feat: manually mirror opencoze's code from bytedance

Change-Id: I09a73aadda978ad9511264a756b2ce51f5761adf

backend/conf/model/template/entity/model_entity_template_ark.yaml

@@ -0,0 +1,94 @@
+id: 2002 # 模型 entity id, 同 id 数据不会覆盖
+name: Doubao Model
+description: test doubao description
+meta:
+  id: 102
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **文本**: 使用普通文本格式回复\n- **Markdown**: 将引导模型使用Markdown格式输出回复\n- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **Text**: Replies in plain text format\n- **Markdown**: Uses Markdown format for replies\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '1'
+        label: 'Markdown'
+      -
+        value: '2'
+        label: 'JSON'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_ark_doubao-1.5-lite.yaml

@@ -0,0 +1,66 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Doubao-1.5-Lite
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity

backend/conf/model/template/entity/model_entity_template_ark_doubao-1.5-pro-256k.yaml

@@ -0,0 +1,66 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Doubao-1.5-Pro-256k
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity

backend/conf/model/template/entity/model_entity_template_ark_doubao-1.5-pro-32k.yaml

@@ -0,0 +1,66 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Doubao-1.5-Pro-32k
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity

backend/conf/model/template/entity/model_entity_template_ark_doubao-1.5-thinking-pro.yaml

@@ -0,0 +1,90 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Doubao-1.5-Thinking-Pro
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '1'
+        label: 'JSON'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_ark_doubao-1.5-thinking-vision-pro.yaml

@@ -0,0 +1,90 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Doubao-1.5-Thinking-Vision-Pro
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '1'
+        label: 'JSON'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_ark_doubao-1.5-vision-lite.yaml

@@ -0,0 +1,90 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Doubao-1.5-Vision-Lite
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '1'
+        label: 'JSON'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_ark_doubao-1.5-vision-pro.yaml

@@ -0,0 +1,90 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Doubao-1.5-Vision-Pro
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '1'
+        label: 'JSON'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_ark_doubao-seed-1.6-flash.yaml

@@ -0,0 +1,90 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Doubao-Seed-1.6-Flash
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '1'
+        label: 'JSON'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_ark_doubao-seed-1.6-thinking.yaml

@@ -0,0 +1,90 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Doubao-Seed-1.6-Thinking
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '1'
+        label: 'JSON'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_ark_doubao-seed-1.6.yaml

@@ -0,0 +1,90 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Doubao-Seed-1.6
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '1'
+        label: 'JSON'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_ark_volc_deepseek-r1.yaml

@@ -0,0 +1,66 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Deepseek-R1-VolcEngine
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity

backend/conf/model/template/entity/model_entity_template_ark_volc_deepseek-v3.yaml

@@ -0,0 +1,66 @@
+id: 65536 # 模型 entity id, 同 id 数据不会覆盖
+name: Deepseek-V3-VolcEngine
+meta:
+  id: 65536
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    label_en: ''
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity

backend/conf/model/template/entity/model_entity_template_basic.yaml

@@ -0,0 +1,132 @@
+id: 100 # 模型 entity id, 同 id 数据不会覆盖
+name: test_model
+description: test_description
+meta:
+  id: 0
+scenario: 1
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: frequency_penalty
+    label:
+      zh: 重复语句惩罚
+      en: Frequency penalty
+    desc:
+      zh: '- **frequency penalty**: 当该值为正时，会阻止模型频繁使用相同的词汇和短语，从而增加输出内容的多样性。'
+      en: '**Frequency Penalty**: When positive, it discourages the model from repeating the same words and phrases, thereby increasing the diversity of the output.'
+    type: float
+    min: '-2'
+    max: '2'
+    precision: 2
+    default_val:
+      default_val: '0'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: presence_penalty
+    label:
+      zh: 重复主题惩罚
+      en: Presence penalty
+    desc:
+      zh: '- **presence penalty**: 当该值为正时，会阻止模型频繁讨论相同的主题，从而增加输出内容的多样性'
+      en: '**Presence Penalty**: When positive, it prevents the model from discussing the same topics repeatedly, thereby increasing the diversity of the output.'
+    type: float
+    min: '-2'
+    max: '2'
+    precision: 2
+    default_val:
+      default_val: '0'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **文本**: 使用普通文本格式回复\n- **Markdown**: 将引导模型使用Markdown格式输出回复\n- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **Text**: Replies in plain text format\n- **Markdown**: Uses Markdown format for replies\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '1'
+        label: 'Markdown'
+      -
+        value: '2'
+        label: 'JSON'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_claude.yaml

@@ -0,0 +1,47 @@
+id: 2006 # 模型 entity id, 同 id 数据不会覆盖
+name: Claude-3.5-Sonnet
+description: test claude description
+meta:
+  id: 106
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_deepseek.yaml

