feat: refactor model manager

* chore: mv model icon * fix: model icon * fix: model icon * feat: refactor model manager * fix: model icon * fix: model icon * feat: refactor model manager See merge request: !905
2025-07-24 13:12:44 +00:00
parent 12f7762797
commit 9b3814e2c5
114 changed files with 2888 additions and 4982 deletions
--- a/backend/conf/model/template/model_template_ark_doubao-1.5-thinking-vision-pro.yaml
+++ b/backend/conf/model/template/model_template_ark_doubao-1.5-thinking-vision-pro.yaml
@@ -0,0 +1,132 @@
+id: 65536
+name: Doubao-1.5-Thinking-Vision-Pro
+icon_uri: default_icon/doubao_v2.png
+icon_url: ""
+description:
+    zh: doubao-1-5-thinking-vision-pro 全新视觉深度思考模型，具备更强的通用多模态理解和推理能力，在 59 个公开评测基准中的 37 个上取得 SOTA 表现。
+    en: doubao-1-5-thinking-vision-pro is a brand-new visual deep thinking model, featuring stronger general multimodal understanding and reasoning abilities, achieving SOTA performance on 37 out of 59 public evaluation benchmarks.
+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"
+      default_val:
+        balance: "0.8"
+        creative: "1"
+        default_val: "1.0"
+        precise: "0.3"
+      precision: 1
+      options: []
+      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"
+      default_val:
+        default_val: "4096"
+      options: []
+      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"
+      default_val:
+        default_val: "0.7"
+      precision: 2
+      options: []
+      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
+      min: ""
+      max: ""
+      default_val:
+        default_val: "0"
+      options:
+        - label: Text
+          value: "0"
+        - label: JSON
+          value: "1"
+      style:
+        widget: radio_buttons
+        label:
+            zh: 输入及输出设置
+            en: Input and output settings
+meta:
+    name: doubao-1.5-thinking-vision-pro
+    protocol: ark
+    capability:
+        function_call: true
+        input_modal:
+            - text
+            - image
+            - video
+        input_tokens: 96000
+        json_mode: true
+        max_tokens: 128000
+        output_modal:
+            - text
+        output_tokens: 16000
+        prefix_caching: false
+        reasoning: true
+        prefill_response: false
+    conn_config:
+        base_url: ""
+        api_key: ""
+        timeout: 0s
+        model: ""
+        temperature: 0.1
+        frequency_penalty: 0
+        presence_penalty: 0
+        max_tokens: 4096
+        top_p: 0.7
+        top_k: 0
+        stop: []
+        openai: null
+        claude: null
+        ark:
+            region: ""
+            access_key: ""
+            secret_key: ""
+            retry_times: null
+            custom_header: {}
+        deepseek: null
+        qwen: null
+        gemini: null
+        custom: {}
+    status: 0