add gemini model

* fix interactive edge

* fix

docSite/content/zh-cn/docs/development/configuration.md

@@ -25,251 +25,6 @@ weight: 707
     "qaMaxProcess": 15, // 问答拆分线程数量
     "tokenWorkers": 50, // Token 计算线程保持数，会持续占用内存，不能设置太大。
     "pgHNSWEfSearch": 100 // 向量搜索参数。越大，搜索越精确，但是速度越慢。设置为100，有99%+精度。
-  },
-  "llmModels": [
-    {
-      "provider": "OpenAI", // 模型提供商，主要用于分类展示，目前已经内置提供商包括：https://github.com/labring/FastGPT/blob/main/packages/global/core/ai/provider.ts, 可 pr 提供新的提供商，或直接填写 Other
-      "model": "gpt-4o-mini", // 模型名(对应OneAPI中渠道的模型名)
-      "name": "gpt-4o-mini", // 模型别名
-      "maxContext": 125000, // 最大上下文
-      "maxResponse": 16000, // 最大回复
-      "quoteMaxToken": 120000, // 最大引用内容
-      "maxTemperature": 1.2, // 最大温度
-      "charsPointsPrice": 0, // n积分/1k token（商业版）
-      "censor": false, // 是否开启敏感校验（商业版）
-      "vision": true, // 是否支持图片输入
-      "datasetProcess": true, // 是否设置为文本理解模型（QA），务必保证至少有一个为true，否则知识库会报错
-      "usedInClassify": true, // 是否用于问题分类（务必保证至少有一个为true）
-      "usedInExtractFields": true, // 是否用于内容提取（务必保证至少有一个为true）
-      "usedInToolCall": true, // 是否用于工具调用（务必保证至少有一个为true）
-      "usedInQueryExtension": true, // 是否用于问题优化（务必保证至少有一个为true）
-      "toolChoice": true, // 是否支持工具选择（分类，内容提取，工具调用会用到。）
-      "functionCall": false, // 是否支持函数调用（分类，内容提取，工具调用会用到。会优先使用 toolChoice，如果为false，则使用 functionCall，如果仍为 false，则使用提示词模式）
-      "customCQPrompt": "", // 自定义文本分类提示词（不支持工具和函数调用的模型
-      "customExtractPrompt": "", // 自定义内容提取提示词
-      "defaultSystemChatPrompt": "", // 对话默认携带的系统提示词
-      "defaultConfig": {}, // 请求API时，挟带一些默认配置（比如 GLM4 的 top_p）
-      "fieldMap": {} // 字段映射（o1 模型需要把 max_tokens 映射为 max_completion_tokens）
-    },
-    {
-      "provider": "OpenAI",
-      "model": "gpt-4o",
-      "name": "gpt-4o",
-      "maxContext": 125000,
-      "maxResponse": 4000,
-      "quoteMaxToken": 120000,
-      "maxTemperature": 1.2,
-      "charsPointsPrice": 0,
-      "censor": false,
-      "vision": true,
-      "datasetProcess": true,
-      "usedInClassify": true,
-      "usedInExtractFields": true,
-      "usedInToolCall": true,
-      "usedInQueryExtension": true,
-      "toolChoice": true,
-      "functionCall": false,
-      "customCQPrompt": "",
-      "customExtractPrompt": "",
-      "defaultSystemChatPrompt": "",
-      "defaultConfig": {},
-      "fieldMap": {}
-    },
-    {
-      "provider": "OpenAI",
-      "model": "o1-mini",
-      "name": "o1-mini",
-      "maxContext": 125000,
-      "maxResponse": 65000,
-      "quoteMaxToken": 120000,
-      "maxTemperature": 1.2,
-      "charsPointsPrice": 0,
-      "censor": false,
-      "vision": false,
-      "datasetProcess": true,
-      "usedInClassify": true,
-      "usedInExtractFields": true,
-      "usedInToolCall": true,
-      "usedInQueryExtension": true,
-      "toolChoice": false,
-      "functionCall": false,
-      "customCQPrompt": "",
-      "customExtractPrompt": "",
-      "defaultSystemChatPrompt": "",
-      "defaultConfig": {
-        "temperature": 1,
-        "max_tokens": null,
-        "stream": false
-      }
-    },
-    {
-      "provider": "OpenAI",
-      "model": "o1-preview",
-      "name": "o1-preview",
-      "maxContext": 125000,
-      "maxResponse": 32000,
-      "quoteMaxToken": 120000,
-      "maxTemperature": 1.2,
-      "charsPointsPrice": 0,
-      "censor": false,
-      "vision": false,
-      "datasetProcess": true,
-      "usedInClassify": true,
-      "usedInExtractFields": true,
-      "usedInToolCall": true,
-      "usedInQueryExtension": true,
-      "toolChoice": false,
-      "functionCall": false,
-      "customCQPrompt": "",
-      "customExtractPrompt": "",
-      "defaultSystemChatPrompt": "",
-      "defaultConfig": {
-         "temperature": 1,
-        "max_tokens": null,
-        "stream": false
-      }
-    }
-  ],
-  "vectorModels": [
-    {
-      "provider": "OpenAI",
-      "model": "text-embedding-3-small",
-      "name": "text-embedding-3-small",
-      "charsPointsPrice": 0,
-      "defaultToken": 512,
-      "maxToken": 3000,
-      "weight": 100
-    },
-    {
-      "provider": "OpenAI",
-      "model": "text-embedding-3-large",
-      "name": "text-embedding-3-large",
-      "charsPointsPrice": 0,
-      "defaultToken": 512,
-      "maxToken": 3000,
-      "weight": 100,
-      "defaultConfig": {
-        "dimensions": 1024
-      }
-    },
-    {
-      "provider": "OpenAI",
-      "model": "text-embedding-ada-002", // 模型名（与OneAPI对应）
-      "name": "Embedding-2", // 模型展示名
-      "charsPointsPrice": 0, // n积分/1k token
-      "defaultToken": 700, // 默认文本分割时候的 token
-      "maxToken": 3000, // 最大 token
-      "weight": 100, // 优先训练权重
-      "defaultConfig": {}, // 自定义额外参数。例如，如果希望使用 embedding3-large 的话，可以传入 dimensions:1024，来返回1024维度的向量。（目前必须小于1536维度）
-      "dbConfig": {}, // 存储时的额外参数（非对称向量模型时候需要用到）
-      "queryConfig": {} // 参训时的额外参数
-    }
-  ],
-  "reRankModels": [],
-  "audioSpeechModels": [
-    {
-      "provider": "OpenAI",
-      "model": "tts-1",
-      "name": "OpenAI TTS1",
-      "charsPointsPrice": 0,
-      "voices": [
-        { "label": "Alloy", "value": "alloy", "bufferId": "openai-Alloy" },
-        { "label": "Echo", "value": "echo", "bufferId": "openai-Echo" },
-        { "label": "Fable", "value": "fable", "bufferId": "openai-Fable" },
-        { "label": "Onyx", "value": "onyx", "bufferId": "openai-Onyx" },
-        { "label": "Nova", "value": "nova", "bufferId": "openai-Nova" },
-        { "label": "Shimmer", "value": "shimmer", "bufferId": "openai-Shimmer" }
-      ]
-    }
-  ],
-  "whisperModel": {
-    "provider": "OpenAI",
-    "model": "whisper-1",
-    "name": "Whisper1",
-    "charsPointsPrice": 0
   }
 }
-```
-
-##  内置的模型提供商ID
-
-为了方便模型分类展示，FastGPT 内置了部分模型提供商的名字和 Logo。如果你期望补充提供商，可[提交 Issue](https://github.com/labring/FastGPT/issues)，并提供几个信息：
-
-1. 厂商官网地址
-2. 厂商 SVG logo，建议是正方形图片。
-
-目前已支持的提供商, 复制 "-" 之前的字符串，作为 provider 的值。
-
-- OpenAI
-- Claude
-- Gemini
-- Meta
-- MistralAI
-- AliCloud - 阿里云
-- Qwen - 通义千问
-- Doubao - 豆包
-- ChatGLM - 智谱
-- DeepSeek - 深度求索
-- Moonshot - 月之暗面
-- MiniMax
-- SparkDesk - 讯飞星火
-- Hunyuan - 腾讯混元
-- Baichuan - 百川
-- Yi - 零一万物
-- Ernie - 文心一言
-- StepFun - 阶跃星辰
-- Ollama
-- BAAI - 智源研究院
-- FishAudio
-- Intern - 书生
-- Moka - Moka-AI
-- Other - 其他
-
-
-## ReRank 模型接入
-
-由于 OneAPI 不支持 Rerank 模型，所以需要单独配置接入，这里
-
-
-### 使用硅基流动的在线模型
-
-有免费的 `bge-reranker-v2-m3` 模型可以使用。
-
-1. [点击注册硅基流动账号](https://cloud.siliconflow.cn/i/TR9Ym0c4)
-2. 进入控制台，获取 API key: https://cloud.siliconflow.cn/account/ak
-3. 修改 FastGPT 配置文件
-
-```json
-{
-    "reRankModels": [
-        {
-            "model": "BAAI/bge-reranker-v2-m3", // 这里的model需要对应 siliconflow 的模型名
-            "name": "BAAI/bge-reranker-v2-m3",
-            "requestUrl": "https://api.siliconflow.cn/v1/rerank",
-            "requestAuth": "siliconflow 上申请的 key"
-        }
-    ]
-}
-```
-
-### 私有部署模型
-
-请使用 4.6.6-alpha 以上版本，配置文件中的 `reRankModels` 为重排模型，虽然是数组，不过目前仅有第1个生效。
-
-1. [部署 ReRank 模型](/docs/development/custom-models/bge-rerank/)
-1. 找到 FastGPT 的配置文件中的 `reRankModels`， 4.6.6 以前是 `ReRankModels`。
-2. 修改对应的值：
-
-```json
-{
-    "reRankModels": [
-        {
-            "model": "bge-reranker-base", // 随意
-            "name": "检索重排-base", // 随意
-            "charsPointsPrice": 0,
-            "requestUrl": "{{host}}/v1/rerank",
-            "requestAuth": "安全凭证，已自动补 Bearer"
-        }
-    ]
-}
-```
+```

