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_basic.yaml
+++ b/backend/conf/model/template/model_template_basic.yaml
@@ -0,0 +1,201 @@
+id: 100
+name: test_model
+icon_uri: default_icon/test_icon_uri.png
+icon_url: test_icon_url
+description:
+    zh: test_description
+    en: test_description
+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: 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"
+      default_val:
+        default_val: "0"
+      precision: 2
+      options: []
+      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"
+      default_val:
+        default_val: "0"
+      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: '- **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
+      min: ""
+      max: ""
+      default_val:
+        default_val: "0"
+      options:
+        - label: Text
+          value: "0"
+        - label: Markdown
+          value: "1"
+        - label: JSON
+          value: "2"
+      style:
+        widget: radio_buttons
+        label:
+            zh: 输入及输出设置
+            en: Input and output settings
+meta:
+    name: test_model
+    protocol: test_protocol
+    capability:
+        function_call: true
+        input_modal:
+            - text
+            - image
+            - audio
+            - video
+        input_tokens: 1024
+        json_mode: true
+        max_tokens: 2048
+        output_modal:
+            - text
+            - image
+            - audio
+            - video
+        output_tokens: 1024
+        prefix_caching: false
+        reasoning: false
+        prefill_response: false
+    conn_config:
+        base_url: https://localhost:1234/chat/completion
+        api_key: qweasdzxc
+        timeout: 10s
+        model: model_name
+        temperature: 0.7
+        frequency_penalty: 0
+        presence_penalty: 0
+        max_tokens: 2048
+        top_p: 0
+        top_k: 0
+        stop:
+            - bye
+        enable_thinking: false
+        openai:
+            by_azure: true
+            api_version: "2024-10-21"
+            response_format:
+                type: text
+                jsonschema: null
+        claude:
+            by_bedrock: true
+            access_key: bedrock_ak
+            secret_access_key: bedrock_secret_ak
+            session_token: bedrock_session_token
+            region: bedrock_region
+        ark:
+            region: region
+            access_key: ak
+            secret_key: sk
+            retry_times: 123
+            custom_header:
+                key: val
+        deepseek:
+            response_format_type: text
+        qwen: null
+        gemini:
+            backend: 0
+            project: ""
+            location: ""
+            api_version: ""
+            headers:
+                key_1:
+                    - val_1
+                    - val_2
+            timeout_ms: 0
+            include_thoughts: true
+            thinking_budget: null
+        custom: {}
+    status: 0