@@ -0,0 +1,72 @@
+id: 2004 # 模型 entity id, 同 id 数据不会覆盖
+name: DeepSeek-V3
+description: test deepseek description
+meta:
+  id: 104
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成随机性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **文本**: 使用普通文本格式回复\n- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **Text**: Replies in plain text format\n- **Markdown**: Uses Markdown format for replies\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '1'
+        label: 'JSON Object'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+

backend/conf/model/template/entity/model_entity_template_gemini.yaml

@@ -0,0 +1,90 @@
+id: 2007 # 模型 entity id, 同 id 数据不会覆盖
+name: Gemini-2.5-Flash
+description: test gemini description
+meta:
+  id: 107
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **文本**: 使用普通文本格式回复\n- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '2'
+        label: 'JSON'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_ollama.yaml

@@ -0,0 +1,47 @@
+id: 2003 # 模型 entity id, 同 id 数据不会覆盖
+name: Gemma-3
+description: test gemma-3 description
+meta:
+  id: 103
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_openai.yaml

@@ -0,0 +1,131 @@
+id: 2001 # 模型 entity id, 同 id 数据不会覆盖
+name: GPT-4o
+description: test gpt-4o description
+meta:
+  id: 101
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.7'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: frequency_penalty
+    label:
+      zh: 重复语句惩罚
+      en: Frequency penalty
+    desc:
+      zh: '- **frequency penalty**: 当该值为正时，会阻止模型频繁使用相同的词汇和短语，从而增加输出内容的多样性。'
+      en: '**Frequency Penalty**: When positive, it discourages the model from repeating the same words and phrases, thereby increasing the diversity of the output.'
+    type: float
+    min: '-2'
+    max: '2'
+    precision: 2
+    default_val:
+      default_val: '0'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: presence_penalty
+    label:
+      zh: 重复主题惩罚
+      en: Presence penalty
+    desc:
+      zh: '- **presence penalty**: 当该值为正时，会阻止模型频繁讨论相同的主题，从而增加输出内容的多样性'
+      en: '**Presence Penalty**: When positive, it prevents the model from discussing the same topics repeatedly, thereby increasing the diversity of the output.'
+    type: float
+    min: '-2'
+    max: '2'
+    precision: 2
+    default_val:
+      default_val: '0'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: response_format
+    label:
+      zh: 输出格式
+      en: Response format
+    desc:
+      zh: '- **文本**: 使用普通文本格式回复\n- **Markdown**: 将引导模型使用Markdown格式输出回复\n- **JSON**: 将引导模型使用JSON格式输出'
+      en: '**Response Format**:\n\n- **Text**: Replies in plain text format\n- **Markdown**: Uses Markdown format for replies\n- **JSON**: Uses JSON format for replies'
+    type: int
+    precision: 0
+    default_val:
+      default_val: '0'
+    options:
+      -
+        value: '0'
+        label: 'Text'
+      -
+        value: '1'
+        label: 'Markdown'
+      -
+        value: '2'
+        label: 'JSON'
+    style:
+      widget: radio_buttons
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings

backend/conf/model/template/entity/model_entity_template_qwen.yaml

@@ -0,0 +1,66 @@
+id: 2005 # 模型 entity id, 同 id 数据不会覆盖
+name: Qwen3-32B
+description: test qwen description
+meta:
+  id: 105
+default_parameters:
+  -
+    name: temperature
+    label:
+      zh: 生成随机性
+      en: Temperature
+    desc:
+      zh: '- **temperature**: 调高温度会使得模型的输出更多样性和创新性，反之，降低温度会使输出内容更加遵循指令要求但减少多样性。建议不要与“Top p”同时调整。'
+      en: '**Temperature**:\n\n- When you increase this value, the model outputs more diverse and innovative content; when you decrease it, the model outputs less diverse content that strictly follows the given instructions.\n- It is recommended not to adjust this value with \"Top p\" at the same time.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 1
+    default_val:
+      default_val: '1.0'
+      creative: '1'
+      balance: '0.8'
+      precise: '0.3'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity
+  -
+    name: max_tokens
+    label:
+      zh: 最大回复长度
+      en: Response max length
+    desc:
+      zh: '控制模型输出的Tokens 长度上限。通常 100 Tokens 约等于 150 个中文汉字。'
+      en: 'You can specify the maximum length of the tokens output through this value. Typically, 100 tokens are approximately equal to 150 Chinese characters.'
+    type: int
+    min: '1'
+    max: '4096'
+    precision: 0
+    default_val:
+      default_val: '4096'
+    style:
+      widget: slider
+      label:
+        zh: 输入及输出设置
+        en: Input and output settings
+  -
+    name: top_p
+    label:
+      zh: Top P
+      en: Top P
+    desc:
+      zh: '- **Top p 为累计概率**: 模型在生成输出时会从概率最高的词汇开始选择，直到这些词汇的总概率累积达到Top p 值。这样可以限制模型只选择这些高概率的词汇，从而控制输出内容的多样性。建议不要与“生成随机性”同时调整。'
+      en: '**Top P**:\n\n- An alternative to sampling with temperature, where only tokens within the top p probability mass are considered. For example, 0.1 means only the top 10% probability mass tokens are considered.\n- We recommend altering this or temperature, but not both.'
+    type: float
+    min: '0'
+    max: '1'
+    precision: 2
+    default_val:
+      default_val: '0.95'
+    style:
+      widget: slider
+      label:
+        zh: 生成多样性
+        en: Generation diversity