docSite/content/zh-cn/docs/development/custom-models/bge-rerank.md

@@ -118,10 +118,17 @@ services:
 ```
 ## 接入 FastGPT
 
-参考 [ReRank模型接入](/docs/development/configuration/#rerank-接入)，host 变量为部署的域名。
+1. 打开 FastGPT 模型配置，新增一个重排模型。
+2. 填写模型配置表单：模型 ID 为`bge-reranker-base`，地址填写`{{host}}/v1/rerank`，host 为你部署的域名/IP:Port。
+
+![alt text](/imgs/image-102.png)
 
 ## QA
 
+### 403报错
+
+FastGPT中，自定义请求 Token 和环境变量的 ACCESS_TOKEN 不一致。 
+
 ### Docker 运行提示 `Bus error (core dumped)`
 
 尝试增加 `docker-compose.yml` 配置项 `shm_size` ，以增加容器中的共享内存目录大小。

docSite/content/zh-cn/docs/development/custom-models/xinference.md

@@ -144,7 +144,6 @@ curl --location --request POST 'https://<oneapi_url>/v1/chat/completions' \
       "usedInClassify": true, // 是否用于问题分类（务必保证至少有一个为true）
       "usedInExtractFields": true, // 是否用于内容提取（务必保证至少有一个为true）
       "usedInToolCall": true, // 是否用于工具调用（务必保证至少有一个为true）
-      "usedInQueryExtension": true, // 是否用于问题优化（务必保证至少有一个为true）
       "toolChoice": true, // 是否支持工具选择（分类，内容提取，工具调用会用到。）
       "functionCall": false, // 是否支持函数调用（分类，内容提取，工具调用会用到。会优先使用 toolChoice，如果为false，则使用 functionCall，如果仍为 false，则使用提示词模式）
       "customCQPrompt": "", // 自定义文本分类提示词（不支持工具和函数调用的模型

docSite/content/zh-cn/docs/development/docker.md

@@ -202,6 +202,10 @@ docker restart oneapi
 
 首次运行，会自动初始化 root 用户，密码为 `1234`（与环境变量中的`DEFAULT_ROOT_PSW`一致），日志里会提示一次`MongoServerError: Unable to read from a snapshot due to pending collection catalog changes;`可忽略。
 
+### 6. 配置模型
+
+[点击查看模型配置教程](/docs/development/modelConfig/intro/)
+
 ## FAQ
 
 ### Mongo 副本集自动初始化失败

docSite/content/zh-cn/docs/development/faq.md

@@ -23,11 +23,11 @@ images: []
 ![](/imgs/faq1.png)
 这是索引模型的长度限制，通过任何方式部署都一样的，但不同索引模型的配置不一样，可以在后台修改参数。
 
-### sealos怎么挂载 小程序配置文件
+### 怎么挂载小程序配置文件
 
-新增配置文件：/app/projects/app/public/xxxx.txt
+将验证文件，挂载到指定位置：/app/projects/app/public/xxxx.txt
 
-如图:
+然后重启。例如:
 
 ![](/imgs/faq2.png)
 

docSite/content/zh-cn/docs/development/modelConfig/intro.md

@@ -0,0 +1,412 @@
+---
+title: 'FastGPT 模型配置说明'
+description: 'FastGPT 模型配置说明'
+icon: 'api'
+draft: false
+toc: true
+weight: 744
+---
+
+在 4.8.20 版本以前，FastGPT 模型配置在 `config.json` 文件中声明，你可以在 https://github.com/labring/FastGPT/blob/main/projects/app/data/model.json 中找到旧版的配置文件示例。
+
+从 4.8.20 版本开始，你可以直接在 FastGPT 页面中进行模型配置，并且系统内置了大量模型，无需从 0 开始配置。下面介绍模型配置的基本流程：
+
+## 1. 使用 OneAPI 对接模型提供商
+
+可以使用 [OneAPI 接入教程](/docs/development/modelconfig/one-api) 来进行模型聚合，从而可以对接更多模型提供商。你需要先在各服务商申请好 API 接入 OneAPI 后，才能在 FastGPT 中使用这些模型。示例流程如下：
+
+![alt text](/imgs/image-95.png)
+
+除了各模型官方的服务外，还有一些第三方服务商提供模型接入服务，当然你也可以用 Ollama 等来部署本地模型，最终都需要接入 OneAPI，下面是一些第三方服务商：
+
+{{% alert icon=" " context="info" %}}
+- [SiliconCloud(硅基流动)](https://cloud.siliconflow.cn/i/TR9Ym0c4): 提供开源模型调用的平台。
+- [Sealos AIProxy](https://hzh.sealos.run/?openapp=system-aiproxy): 提供国内各家模型代理，无需逐一申请 api。
+{{% /alert %}}
+
+在 OneAPI 配置好模型后，你就可以打开 FastGPT 页面，启用对应模型了。
+
+## 2. 登录 root 用户
+
+仅 root 用户可以进行模型配置。
+
+## 3. 进入模型配置页面
+
+登录 root 用户后，在`账号-模型提供商-模型配置`中，你可以看到所有内置的模型和自定义模型，以及哪些模型启用了。
+
+![alt text](/image-90.png)
+
+## 4. 配置介绍
+
+{{% alert icon="🤖 " context="success" %}}
+注意：目前语音识别模型和重排模型仅会生效一个，所以配置时候，只需要配置一个即可。
+{{% /alert %}}
+
+### 核心配置
+
+- 模型 ID：实际发出请求的`model`值，全局唯一。
+- 自定义请求地址/Token：如果需要绕过`OneAPI`，可以设置自定义请求地址和 Token。一般情况下不需要，如果 OneAPI 不支持某些模型，可以使用该特性。
+
+### 模型类型
+
+1. 语言模型 - 进行文本对话，多模态模型支持图片识别。
+2. 索引模型 - 对文本块进行索引，用于相关文本检索。
+3. 语音合成 - 将文本转换为语音。
+4. 语音识别 - 将语音转换为文本。
+5. 重排模型 - 对文本进行重排，用于优化文本质量。
+
+### 启用模型
+
+系统内置了目前主流厂商的模型，如果你不熟悉配置，直接点击`启用`即可，需要注意到是，模型 ID 需要和 OneAPI 中渠道的`模型`一致。
+
+| | |
+| --- | --- |
+| ![alt text](/imgs/image-91.png) | ![alt text](/imgs/image-92.png) |
+
+### 修改模型配置
+
+点击模型右侧的齿轮即可进行模型配置，不同类型模型的配置有区别。
+
+| | |
+| --- | --- |
+| ![alt text](/imgs/image-93.png) | ![alt text](/imgs/image-94.png) |
+
+### 新增自定义模型
+
+如果系统内置的模型无法满足你的需求，你可以添加自定义模型。自定义模型中，如果`模型 ID`与系统内置的模型 ID 一致，则会被认为是修改系统模型。
+
+| | |
+| --- | --- |
+| ![alt text](/imgs/image-96.png) | ![alt text](/imgs/image-97.png) |
+
+### 通过配置文件配置
+
+如果你觉得通过页面配置模型比较麻烦，你也可以通过配置文件来配置模型。或者希望快速将一个系统的配置，复制到另一个系统，也可以通过配置文件来实现。
+
+| | |
+| --- | --- |
+| ![alt text](/imgs/image-98.png) | ![alt text](/imgs/image-99.png) |
+
+**语言模型字段说明：**
+
+```json
+{
+    "model": "模型 ID",
+    "metadata": {
+        "isCustom": true, // 是否为自定义模型
+        "isActive": true, // 是否启用
+        "provider": "OpenAI", // 模型提供商，主要用于分类展示，目前已经内置提供商包括：https://github.com/labring/FastGPT/blob/main/packages/global/core/ai/provider.ts, 可 pr 提供新的提供商，或直接填写 Other
+        "model": "gpt-4o-mini", // 模型ID(对应OneAPI中渠道的模型名)
+        "name": "gpt-4o-mini", // 模型别名
+        "maxContext": 125000, // 最大上下文
+        "maxResponse": 16000, // 最大回复
+        "quoteMaxToken": 120000, // 最大引用内容
+        "maxTemperature": 1.2, // 最大温度
+        "charsPointsPrice": 0, // n积分/1k token（商业版）
+        "censor": false, // 是否开启敏感校验（商业版）
+        "vision": true, // 是否支持图片输入
+        "datasetProcess": true, // 是否设置为文本理解模型（QA），务必保证至少有一个为true，否则知识库会报错
+        "usedInClassify": true, // 是否用于问题分类（务必保证至少有一个为true）
+        "usedInExtractFields": true, // 是否用于内容提取（务必保证至少有一个为true）
+        "usedInToolCall": true, // 是否用于工具调用（务必保证至少有一个为true）
+        "toolChoice": true, // 是否支持工具选择（分类，内容提取，工具调用会用到。）
+        "functionCall": false, // 是否支持函数调用（分类，内容提取，工具调用会用到。会优先使用 toolChoice，如果为false，则使用 functionCall，如果仍为 false，则使用提示词模式）
+        "customCQPrompt": "", // 自定义文本分类提示词（不支持工具和函数调用的模型
+        "customExtractPrompt": "", // 自定义内容提取提示词
+        "defaultSystemChatPrompt": "", // 对话默认携带的系统提示词
+        "defaultConfig": {}, // 请求API时，挟带一些默认配置（比如 GLM4 的 top_p）
+        "fieldMap": {} // 字段映射（o1 模型需要把 max_tokens 映射为 max_completion_tokens）
+    }
+}
+```
+
+**索引模型字段说明:**
+
+```json
+{
+    "model": "模型 ID",
+    "metadata": {
+        "isCustom": true, // 是否为自定义模型
+        "isActive": true, // 是否启用
+        "provider": "OpenAI", // 模型提供商
+        "model": "text-embedding-3-small", // 模型ID
+        "name": "text-embedding-3-small", // 模型别名
+        "charsPointsPrice": 0, // n积分/1k token
+        "defaultToken": 512, // 默认文本分割时候的 token
+        "maxToken": 3000 // 最大 token
+    }
+}
+```
+
+**重排模型字段说明:**
+
+```json
+{
+    "model": "模型 ID",
+    "metadata": {
+        "isCustom": true, // 是否为自定义模型
+        "isActive": true, // 是否启用
+        "provider": "BAAI", // 模型提供商
+        "model": "bge-reranker-v2-m3", // 模型ID
+        "name": "ReRanker-Base", // 模型别名
+        "requestUrl": "", // 自定义请求地址
+        "requestAuth": "", // 自定义请求认证
+        "type": "rerank" // 模型类型
+    }
+}
+```
+
+**语音合成模型字段说明:**
+
+```json
+{
+    "model": "模型 ID",
+    "metadata": {
+      "isActive": true, // 是否启用
+      "isCustom": true, // 是否为自定义模型
+      "type": "tts", // 模型类型
+      "provider": "FishAudio", // 模型提供商
+      "model": "fishaudio/fish-speech-1.5", // 模型ID
+      "name": "fish-speech-1.5", // 模型别名
+      "voices": [ // 音色
+        {
+          "label": "fish-alex", // 音色名称
+          "value": "fishaudio/fish-speech-1.5:alex", // 音色ID
+        },
+        {
+          "label": "fish-anna", // 音色名称
+          "value": "fishaudio/fish-speech-1.5:anna", // 音色ID
+        }
+      ],
+      "charsPointsPrice": 0 // n积分/1k token
+    }
+}
+```
+
+**语音识别模型字段说明:**
+
+```json
+{
+    "model": "whisper-1",
+    "metadata": {
+      "isActive": true, // 是否启用
+      "isCustom": true, // 是否为自定义模型
+      "provider": "OpenAI", // 模型提供商
+      "model": "whisper-1", // 模型ID
+      "name": "whisper-1", // 模型别名
+      "charsPointsPrice": 0, // n积分/1k token
+      "type": "stt" // 模型类型
+    }
+}
+```
+
+## 模型测试
+
+FastGPT 页面上提供了每类模型的简单测试，可以初步检查模型是否正常工作，会实际按模板发送一个请求。
+
+![alt text](/imgs/image-105.png)
+
+## 模型接入示例
+
+### ReRank 模型接入
+
+由于 OneAPI 不支持 Rerank 模型，所以需要单独配置。FastGPT 中，模型配置支持自定义请求地址，可以绕过 OneAPI，直接向提供商发起请求，可以利用这个特性来接入 Rerank 模型。
+
+
+#### 使用硅基流动的在线模型
+
+有免费的 `bge-reranker-v2-m3` 模型可以使用。
+
+1. [点击注册硅基流动账号](https://cloud.siliconflow.cn/i/TR9Ym0c4)
+2. 进入控制台，获取 API key: https://cloud.siliconflow.cn/account/ak
+3. 打开 FastGPT 模型配置，新增一个`BAAI/bge-reranker-v2-m3`的重排模型（如果系统内置了，也可以直接变更,无需新增）。
+
+![alt text](/imgs/image-101.png)
+
+#### 私有部署模型
+
+[点击查看部署 ReRank 模型教程](/docs/development/custom-models/bge-rerank/)
+
+
+## 旧版模型配置说明
+
+配置好 OneAPI 后，需要在`config.json`文件中，手动的增加模型配置，并重启。
+
+由于环境变量不利于配置复杂的内容，FastGPT 采用了 ConfigMap 的形式挂载配置文件，你可以在 `projects/app/data/config.json` 看到默认的配置文件。可以参考 [docker-compose 快速部署](/docs/development/docker/) 来挂载配置文件。
+
+**开发环境下**，你需要将示例配置文件 `config.json` 复制成 `config.local.json` 文件才会生效。  
+**Docker部署**，修改`config.json` 文件，需要重启容器。
+
+下面配置文件示例中包含了系统参数和各个模型配置：
+
+```json
+{
+  "feConfigs": {
+    "lafEnv": "https://laf.dev" // laf环境。 https://laf.run （杭州阿里云） ,或者私有化的laf环境。如果使用 Laf openapi 功能，需要最新版的 laf 。
+  },
+  "systemEnv": {
+    "vectorMaxProcess": 15, // 向量处理线程数量
+    "qaMaxProcess": 15, // 问答拆分线程数量
+    "tokenWorkers": 50, // Token 计算线程保持数，会持续占用内存，不能设置太大。
+    "pgHNSWEfSearch": 100 // 向量搜索参数。越大，搜索越精确，但是速度越慢。设置为100，有99%+精度。
+  },
+  "llmModels": [
+    {
+      "provider": "OpenAI", // 模型提供商，主要用于分类展示，目前已经内置提供商包括：https://github.com/labring/FastGPT/blob/main/packages/global/core/ai/provider.ts, 可 pr 提供新的提供商，或直接填写 Other
+      "model": "gpt-4o-mini", // 模型名(对应OneAPI中渠道的模型名)
+      "name": "gpt-4o-mini", // 模型别名
+      "maxContext": 125000, // 最大上下文
+      "maxResponse": 16000, // 最大回复
+      "quoteMaxToken": 120000, // 最大引用内容
+      "maxTemperature": 1.2, // 最大温度
+      "charsPointsPrice": 0, // n积分/1k token（商业版）
+      "censor": false, // 是否开启敏感校验（商业版）
+      "vision": true, // 是否支持图片输入
+      "datasetProcess": true, // 是否设置为文本理解模型（QA），务必保证至少有一个为true，否则知识库会报错
+      "usedInClassify": true, // 是否用于问题分类（务必保证至少有一个为true）
+      "usedInExtractFields": true, // 是否用于内容提取（务必保证至少有一个为true）
+      "usedInToolCall": true, // 是否用于工具调用（务必保证至少有一个为true）
+      "toolChoice": true, // 是否支持工具选择（分类，内容提取，工具调用会用到。）
+      "functionCall": false, // 是否支持函数调用（分类，内容提取，工具调用会用到。会优先使用 toolChoice，如果为false，则使用 functionCall，如果仍为 false，则使用提示词模式）
+      "customCQPrompt": "", // 自定义文本分类提示词（不支持工具和函数调用的模型
+      "customExtractPrompt": "", // 自定义内容提取提示词
+      "defaultSystemChatPrompt": "", // 对话默认携带的系统提示词
+      "defaultConfig": {}, // 请求API时，挟带一些默认配置（比如 GLM4 的 top_p）
+      "fieldMap": {} // 字段映射（o1 模型需要把 max_tokens 映射为 max_completion_tokens）
+    },
+    {
+      "provider": "OpenAI",
+      "model": "gpt-4o",
+      "name": "gpt-4o",
+      "maxContext": 125000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 1.2,
+      "charsPointsPrice": 0,
+      "censor": false,
+      "vision": true,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "defaultConfig": {},
+      "fieldMap": {}
+    },
+    {
+      "provider": "OpenAI",
+      "model": "o1-mini",
+      "name": "o1-mini",
+      "maxContext": 125000,
+      "maxResponse": 65000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 1.2,
+      "charsPointsPrice": 0,
+      "censor": false,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "defaultConfig": {
+        "temperature": 1,
+        "max_tokens": null,
+        "stream": false
+      }
+    },
+    {
+      "provider": "OpenAI",
+      "model": "o1-preview",
+      "name": "o1-preview",
+      "maxContext": 125000,
+      "maxResponse": 32000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 1.2,
+      "charsPointsPrice": 0,
+      "censor": false,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "defaultConfig": {
+         "temperature": 1,
+        "max_tokens": null,
+        "stream": false
+      }
+    }
+  ],
+  "vectorModels": [
+    {
+      "provider": "OpenAI",
+      "model": "text-embedding-3-small", 
+      "name": "text-embedding-3-small",
+      "charsPointsPrice": 0,
+      "defaultToken": 512,
+      "maxToken": 3000,
+      "weight": 100
+    },
+    {
+      "provider": "OpenAI",
+      "model": "text-embedding-3-large",
+      "name": "text-embedding-3-large",
+      "charsPointsPrice": 0,
+      "defaultToken": 512,
+      "maxToken": 3000,
+      "weight": 100,
+      "defaultConfig": {
+        "dimensions": 1024
+      }
+    },
+    {
+      "provider": "OpenAI",
+      "model": "text-embedding-ada-002", // 模型名（与OneAPI对应）
+      "name": "Embedding-2", // 模型展示名
+      "charsPointsPrice": 0, // n积分/1k token
+      "defaultToken": 700, // 默认文本分割时候的 token
+      "maxToken": 3000, // 最大 token
+      "weight": 100, // 优先训练权重
+      "defaultConfig": {}, // 自定义额外参数。例如，如果希望使用 embedding3-large 的话，可以传入 dimensions:1024，来返回1024维度的向量。（目前必须小于1536维度）
+      "dbConfig": {}, // 存储时的额外参数（非对称向量模型时候需要用到）
+      "queryConfig": {} // 参训时的额外参数
+    }
+  ],
+  "reRankModels": [],
+  "audioSpeechModels": [
+    {
+      "provider": "OpenAI",
+      "model": "tts-1",
+      "name": "OpenAI TTS1",
+      "charsPointsPrice": 0,
+      "voices": [
+        { "label": "Alloy", "value": "alloy", "bufferId": "openai-Alloy" },
+        { "label": "Echo", "value": "echo", "bufferId": "openai-Echo" },
+        { "label": "Fable", "value": "fable", "bufferId": "openai-Fable" },
+        { "label": "Onyx", "value": "onyx", "bufferId": "openai-Onyx" },
+        { "label": "Nova", "value": "nova", "bufferId": "openai-Nova" },
+        { "label": "Shimmer", "value": "shimmer", "bufferId": "openai-Shimmer" }
+      ]
+    }
+  ],
+  "whisperModel": {
+    "provider": "OpenAI",
+    "model": "whisper-1",
+    "name": "Whisper1",
+    "charsPointsPrice": 0
+  }
+}
+```

docSite/content/zh-cn/docs/development/modelConfig/one-api.md

@@ -94,70 +94,16 @@ CHAT_API_KEY=sk-xxxxxx
 
 ![](/imgs/oneapi-demo1.png)
 
-### 2. 修改 FastGPT 配置文件
+### 2. 修改 FastGPT 模型配置
 
-可以在 `/projects/app/src/data/config.json` 里找到配置文件（本地开发需要复制成 config.local.json）,按下面内容修改配置文件，最新/更具体的配置说明，可查看[FastGPT 配置文件说明](/docs/development/configuration)。
+打开 FastGPT 模型配置，启动文心千帆模型，如果希望未内置，可以通过新增模型来配置。
 
-配置模型关键点在于`model` 需要与 OneAPI 渠道中的模型一致。
-
-```json
-{
-  "llmModels": [ // 语言模型配置
-    {
-      "model": "ERNIE-Bot", // 这里的模型需要对应 One API 的模型
-      "name": "文心一言", // 对外展示的名称
-      "avatar": "/imgs/model/openai.svg", // 模型的logo
-      "maxContext": 16000, // 最大上下文
-      "maxResponse": 4000, // 最大回复
-      "quoteMaxToken": 13000, // 最大引用内容
-      "maxTemperature": 1.2, // 最大温度
-      "charsPointsPrice": 0, 
-      "censor": false,
-      "vision": false, // 是否支持图片输入
-      "datasetProcess": true, // 是否设置为知识库处理模型
-      "usedInClassify": true, // 是否用于问题分类
-      "usedInExtractFields": true, // 是否用于字段提取
-      "usedInToolCall": true, // 是否用于工具调用
-      "usedInQueryExtension": true, // 是否用于问题优化
-      "toolChoice": true, // 是否支持工具选择
-      "functionCall": false, // 是否支持函数调用
-      "customCQPrompt": "", // 自定义文本分类提示词（不支持工具和函数调用的模型
-      "customExtractPrompt": "", // 自定义内容提取提示词
-      "defaultSystemChatPrompt": "", // 对话默认携带的系统提示词
-      "defaultConfig":{}  // 请求API时，挟带一些默认配置（比如 GLM4 的 top_p）
-    }
-  ],
-  "vectorModels": [ // 向量模型配置
-    {
-      "model": "text-embedding-ada-002",
-      "name": "Embedding-2",
-      "avatar": "/imgs/model/openai.svg",
-      "charsPointsPrice": 0,
-      "defaultToken": 700,
-      "maxToken": 3000,
-      "weight": 100
-    },
-  ]
-}
-```
-
-### 3. 重启 FastGPT
-
-**Docker 版本**
-
-```bash
-docker-compose down
-docker-compose up -d
-```
-
-**Sealos 版本**
-
-直接找到 FastGPT 服务，点击重启即可。
+![alt text](/imgs/image-103.png)
 
 
 ## 其他服务商接入参考
 
-这章介绍一些提供商接入 OneAPI 的教程，配置后不要忘记修改 FastGPT 配置文件。
+这章介绍一些提供商接入 OneAPI 的教程，配置后不要忘记在 FastGPT 模型配置中启用。
 
 ### 阿里通义千问
 

docSite/content/zh-cn/docs/development/modelConfig/siliconCloud.md

@@ -27,139 +27,13 @@ OPENAI_BASE_URL=https://api.siliconflow.cn/v1
 CHAT_API_KEY=sk-xxxxxx
 ```
 
