OCX / EclipseCon 2024: GitHub Copilot + Spring: Making AI-Assisted Coding Spring Aware

Transcript

1. Jinbo Wang, Senior Software Engineer, Microsoft Martin Lippert, Spring Engineering, Broadcom October 2024 GitHub Copilot + Spring: Making AI-assisted Coding Spring aware Copyright © 2024 Broadcom, Inc. or its affiliates.
2. How can AI assist Java development experience in IDE?
3. The Power of GitHub Copilot Code Completion Explain Fix Generate Docs Generate Tests Chat & Inline Chat
4. Suggest Refactoring: Use AI to plan refactoring
5. Refactor Code in a Specific Pattern - Replace ‘+’, ‘StringBuffer’ to ‘StringBuilder’, ‘Text Block’ - Escape String - Dedup repeated code - Migrate to design patterns (Builder, Singleton, etc.) - Extract long method to smaller ones …
6. Code Migration: Modernize Legacy Code - Text Block for Multiline Strings - Replace Loop with Streams API - Use Enhanced Switch Expressions - Use Pattern Matching for instance of
7. IDE Refactoring vs AI Refactoring ► IDE Refactoring - Rule-based, Predefined - Limited by IDE features - Requires developers to understand when and how to use it ► AI Refactoring - Trained on huge amounts of examples, easy to scale - More creative, can handle more complex refactoring pattern - Suggest refactoring the developer might not have considered
8. Influence the AI assistant (towards making it Spring aware)
9. In general, there are two ways Influence the AI assistant Changing the model itself (e.g. via fine tuning) Feeding additional information when asking (e.g. better prompts/questions, RAG, etc.)
10. The Copilot case in Visual Studio Code
11. Coding with an LLM Type your question
12. Coding with an LLM Type your question Generate a prompt for the LLM
13. Coding with an LLM Type your question Generate a prompt for the LLM Add context information
14. Coding with an LLM Type your question Generate a prompt for the LLM Add context information Send final prompt LLM
15. Coding with an LLM Type your question Generate a prompt for the LLM Add context information Send final prompt LLM Receive Response
16. Coding with an LLM Type your question Generate a prompt for the LLM Add context information Send final prompt LLM Receive Response Show and interpret the response
17. Coding with an LLM Type your question Generate a prompt for the LLM Add context information Send final prompt LLM Receive Response Show and interpret the response Put code snippets from response into your project
18. Coding with an LLM Type your question Generate a prompt for the LLM Add context information Send final prompt LLM Receive Response Show and interpret the response Put code snippets from response into your project
19. How to enhance Copilot?
20. APIs for Copilot There are APIs in place within VSCode to interact with Copilot: - API to submit prompts to the LLM yourself (direct use of Copilot LLM) - API to enhance Copilot Chat (open ended questions) - Enhance / change the prompt - Specify tasks - Fill in variables / placeholders - Enhance / modify the result (e.g. insert buttons) - Inline Chats: no extension API available yet - Side note: APIs are still evolving rapidly, moving target
21. Coding with an LLM Type your question Generate a prompt for the LLM Add context information Send final prompt LLM Receive Response Show and interpret the response Put code snippets from response into your project Predefine the question, no need for the user to type something
22. Coding with an LLM Type your question Generate a prompt for the LLM Add context information Send final prompt LLM Receive Response Show and interpret the response Put code snippets from response into your project Add more context to the prompt, but what exactly?
23. Coding with an LLM Type your question Generate a prompt for the LLM Add context information Send final prompt LLM Receive Response Show and interpret the response Put code snippets from response into your project Show - and maybe enhance the response with additional information / actions
24. Coding with an LLM Type your question Generate a prompt for the LLM Add context information Send final prompt LLM Receive Response Show and interpret the response Put code snippets from response into your project Be smart about where to and how to add code to the project
25. Making it Spring aware
26. Concrete Actions 1
27. Concrete Actions - We identify concrete actions where AI can help and provide a meaningful contribution - We craft the prompt with the necessary input, there is no user interaction - Not open-ended, very limited to a specific case Example: - 👍 Explain SpEL expression - 👍 Explain SQL/HQL/JPQL Query - 👍 Explain Pointcut expression - 🤔 CRON: eh, AI is too much for that, simple logic is enough
28. Latest Spring Tools release
29. Full Chat Agent 3
30. Chat Agent - Enhance the prompt (with random information) - Fully open-ended / chat experience - Enhancing the result (buttons + better code merge) - The more structure you ask for, the better you can interpret / merge the result
31. The Spring agent in action
32. The Spring agent in action
33. The Spring agent in action
34. The Spring agent in action
35. Challenges
36. LLM is changing behind the scenes 1
37. New Language or Framework Versions 2
38. Size limitations 3
39. Is it getting better or worse? 4
40. Questions
41. Thank you @https://github.com/testforstephen @martinlippert https://www.linkedin.com/in/martin-lippert-9a1909/ © 2024 Broadcom