Using_Hono_in__B2B_SaaS_Application.pdf

Transcript

1. Using Hono in B2B SaaS Application Hono Conference 2024 - Our first step
2. Agenda 1. Self Introduction 2. Basics of Hono 3. UseCases in AI Worker 4. Conclusion
3. Self Introduction sugar cat Cyber Agent/AIShift Backend Engineer Interests: Web Performance, Security @sugar235711
4. Product Introduction • AI Worker ◦ A platform for business improvement utilizing generative AI
5. AI Worker Tech Stack
6. AI Worker Tech Stack
7. Basics of Hono
8. What is Hono • Fast, lightweight, built on Web Standards ◦ Runtime Compatibility: Node, Deno, Bun, Workers Key Features: • Built-in Middleware: A wide range of middleware is included by default, ensuring smooth development. • Simple and Intuitive API: Designed with a clear and easy-to-understand API, allowing for rapid development.
9. Example: Simple API
10. Example: Simple API Generate a Hono instance and define API endpoints based on it.
11. Example: Simple API You can insert any middleware before executing endpoints.
12. Example: Simple API The Context object can manipulate headers, request bodies, and response bodies.
13. Example: Handling Context
14. Example: Handling Context With generics, you can bind any variables or functions to the Context object.
15. Example: Handling Context Use context getters and setters to handle and propagate bindings between methods.
16. Example: Integration with Zod OpenAPI
17. Example: Integration with Zod OpenAPI Create request and response schemas with Zod and register them to a route.
18. Example: Integration with Zod OpenAPI By combining this with @hono/zod-openapi, requests are automatically validated.
19. Example: Integration with Zod OpenAPI Combine with Swagger middleware to auto-generate a UI.
20. Use Cases in AI Worker
21. Keyword • AI • B2B (Multi-tenant)
22. AI
23. Recent Trends in AI • Utilization of LLM ◦ GPT, Claude…
24. Using Streaming SSE for Real-time Response • Expressing that responses are gradually returned in an interactive AI UI.
25. Example: SSE with Hono Helper + GPT
26. Example: SSE with Hono Helper + GPT streamSSE: A helper to handle responses as SSE (Server-Sent Events)
27. Example: SSE with Hono Helper + GPT Stream returned by GPT
28. Example: SSE with Hono Helper + GPT Push to the client using data: { "hoge": "fuga!" } format.
29. Example: SSE with Hono Helper + GPT Close the stream at the end of processing or on interruption.
30. Stream is easy to handle. How is it integrated into actual products?
31. AI Worker Tech Stack
32. RAG
33. RAG Quick Start
34. RAG Quick Start Accept user input, like text in a chat box.
35. RAG Quick Start The accepted text is embedded and represented as a vector.
36. RAG Quick Start Retrieve information related to the user's input.
37. RAG Quick Start Embed context in the prompt and generate a response.
38. RAG Quick Start Retrieval-Augmented Generation
39. Uploading Documents for Search Now, one important point in performing RAG (Retrieval-Augmented Generation) is that documents need to be registered in the Vector Store in advance.
40. Uploading Documents for Search The user uploads a file in some way, which is then embedded and stored in the vector store.
41. Uploading Documents for Search
42. AI Worker Tech Stack
43. Example: File Upload with @hono/zod-openapi
44. Example: File Upload with @hono/zod-openapi Enable validation of multiple files using multipart/form-data.
45. Example: File Upload with @hono/zod-openapi HonoRequest has a parseBody implementation, making it easy to parse multiple files.
46. B2B(Multi-tenant)
47. AI Worker as a Bridge Model Multi-tenant • Single Instance with Multiple Schemas • Switching Based on Tenant ID
48. AI Worker as a Bridge Model Multi-tenant • Single Instance with Multiple Schemas • Switching Based on Tenant ID TenantID
49. Extracting Tenant ID from Access Token
50. Extracting Tenant ID from Access Token Set tenantID in the context and propagate it to subsequent processes.
51. Extracting Tenant ID from Access Token Clearly identify the requester and propagate the Logger in the Context.
52. Security:Validation at DB and Response Levels Our company adopts Clean Architecture and DDD, resulting in separated layers. Request Response Handler Usecase Repository
53. Security:Validation at DB and Response Levels It is necessary to properly validate each layer to prevent unnecessary fields from leaking. Request Response Handler Usecase Repository
54. Security:Validation at DB and Response Levels Request Response Handler Usecase Repository
55. Security:Validation at DB and Response Levels Request Response Handler Usecase Repository Pass the response through Zod's parse as a DTO to avoid unnecessary fields and potential incidents.
56. Conclusion • In AI Worker, we use Hono's features for various aspects such as RAG, B2B tenant management, and security measures. For those who want to learn more about Hono: