Skip to content

docs(zh): polish wording of 30-Minute Quick Start Chinese documentation - #945

Open
cubelitblade wants to merge 7 commits into
langgenius:mainfrom
cubelitblade:patch-1
Open

docs(zh): polish wording of 30-Minute Quick Start Chinese documentation#945
cubelitblade wants to merge 7 commits into
langgenius:mainfrom
cubelitblade:patch-1

Conversation

@cubelitblade

@cubelitblade cubelitblade commented Aug 15, 2026

Copy link
Copy Markdown
  • Changed some machine-translated field and node names to match the actual translations used in Dify's Simplified Chinese interface
  • Adjusted certain field names to those automatically generated during step-by-step operations in a Simplified Chinese environment
  • Refined various phrasing to better conform to Simplified Chinese expression habits, improving overall readability

@cubelitblade
docs(zh): polish wording of 30-Minute Quick Start Chinese documentation
6665716 
- Changed some machine-translated field and node names to match the actual translations used in Dify's Simplified Chinese interface
- Adjusted certain field names to those automatically generated during step-by-step operations in a Simplified Chinese environment
- Refined various phrasing to better conform to Simplified Chinese expression habits, improving overall readability
Copilot AI lite review requested due to automatic review settings August 15, 2026 17:55
@cubelitblade
cubelitblade requested a review from RiskeyL as a code owner August 15, 2026 17:55
Copilot AI reviewed Aug 15, 2026
View reviewed changes

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR polishes wording in the Simplified Chinese “30 分钟快速入门” guide, aiming to better match Dify’s zh UI labels and improve readability.

Changes:

  • Updated multiple UI label translations (nodes/fields/buttons) and refined phrasing for more natural Simplified Chinese.
  • Adjusted terminology and step instructions throughout the workflow-building walkthrough.
  • Tweaked examples and explanations for clarity and consistency.
Suppressed comments (2)

zh/quick-start.mdx:235

  • The English source uses {x}type in Doc (a type enum value). Translating this filter value to 文档 may make the instruction incorrect in the UI; keep the filter value as Doc to match the original guide.
    2. 启用 **过滤条件**：`{x}type` **在** `文档`。

zh/quick-start.mdx:516

  • In this block: (1) “模板节点” should match the renamed node “模板转换节点”; (2) keep token terminology consistent (“令牌” vs “词元”); (3) fix the duplicated “的” in “合适的的场景”.
  虽然 LLM 也可以处理输出格式化，但它们的输出往往不一致且难以预测。对于不需要推理的、基于规则的格式化任务，模板节点能以更稳定可靠的方式完成，且不消耗任何词元。

  LLM 固然强大，但懂得在合适的的场景选择合适的工具，才是构建更可靠、更具经济效益的 AI 应用的关键。

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

Comment thread zh/quick-start.mdx
Comment thread zh/quick-start.mdx

<Info>
如果用户输入了无效的平台名称，比如 `ohhhhhh` 或 `BookFace` 怎么办？我们不想浪费时间和令牌生成无用的内容。
如果用户输入了无效的平台名称，比如 `ohhhhhh` 或 `BookFace` 怎么办？我们不想浪费时间和词元生成无用的内容。

@cubelitblade cubelitblade Aug 15, 2026

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'd like to clarify the terminology here. In the Chinese docs, "令牌" is reserved for credentials/access tokens (authentication), while "词元" is the correct translation for LLM tokens in the NLP context — it has been officially adopted by China's National Committee for Terminology in Science and Technology and is also used on Wikipedia and Baidu Baike. You can refer to the Wikipedia entry for more details: https://zh.wikipedia.org/wiki/%E8%AF%8D%E5%85%83

So the current usage in this PR is intentional and accurate — "词元" is the right term for token usage/consumption in the LLM context. "令牌" would be incorrect here.

Comment thread zh/quick-start.mdx Outdated
Comment thread zh/quick-start.mdx
1. 将 `用户输入/user_file` 设置为输入变量。

2. 启用 **过滤条件**：`{x}type` **在** `Image`。
2. 启用 **过滤条件**：`{x}type` **在** `图片`。

@cubelitblade cubelitblade Aug 15, 2026

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Regarding the filter value: in the Simplified Chinese UI, the type label for images is indeed displayed as "图片" (not "Image"). Since this step refers directly to the UI element, I kept it as "图片" to match what users actually see in the interface. Translating it back to "Image" would be inconsistent with the localized UI and could confuse users following the guide in Chinese.
image

Comment thread zh/quick-start.mdx Outdated
Comment thread zh/quick-start.mdx Outdated

<Check>
这就是为什么我们在用户输入节点的目标平台字段的标签名称中包含了 `(≤10)`。
这就是我们在用户输入节点的目标平台字段的标签名称中包含了 `(≤10)`的原因。
Comment thread zh/quick-start.mdx Outdated
Comment thread zh/quick-start.mdx Outdated
@cubelitblade
Potential fix for pull request finding
ee9ffd9 
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Copilot AI review requested due to automatic review settings August 15, 2026 18:10
Copilot AI reviewed Aug 15, 2026
View reviewed changes

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.

Suppressed comments (8)

zh/quick-start.mdx:230

  • {x}type 的过滤值这里改成了 图片。但同一教程的 en/ja 版本仍使用 Image，且这类枚举值通常是非本地化的（否则不同语言版本的步骤会不一致）。如果实际值仍为 Image，按本文操作会导致过滤条件匹配失败。建议除非已确认 UI/数据值已本地化，否则保持与 en/ja 一致。
    2. 启用 **过滤条件**：`{x}type` **在** `图片`。

zh/quick-start.mdx:235

  • {x}type 的过滤值这里改成了 文档，但 en/ja 版本使用的是 Doc。如果该字段的实际枚举值仍为 Doc（常见于非本地化内部值），按本文操作会导致过滤条件不生效。建议除非已确认本地化后的真实取值，否则保持 Doc。
    2. 启用 **过滤条件**：`{x}type` **在** `文档`。

zh/quick-start.mdx:452

  • 中文标点前多了一个空格（**结构化输出** ，），会影响排版一致性。
        1. 在 **输出变量** 旁，开启 **结构化输出** ，将出现 `structured_output` 变量。点击 **配置**。

zh/quick-start.mdx:475

  • 行内代码后缺少空格：(≤10) 与“的”之间建议加空格，避免阅读时粘连。
          这就是我们在用户输入节点的目标平台字段的标签名称中包含了 `(≤10)`的原因。

zh/quick-start.mdx:496

  • 本节已将节点名称改为“模板转换节点”，但此处仍写“模板节点”，术语不一致会让读者难以对应到 UI 中的节点名称。
2. 在模板节点的面板上，将 `迭代/output` 设置为输入变量并命名为 `output`。

zh/quick-start.mdx:522

  • 这里第 1 步仍写“在模板节点之后”，但上文已改为“模板转换节点”，且第 2 步输出变量也使用了 模板转换/output。建议两步统一为“模板转换节点”。
1. 在模板节点之后，添加一个输出节点。
2. 在输出节点的面板上，将 `模板转换/output` 设置为输出变量。

zh/quick-start.mdx:508

  • 这句话里“每个 平台 - 内容 对”出现了多余空格，读起来不顺畅。
    - `{% for item in output %}` / `{% endfor %}`：遍历输入数组中的每个 平台 - 内容 对。

zh/quick-start.mdx:516

  • 这里仍使用“模板节点”，与本节标题/步骤中的“模板转换节点”不一致；同时“合适的的场景”存在重复用字。建议统一术语并修正重复字。
  虽然 LLM 也可以处理输出格式化，但它们的输出往往不一致且难以预测。对于不需要推理的、基于规则的格式化任务，模板节点能以更稳定可靠的方式完成，且不消耗任何词元。

  LLM 固然强大，但懂得在合适的的场景选择合适的工具，才是构建更可靠、更具经济效益的 AI 应用的关键。

Copilot AI review requested due to automatic review settings August 15, 2026 18:28
Copilot AI reviewed Aug 15, 2026
View reviewed changes

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.

Suppressed comments (4)

zh/quick-start.mdx:514

  • 这里“模板节点”与本节标题/步骤中使用的“模板转换节点”不一致，容易让读者误以为是两个不同的节点。建议统一为“模板转换节点”。
  虽然 LLM 也可以处理输出格式化，但它们的输出往往不一致且难以预测。对于不需要推理的、基于规则的格式化任务，模板节点能以更稳定可靠的方式完成，且不消耗任何词元。

zh/quick-start.mdx:522

  • 上一节已将节点名称写作“模板转换节点”，但这里仍写为“模板节点”，会造成步骤指引不一致。建议改为“模板转换节点”。
1. 在模板节点之后，添加一个输出节点。
2. 在输出节点的面板上，将 `模板转换/output` 设置为输出变量。

zh/quick-start.mdx:452

  • 此处在加粗文本后的中文逗号前多了一个空格（“结构化输出 ，”），会导致中文标点排版不规范。建议移除空格。
        1. 在 **输出变量** 旁，开启 **结构化输出** ，将出现 `structured_output` 变量。点击 **配置**。

zh/quick-start.mdx:516

  • 此句有重复用字（“合适的的场景”），属于明显笔误，建议删除一个“的”。
  LLM 固然强大，但懂得在合适的的场景选择合适的工具，才是构建更可靠、更具经济效益的 AI 应用的关键。

Copilot AI review requested due to automatic review settings August 15, 2026 18:33
Copilot AI reviewed Aug 15, 2026
View reviewed changes

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.

Suppressed comments (2)

zh/quick-start.mdx:508

  • 该句在“每个 平台 - 内容 对”中插入了多余空格（除“平台 - 内容”外），阅读上像是排版错误。建议仅保留“平台 - 内容”两侧空格，并用引号明确这是一个整体短语。
    - `{% for item in output %}` / `{% endfor %}`：遍历输入数组中的每个 平台 - 内容 对。

zh/quick-start.mdx:475

  • 这里用“标签名称”与前文输入字段配置里的“显示名称”表述不一致，容易让读者误以为是两个不同的 UI 字段。建议统一为“显示名称”。
          这就是我们在用户输入节点的目标平台字段的标签名称中包含了 `(≤10)` 的原因。

Copilot AI review requested due to automatic review settings August 15, 2026 18:37
Copilot AI reviewed Aug 15, 2026
View reviewed changes

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.

Suppressed comments (2)

zh/quick-start.mdx:135

  • linkedIn 的大小写不符合品牌写法（应为 LinkedIn），可能会降低示例的可信度与可读性。
  由于我们的平台字段接受自由格式的文本输入，用户可能会以各种方式输入：`x 和 linkedIn`、`在 Twitter 和 LinkedIn 上发布`，甚至 `帮我发 Twitter + LinkedIn`。

zh/quick-start.mdx:475

  • 本页前文已使用“显示名称”来描述用户输入字段（与 UI 文案一致），这里仍写“标签名称”会造成术语不一致，读者可能不确定要看哪个字段。建议统一为“显示名称”。
          这就是我们在用户输入节点的目标平台字段的显示名称中包含了 `(≤10)` 的原因。

Copilot AI review requested due to automatic review settings August 15, 2026 18:40
Copilot AI reviewed Aug 15, 2026

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

Copilot AI review requested due to automatic review settings August 15, 2026 18:44
Copilot AI reviewed Aug 15, 2026

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

@dosubot dosubot Bot added size:L This PR changes 100-499 lines, ignoring generated files. documentation Improvements or additions to documentation labels Aug 15, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

Copilot code review Copilot
Copilot review effort
Applies to this pull request for everyone.Learn more about Copilot code review.
Copilot left review comments
@RiskeyL RiskeyL Awaiting requested review from RiskeyL RiskeyL is a code owner

At least 1 approving review is required to merge this pull request.

Assignees

No one assigned

Labels

documentation Improvements or additions to documentation size:L This PR changes 100-499 lines, ignoring generated files.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@cubelitblade