-## 3. 修改 FastGPT 配置文件
+## 3. 修改 FastGPT 模型配置
 
-我们选取 SiliconCloud 中的模型作为 FastGPT 配置。这里配置了 `Qwen2.5 72b` 的纯语言和视觉模型；选择 `bge-m3` 作为向量模型；选择 `bge-reranker-v2-m3` 作为重排模型。选择 `fish-speech-1.5` 作为语音模型；选择 `SenseVoiceSmall` 作为语音输入模型。
+系统内置了几个硅基流动的模型进行体验，如果需要其他模型，可以手动添加。
 
-注意：ReRank 模型仍需配置一次 Api Key
+这里启动了 `Qwen2.5 72b` 的纯语言和视觉模型；选择 `bge-m3` 作为向量模型；选择 `bge-reranker-v2-m3` 作为重排模型。选择 `fish-speech-1.5` 作为语音模型；选择 `SenseVoiceSmall` 作为语音输入模型。
 
-```json
-{
-    "llmModels": [
-    {
-      "provider": "Other", // 模型提供商，主要用于分类展示，目前已经内置提供商包括：https://github.com/labring/FastGPT/blob/main/packages/global/core/ai/provider.ts, 可 pr 提供新的提供商，或直接填写 Other
-      "model": "Qwen/Qwen2.5-72B-Instruct", // 模型名(对应OneAPI中渠道的模型名)
-      "name": "Qwen2.5-72B-Instruct", // 模型别名
-      "maxContext": 32000, // 最大上下文
-      "maxResponse": 4000, // 最大回复
-      "quoteMaxToken": 30000, // 最大引用内容
-      "maxTemperature": 1, // 最大温度
-      "charsPointsPrice": 0, // n积分/1k token（商业版）
-      "censor": false, // 是否开启敏感校验（商业版）
-      "vision": false, // 是否支持图片输入
-      "datasetProcess": true, // 是否设置为文本理解模型（QA），务必保证至少有一个为true，否则知识库会报错
-      "usedInClassify": true, // 是否用于问题分类（务必保证至少有一个为true）
-      "usedInExtractFields": true, // 是否用于内容提取（务必保证至少有一个为true）
-      "usedInToolCall": true, // 是否用于工具调用（务必保证至少有一个为true）
-      "usedInQueryExtension": true, // 是否用于问题优化（务必保证至少有一个为true）
-      "toolChoice": true, // 是否支持工具选择（分类，内容提取，工具调用会用到。）
-      "functionCall": false, // 是否支持函数调用（分类，内容提取，工具调用会用到。会优先使用 toolChoice，如果为false，则使用 functionCall，如果仍为 false，则使用提示词模式）
-      "customCQPrompt": "", // 自定义文本分类提示词（不支持工具和函数调用的模型
-      "customExtractPrompt": "", // 自定义内容提取提示词
-      "defaultSystemChatPrompt": "", // 对话默认携带的系统提示词
-      "defaultConfig": {}, // 请求API时，挟带一些默认配置（比如 GLM4 的 top_p）
-      "fieldMap": {} // 字段映射（o1 模型需要把 max_tokens 映射为 max_completion_tokens）
-    },
-    {
-      "provider": "Other",
-      "model": "Qwen/Qwen2-VL-72B-Instruct",
-      "name": "Qwen2-VL-72B-Instruct",
-      "maxContext": 32000,
-      "maxResponse": 4000,
-      "quoteMaxToken": 30000,
-      "maxTemperature": 1,
-      "charsPointsPrice": 0,
-      "censor": false,
-      "vision": true,
-      "datasetProcess": false,
-      "usedInClassify": false,
-      "usedInExtractFields": false,
-      "usedInToolCall": false,
-      "usedInQueryExtension": false,
-      "toolChoice": false,
-      "functionCall": false,
-      "customCQPrompt": "",
-      "customExtractPrompt": "",
-      "defaultSystemChatPrompt": "",
-      "defaultConfig": {}
-    }
-  ],
-  "vectorModels": [
-    {
-      "provider": "Other",
-      "model": "Pro/BAAI/bge-m3",
-      "name": "Pro/BAAI/bge-m3",
-      "charsPointsPrice": 0,
-      "defaultToken": 512,
-      "maxToken": 5000,
-      "weight": 100
-    }
-  ],
-  "reRankModels": [
-    {
-        "model": "BAAI/bge-reranker-v2-m3", // 这里的model需要对应 siliconflow 的模型名
-        "name": "BAAI/bge-reranker-v2-m3",
-        "requestUrl": "https://api.siliconflow.cn/v1/rerank",
-        "requestAuth": "siliconflow 上申请的 key"
-    }
-  ],
-  "audioSpeechModels": [
-    {
-        "model": "fishaudio/fish-speech-1.5",
-        "name": "fish-speech-1.5",
-        "voices": [
-            {
-                "label": "fish-alex",
-                "value": "fishaudio/fish-speech-1.5:alex",
-                "bufferId": "fish-alex"
-            },
-            {
-                "label": "fish-anna",
-                "value": "fishaudio/fish-speech-1.5:anna",
-                "bufferId": "fish-anna"
-            },
-            {
-                "label": "fish-bella",
-                "value": "fishaudio/fish-speech-1.5:bella",
-                "bufferId": "fish-bella"
-            },
-            {
-                "label": "fish-benjamin",
-                "value": "fishaudio/fish-speech-1.5:benjamin",
-                "bufferId": "fish-benjamin"
-            },
-            {
-                "label": "fish-charles",
-                "value": "fishaudio/fish-speech-1.5:charles",
-                "bufferId": "fish-charles"
-            },
-            {
-                "label": "fish-claire",
-                "value": "fishaudio/fish-speech-1.5:claire",
-                "bufferId": "fish-claire"
-            },
-            {
-                "label": "fish-david",
-                "value": "fishaudio/fish-speech-1.5:david",
-                "bufferId": "fish-david"
-            },
-            {
-                "label": "fish-diana",
-                "value": "fishaudio/fish-speech-1.5:diana",
-                "bufferId": "fish-diana"
-            }
-        ]
-    }
-  ],
-  "whisperModel": {
-    "model": "FunAudioLLM/SenseVoiceSmall",
-    "name": "SenseVoiceSmall",
-    "charsPointsPrice": 0
-  }
-}
-```
-
-## 4. 重启 FastGPT
+![alt text](/imgs/image-104.png)
 
