今日已更新 320 条资讯 | 累计 22510 条内容
关于我们

标签：#ens

找到 1544 篇相关文章

AI 资讯

Stop letting LLMs hallucinate dates — a tool for AI agents

If you're building an AI agent that touches dates — booking flows, scheduling bots, "remind me on Friday" assistants — you've probably noticed: LLMs are terrible at dates. They hallucinate weekday-to-date mappings. They fencepost-error ranges. They forget what "next Friday" means in Ukrainian vs English. Asking the model to "be careful" doesn't fix it — what fixes it is moving date interpretation out of the model and into a deterministic tool. That's what whenis is. Use it as an agent tool Define a resolveDate(expression, reference) tool that calls whenis . Let the model invoke it instead of guessing. import { createParser } from ' @whenis/core ' ; import { uk } from ' @whenis/locale-uk ' ; import { booking } from ' @whenis/booking ' ; const parser = createParser ({ locales : [ uk ], plugins : [ booking ], options : { preferFuture : true }, }); const ref = new Date ( ' 2026-05-28 ' ); parser . parse ( " наступної п'ятниці " , { reference : ref }); // → { type: 'date', date: '2026-06-05', confidence: 1 } parser . parse ( ' з 5 по 10 червня ' , { reference : ref }); // → { type: 'range', start: '2026-06-05', end: '2026-06-11', nights: 6 } parser . parse ( ' після свят ' , { reference : ref }); // → { type: 'fuzzy', reason: 'holiday_ref', // metadata: { suggest_next_month: true } } English works the same way: import { en } from ' @whenis/locale-en ' ; const parser = createParser ({ locales : [ en ], options : { preferFuture : true } }); parser . parse ( ' next Friday ' , { reference : new Date ( ' 2026-05-28 ' ) }); // → { type: 'date', date: '2026-06-05', confidence: 1 } How it differs from chrono-node Multi-candidate output. A bare "Friday" mid-week emits both this Friday and next Friday with confidence scores. Your agent re-ranks using conversation context — no silent guessing inside the library. Locale as data. Adding RU/PL/CS is one source file with no engine changes. The Ukrainian locale ships full inflection: months × 7 cases, weekdays × 4 cases, pointers, conne

2026-05-28 原文 →
AI 资讯

Go Modules in Practice: Init, Tidy, Vendor, and Publishing Packages

As a backend engineer, I have worked on many services where the hard part was not only writing the code. The hard part was keeping the project clean, reproducible, easy to build, and safe to maintain as the team and codebase grew. In Go, a big part of that discipline comes from understanding Go Modules . At first, Go Modules may look simple: a go.mod file, a go.sum file, and a few commands like go mod init and go mod tidy . But in real projects, these small tools decide how your service builds in CI, how your dependencies are verified, how private repositories are handled, and how other developers can use your package. In this article, I want to explain Go Modules in a practical way, from the mindset of someone building production backend systems. We will cover: What Go Modules are and why Go does not work like NPM or Pip How go mod init , go mod tidy , and go mod vendor actually help How I think about Go project structure without over-engineering How to publish your own Go package A few production tips that matter in real teams What Are Go Modules? A Go module is a versioned collection of Go packages. In simple words, it is the boundary of your project. It tells Go: what your project is called which Go version it targets which dependencies it needs which versions of those dependencies should be used A Go module is defined by the go.mod file. Before Go Modules, Go projects were commonly managed inside GOPATH . That worked, but it created friction around dependency versions and project location. Go Modules solved that by making dependency management explicit and project-based. Today, when I start a serious Go project, one of the first things I do is initialize a module. Why Go Packages Feel Different From NPM or Pip If you come from JavaScript or Python, Go package management may feel a little strange at first. In Node.js, packages are usually published to NPM . In Python, packages are usually published to PyPI . Go is different. Go uses the module path as an import

2026-05-28 原文 →
← 上一页 下一页 →