Skip to content

RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.

fix(i18n): rename 'Max tokens' to 'Max context length' and drop misleading default (#19729)

chanxa557a81e345d
diff --git a/web/src/locales/en.ts b/web/src/locales/en.ts
index 5930e0cf54..dce87f4ff9 100644
--- a/web/src/locales/en.ts
+++ b/web/src/locales/en.ts
@@ -1136,7 +1136,7 @@ This auto-tagging feature enhances retrieval by adding another layer of domain-s
'Similar to the presence penalty, this reduces the model’s tendency to repeat the same words frequently.',
maxTokens: 'Max tokens',
maxTokensMessage: 'Max tokens is required',
- maxTokensTip: `The maximum context size of the model; an invalid or incorrect value will cause an error. Defaults to 512.`,
+ maxTokensTip: `The maximum context size of the model; an invalid or incorrect value will cause an error. `,
maxTokensInvalidMessage: 'Please enter a valid number for Max tokens.',
maxTokensMinMessage: 'Max tokens cannot be less than 0.',
thinking: 'Thinking',
@@ -1988,9 +1988,9 @@ Example: Virtual Hosted Style`,
avatar: 'Avatar',
avatarTip: 'This will be displayed on your profile.',
profileDescription: 'Update your photo and personal details here.',
- maxTokens: 'Max tokens',
- maxTokensMessage: 'Max tokens is required',
- maxTokensTip: `The maximum context size of the model; an invalid or incorrect value will cause an error. Defaults to 512.`,
+ maxTokens: 'Max context length',
+ maxTokensMessage: 'Max context length is required',
+ maxTokensTip: `The maximum context size of the model; an invalid or incorrect value will cause an error. `,
maxTokensInvalidMessage: 'Please enter a valid number for Max tokens.',
maxTokensMinMessage: 'Max tokens cannot be less than 0.',
password: 'Password',
@@ -2359,7 +2359,7 @@ Example: Virtual Hosted Style`,
batchRemoveModels: 'Remove all models',
batchVerifyModels: 'Verify all models',
editCustomModelTitle: 'Edit model',
- modelMaxTokens: 'Max tokens',
+ modelMaxTokens: 'Max context length',
modelFeatures: 'Model features',
modelFeatureToolCall: 'Tool call',
modelFeatureFunctionCall: 'Function call',
diff --git a/web/src/locales/zh.ts b/web/src/locales/zh.ts
index c13d3b0423..fce5cac67f 100644
--- a/web/src/locales/zh.ts
+++ b/web/src/locales/zh.ts
@@ -1032,7 +1032,7 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取 Entities 和 R
'与存在惩罚类似,这减少了模型频繁重复相同单词的倾向。',
maxTokens: '最大 Token 数',
maxTokensMessage: '最大 Token 数是必填项',
- maxTokensTip: `模型的最大上下文大小;无效或不正确的值会导致错误。默认值为 512。`,
+ maxTokensTip: `模型的最大上下文大小;无效或不正确的值会导致错误。`,
maxTokensInvalidMessage: '请输入有效的最大令牌数。',
maxTokensMinMessage: '最大令牌数不能小于 0。',
thinking: '思考中...',
@@ -1649,9 +1649,9 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取 Entities 和 R
avatar: '头像',
avatarTip: '这会在你的个人主页展示',
profileDescription: '在此更新您的照片和个人详细信息。',
- maxTokens: '最大token数',
- maxTokensMessage: '最大token数是必填项',
- maxTokensTip: `模型的最大上下文大小;无效或不正确的值会导致错误。默认值为 512。`,
+ maxTokens: '最大上下文长度',
+ maxTokensMessage: '最大上下文长度是必填项',
+ maxTokensTip: `模型的最大上下文大小;无效或不正确的值会导致错误。`,
maxTokensInvalidMessage: '请输入有效的最大令牌数。',
maxTokensMinMessage: '最大令牌数不能小于 0。',
password: '密码',
@@ -1968,7 +1968,7 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取 Entities 和 R
batchRemoveModels: '移除全部模型',
batchVerifyModels: '验证全部模型',
editCustomModelTitle: '编辑模型',
- modelMaxTokens: '最大 Token 数',
+ modelMaxTokens: '最大上下文长度',
modelTypes: {
chat: 'Chat',
embedding: 'Embedding',