained on huge corpuses of text, in various languages and domains ◦ Ex: PaLM 2 learned 340 billion parameters, and trained over 3.6 trillions of tokens • Learn the statistical relationships between words and phrases, as well as the patterns of human language • Can be fine-tuned for specific tasks or domain knowledge
7. Google Cloud 7 Language model sizes — March 2023 https://lifearchitect.ai/models/
8. Google Cloud 8 With larger models emerge new capabilities https://blog.research.google/2022/04/pathways-language-model-palm-scaling-to.html
9. Google Cloud Proprietary & Confidential 9 02 What does Google (Cloud) offers? @glaforge@uwyn.net
10. Google Cloud Bard 10 PaLM, Codey, Imagen, MakerSuite, Vertex AI Vertex AI MakerSuite Model Garden Codey Imagen Llama 2, Claude 2, Falcon, Vicuna, Stable Diffusion … Search & Conversation Vector Search Notebooks Pipelines AutoML PaLM Gemini … Vision, Video, TTS / STT, NL APIs
11. Google Cloud 11 What is Gemini? • Gemini is Google Deep Mind’s most capable AI model • It’s a multimodal large language model: text, images, videos • Comes in 3 sizes: Nano, Pro, and Ultra • Supports function calling • Ranks at the top of the various LLM benchmarks (general knowledge, translation, image understanding, reasoning, math, coding, and more…) • Will be integrated into Bard soon
12. Google Cloud Proprietary & Confidential 12 03 Time to have a look at some demos! @glaforge@uwyn.net
13. Google Cloud 13 Let’s play with Bard and MakerSuite! Bard PaLM MakerSuite
19. Google Cloud 19 Python is all the rage in AI… What’s in it for us, Java developers?
20. Google Cloud 20 Generating bedtime stories for kids https://bed-time-stories.web.app/
22. Google Cloud 22 Vertex AI Java API
23. Google Cloud 23 LangChain4J
24. Google Cloud 24 Searching the Apache Groovy documentation Apply the RAG pattern: Retrieval Augmented Generation
25. LLM Vector DB embedding vectors chunks DOCS calculate split store vector + chunk ❶ INGESTION
26. LLM Vector DB embedding vectors chunks DOCS calculate prompt embedding vector split calculate find similar answer context + prompt + chunks store vector + chunk ❶ INGESTION ❷ QUERYING
28. Google Cloud Proprietary & Confidential 28 04 Summary @glaforge@uwyn.net
29. Google Cloud 29 Summary • PaLM 2 & Gemini are powerful LLM that allow you to build all sorts of generative AI ideas and projects • Using the PaLM API from Java is not necessarily ideal, but with REST or LangChain4j, it’s easy • Fortunately, Gemini has a much better SDK! (and is also supported in LangChain4j) • Easy to deploy & serve containerized apps on Cloud Run • And LangChain4J is pretty sweet!
30. Google Cloud 30 More about LangChain4J youtube.com/watch?v=BD1MSLbs9KE
31. Google Cloud 31 What to build next? • Chat Q&A with the Apache Groovy documentation ◦ improve the quality of responses • News curation that collects & summarize my social feeds What about you, what would you build?
32. Google Cloud 32 Going further Guillaume Laforge Developer Advocate Learn more about Generative AI at goo.gle/generativeai @glaforge@uwyn.net
33. Thanks! Guillaume Laforge Developer Advocate @glaforge@uwyn.net