diff --git a/web/app/components/develop/template/template_workflow.en.mdx b/web/app/components/develop/template/template_workflow.en.mdx
index 0f15c4406b..556b306a64 100644
--- a/web/app/components/develop/template/template_workflow.en.mdx
+++ b/web/app/components/develop/template/template_workflow.en.mdx
@@ -90,7 +90,7 @@ Workflow applications offers non-session support and is ideal for translation, a
Each streaming chunk starts with `data:`, separated by two newline characters `\n\n`, as shown below:
```streaming {{ title: 'Response' }}
- data: {"event": "message", "task_id": "900bbd43-dc0b-4383-a372-aa6e6c414227", "id": "663c5084-a254-4040-8ad3-51f2a3c1a77c", "answer": "Hi", "created_at": 1705398420}\n\n
+ data: {"event": "text_chunk", "workflow_run_id": "b85e5fc5-751b-454d-b14e-dc5f240b0a31", "task_id": "bd029338-b068-4d34-a331-fc85478922c2", "data": {"text": "\u4e3a\u4e86", "from_variable_selector": ["1745912968134", "text"]}}\n\n
```
The structure of the streaming chunks varies depending on the `event`:
@@ -116,6 +116,13 @@ Workflow applications offers non-session support and is ideal for translation, a
- `predecessor_node_id` (string) optional Prefix node ID, used for canvas display execution path
- `inputs` (object) Contents of all preceding node variables used in the node
- `created_at` (timestamp) timestamp of start, e.g., 1705395332
+ - `event: text_chunk` Text fragment
+ - `task_id` (string) Task ID, used for request tracking and the below Stop Generate API
+ - `workflow_run_id` (string) Unique ID of workflow execution
+ - `event` (string) fixed to `text_chunk`
+ - `data` (object) detail
+ - `text` (string) Text content
+ - `from_variable_selector` (array) Text source path, helping developers understand which node and variable generated the text
- `event: node_finished` node execution ends, success or failure in different states in the same event
- `task_id` (string) Task ID, used for request tracking and the below Stop Generate API
- `workflow_run_id` (string) Unique ID of workflow execution
diff --git a/web/app/components/develop/template/template_workflow.ja.mdx b/web/app/components/develop/template/template_workflow.ja.mdx
index 0239b40224..3f33be58b9 100644
--- a/web/app/components/develop/template/template_workflow.ja.mdx
+++ b/web/app/components/develop/template/template_workflow.ja.mdx
@@ -93,7 +93,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
各ストリーミングチャンクは`data:`で始まり、2つの改行文字`\n\n`で区切られます。以下のように表示されます：
```streaming {{ title: '応答' }}
- data: {"event": "message", "task_id": "900bbd43-dc0b-4383-a372-aa6e6c414227", "id": "663c5084-a254-4040-8ad3-51f2a3c1a77c", "answer": "Hi", "created_at": 1705398420}\n\n
+ data: {"event": "text_chunk", "workflow_run_id": "b85e5fc5-751b-454d-b14e-dc5f240b0a31", "task_id": "bd029338-b068-4d34-a331-fc85478922c2", "data": {"text": "\u4e3a\u4e86", "from_variable_selector": ["1745912968134", "text"]}}\n\n
```
ストリーミングチャンクの構造は`event`に応じて異なります：
@@ -119,6 +119,13 @@ import { Row, Col, Properties, Property, Heading, SubProperty, Paragraph } from
- `predecessor_node_id` (string) オプションのプレフィックスノードID、キャンバス表示実行パスに使用
- `inputs` (object) ノードで使用されるすべての前のノード変数の内容
- `created_at` (timestamp) 開始のタイムスタンプ、例：1705395332
+ - `event: text_chunk` テキストフラグメント
+ - `task_id` (string) タスクID、リクエスト追跡と以下のStop Generate APIに使用
+ - `workflow_run_id` (string) ワークフロー実行の一意のID
+ - `event` (string) `text_chunk`に固定
+ - `data` (object) 詳細
+ - `text` (string) テキスト内容
+ - `from_variable_selector` (array) テキスト生成元パス（開発者がどのノードのどの変数から生成されたかを理解するための情報）
- `event: node_finished` ノード実行終了、同じイベントで異なる状態で成功または失敗
- `task_id` (string) タスクID、リクエスト追跡と以下のStop Generate APIに使用
- `workflow_run_id` (string) ワークフロー実行の一意のID
diff --git a/web/app/components/develop/template/template_workflow.zh.mdx b/web/app/components/develop/template/template_workflow.zh.mdx
index 939df2703d..b032407ee9 100644
--- a/web/app/components/develop/template/template_workflow.zh.mdx
+++ b/web/app/components/develop/template/template_workflow.zh.mdx
@@ -87,7 +87,7 @@ Workflow 应用无会话支持，适合用于翻译/文章写作/总结 AI 等
每个流式块均为 data: 开头，块之间以 `\n\n` 即两个换行符分隔，如下所示：
```streaming {{ title: 'Response' }}
- data: {"event": "message", "task_id": "900bbd43-dc0b-4383-a372-aa6e6c414227", "id": "663c5084-a254-4040-8ad3-51f2a3c1a77c", "answer": "Hi", "created_at": 1705398420}\n\n
+ data: {"event": "text_chunk", "workflow_run_id": "b85e5fc5-751b-454d-b14e-dc5f240b0a31", "task_id": "bd029338-b068-4d34-a331-fc85478922c2", "data": {"text": "\u4e3a\u4e86", "from_variable_selector": ["1745912968134", "text"]}}\n\n
```
流式块中根据 `event` 不同，结构也不同，包含以下类型：
@@ -113,6 +113,13 @@ Workflow 应用无会话支持，适合用于翻译/文章写作/总结 AI 等
- `predecessor_node_id` (string) 前置节点 ID，用于画布展示执行路径
- `inputs` (object) 节点中所有使用到的前置节点变量内容
- `created_at` (timestamp) 开始时间
+ - `event: text_chunk` 文本片段
+ - `task_id` (string) 任务 ID，用于请求跟踪和下方的停止响应接口
+ - `workflow_run_id` (string) workflow 执行 ID
+ - `event` (string) 固定为 `text_chunk`
+ - `data` (object) 详细内容
+ - `text` (string) 文本内容
+ - `from_variable_selector` (array) 文本来源路径，帮助开发者了解文本是由哪个节点的哪个变量生成的
- `event: node_finished` node 执行结束，成功失败同一事件中不同状态
- `task_id` (string) 任务 ID，用于请求跟踪和下方的停止响应接口
- `workflow_run_id` (string) workflow 执行 ID