 ## 5. 体验测试
 

docSite/content/zh-cn/docs/development/sealos.md

@@ -34,7 +34,7 @@ FastGPT 使用了 one-api 项目来管理模型池，其可以兼容 OpenAI 、A
 
 <a href="https://bja.sealos.run/?openapp=system-template%3FtemplateName%3Dfastgpt" rel="external" target="_blank"><img src="https://raw.githubusercontent.com/labring-actions/templates/main/Deploy-on-Sealos.svg" alt="Deploy on Sealos"/></a>
 
-### 开始部署
+### 1. 开始部署
 
 由于需要部署数据库，部署完后需要等待 2~4 分钟才能正常访问。默认用了最低配置，首次访问时会有些慢。
 
@@ -52,27 +52,15 @@ FastGPT 使用了 one-api 项目来管理模型池，其可以兼容 OpenAI 、A
 
 ![](/imgs/sealos2.png)
 
-### 登录
+### 2. 登录
 
 用户名：`root`
 
 密码是刚刚一键部署时设置的`root_password`
 
-### 修改配置文件和环境变量
+### 3. 配置模型
 
-在 Sealos 中，你可以打开`应用管理`（App Launchpad）看到部署的 FastGPT，可以打开`数据库`（Database）看到对应的数据库。
-
-在`应用管理`中，选中 FastGPT，点击变更，可以看到对应的环境变量和配置文件。
-
-![](/imgs/fastgptonsealos1.png)
-
-{{% alert icon="🤖 " context="success" %}}
-在 Sealos 上，FastGPT 一共运行了 1 个服务和 2 个数据库，如暂停和删除请注意数据库一同操作。（你可以白天启动，晚上暂停它们，省钱大法）
-{{% /alert %}}
-
-### 更新
-
-点击变更或重启会自动拉取镜像更新，请确保镜像`tag`正确。建议不要使用`latest`，改成固定版本号。
+[点击查看模型配置教程](/docs/development/modelConfig/intro/)
 
 ## 收费
 
@@ -88,7 +76,20 @@ FastGPT 商业版共包含了2个应用（fastgpt, fastgpt-plus）和2个数据
 
 点击右侧的详情，可以查看对应应用的详细信息。
 
+### 修改配置文件和环境变量
+
+在 Sealos 中，你可以打开`应用管理`（App Launchpad）看到部署的 FastGPT，可以打开`数据库`（Database）看到对应的数据库。
+
+在`应用管理`中，选中 FastGPT，点击变更，可以看到对应的环境变量和配置文件。
+
+![](/imgs/fastgptonsealos1.png)
+
+{{% alert icon="🤖 " context="success" %}}
+在 Sealos 上，FastGPT 一共运行了 1 个服务和 2 个数据库，如暂停和删除请注意数据库一同操作。（你可以白天启动，晚上暂停它们，省钱大法）
+{{% /alert %}}
+
 ### 如何更新/升级 FastGPT
+
 [升级脚本文档](https://doc.tryfastgpt.ai/docs/development/upgrading/)先看下文档，看下需要升级哪个版本。注意，不要跨版本升级！！！！！
 
 例如，目前是4.5 版本，要升级到4.5.1，就先把镜像版本改成v4.5.1，执行一下升级脚本，等待完成后再继续升级。如果目标版本不需要执行初始化，则可以跳过。
@@ -148,8 +149,6 @@ SYSTEM_FAVICON 可以是一个网络地址
 
 ![](/imgs/onsealos8.png)
 
-### 管理后台(已合并到plus)
-
 ### 商业版镜像配置文件
 
 ```

docSite/content/zh-cn/docs/development/upgrading/4811.md

@@ -31,7 +31,6 @@ weight: 813
     "usedInClassify": true,
     "usedInExtractFields": true,
     "usedInToolCall": true,
-    "usedInQueryExtension": true,
     "toolChoice": false,
     "functionCall": false,
     "customCQPrompt": "",
@@ -56,7 +55,6 @@ weight: 813
     "usedInClassify": true,
     "usedInExtractFields": true,
     "usedInToolCall": true,
-    "usedInQueryExtension": true,
     "toolChoice": false,
     "functionCall": false,
     "customCQPrompt": "",

docSite/content/zh-cn/docs/development/upgrading/4820.md

@@ -0,0 +1,38 @@
+---
+title: 'V4.8.20(进行中)'
+description: 'FastGPT V4.8.20 更新说明'
+icon: 'upgrade'
+draft: false
+toc: true
+weight: 804
+---
+
+## 更新指南
+
+### 1. 更新环境变量
+
+如果有很早版本用户，配置了`ONEAPI_URL`的，需要统一改成`OPENAI_BASE_URL`
+
+### 1. 更新镜像：
+
+
+### 2. 运行升级脚本
+
+从任意终端，发起 1 个 HTTP 请求。其中 {{rootkey}} 替换成环境变量里的 `rootkey`；{{host}} 替换成**FastGPT 域名**。
+
+```bash
+curl --location --request POST 'https://{{host}}/api/admin/initv4820' \
+--header 'rootkey: {{rootkey}}' \
+--header 'Content-Type: application/json'
+```
+
+自动把原配置文件的模型加载到新版模型配置中
+
+## 完整更新内容
+
+1. 新增 - 可视化模型参数配置。预设超过 100 个模型配置。同时支持所有类型模型的一键测试。（预计下个版本会完全支持在页面上配置渠道）。
+2. 新增 - 使用记录导出和仪表盘。
+3. 新增 - markdown 语法扩展，支持音视频（代码块 audio 和 video）。
+4. 优化 - 页面组件抽离，减少页面组件路由。
+5. 优化 - 全文检索，忽略大小写。
+6. 优化 - 问答生成和增强索引改成流输出，避免部分模型超时。

files/helm/fastgpt/templates/configmap-config.yaml

@@ -23,7 +23,6 @@ data:
           "usedInClassify": true,
           "usedInExtractFields": true,
           "usedInToolCall": true,
-          "usedInQueryExtension": true,
           "toolChoice": true,
           "functionCall": false,
           "customCQPrompt": "",
@@ -45,7 +44,6 @@ data:
           "usedInClassify": true,
           "usedInExtractFields": true,
           "usedInToolCall": true,
-          "usedInQueryExtension": true,
           "toolChoice": true,
           "functionCall": false,
           "customCQPrompt": "",
@@ -67,7 +65,6 @@ data:
           "usedInClassify": true,
           "usedInExtractFields": true,
           "usedInToolCall": true,
-          "usedInQueryExtension": true,
           "toolChoice": true,
           "functionCall": false,
           "customCQPrompt": "",
@@ -89,7 +86,6 @@ data:
           "usedInClassify": false,
           "usedInExtractFields": false,
           "usedInToolCall": false,
-          "usedInQueryExtension": false,
           "toolChoice": true,
           "functionCall": false,
           "customCQPrompt": "",

packages/global/common/error/code/user.ts

@@ -2,12 +2,22 @@ import { ErrType } from '../errorCode';
 import { i18nT } from '../../../../web/i18n/utils';
 /* team: 503000 */
 export enum UserErrEnum {
+  notUser = 'notUser',
+  userExist = 'userExist',
   unAuthRole = 'unAuthRole',
   account_psw_error = 'account_psw_error',
   balanceNotEnough = 'balanceNotEnough',
   unAuthSso = 'unAuthSso'
 }
 const errList = [
+  {
+    statusText: UserErrEnum.notUser,
+    message: i18nT('common:code_error.account_not_found')
+  },
+  {
+    statusText: UserErrEnum.userExist,
+    message: i18nT('common:code_error.account_exist')
+  },
   {
     statusText: UserErrEnum.account_psw_error,
     message: i18nT('common:code_error.account_error')

packages/global/common/system/types/index.d.ts

@@ -3,7 +3,7 @@ import type {
   ChatModelItemType,
   FunctionModelItemType,
   LLMModelItemType,
-  VectorModelItemType,
+  EmbeddingModelItemType,
   AudioSpeechModels,
   STTModelType,
   ReRankModelItemType
@@ -31,11 +31,13 @@ export type FastGPTConfigFileType = {
   feConfigs: FastGPTFeConfigsType;
   systemEnv: SystemEnvType;
   subPlans?: SubPlanType;
-  llmModels: ChatModelItemType[];
-  vectorModels: VectorModelItemType[];
-  reRankModels: ReRankModelItemType[];
-  audioSpeechModels: AudioSpeechModelType[];
-  whisperModel: STTModelType;
+
+  // Abandon
+  llmModels?: ChatModelItemType[];
+  vectorModels?: EmbeddingModelItemType[];
+  reRankModels?: ReRankModelItemType[];
+  audioSpeechModels?: TTSModelType[];
+  whisperModel?: STTModelType;
 };
 
 export type FastGPTFeConfigsType = {

packages/global/core/ai/constants.ts

@@ -15,15 +15,13 @@ export enum LLMModelTypeEnum {
   all = 'all',
   classify = 'classify',
   extractFields = 'extractFields',
-  toolCall = 'toolCall',
-  queryExtension = 'queryExtension'
+  toolCall = 'toolCall'
 }
 export const llmModelTypeFilterMap = {
   [LLMModelTypeEnum.all]: 'model',
   [LLMModelTypeEnum.classify]: 'usedInClassify',
   [LLMModelTypeEnum.extractFields]: 'usedInExtractFields',
-  [LLMModelTypeEnum.toolCall]: 'usedInToolCall',
-  [LLMModelTypeEnum.queryExtension]: 'usedInQueryExtension'
+  [LLMModelTypeEnum.toolCall]: 'usedInToolCall'
 };
 
 export enum EmbeddingTypeEnm {

packages/global/core/ai/model.d.ts

@@ -1,3 +1,4 @@
+import { ModelTypeEnum } from './model';
 import type { ModelProviderIdType } from './provider';
 
 type PriceType = {
@@ -7,68 +8,73 @@ type PriceType = {
   inputPrice?: number; // 1k tokens=n points
   outputPrice?: number; // 1k tokens=n points
 };
-export type LLMModelItemType = PriceType & {
+type BaseModelItemType = {
   provider: ModelProviderIdType;
   model: string;
   name: string;
   avatar?: string; // model icon, from provider
-  maxContext: number;
-  maxResponse: number;
-  quoteMaxToken: number;
-  maxTemperature: number;
 
-  censor?: boolean;
-  vision?: boolean;
+  isActive?: boolean;
+  isCustom?: boolean;
+  isDefault?: boolean;
 
-  // diff function model
-  datasetProcess?: boolean; // dataset
-  usedInClassify?: boolean; // classify
-  usedInExtractFields?: boolean; // extract fields
-  usedInToolCall?: boolean; // tool call
-  usedInQueryExtension?: boolean; // query extension
-
-  functionCall: boolean;
-  toolChoice: boolean;
-
-  customCQPrompt: string;
-  customExtractPrompt: string;
-
-  defaultSystemChatPrompt?: string;
-  defaultConfig?: Record<string, any>;
-  fieldMap?: Record<string, string>;
+  // If has requestUrl, it will request the model directly
+  requestUrl?: string;
+  requestAuth?: string;
 };
 
-export type VectorModelItemType = PriceType & {
-  provider: ModelProviderIdType;
-  model: string; // model name
-  name: string; // show name
-  avatar?: string;
-  defaultToken: number; // split text default token
-  maxToken: number; // model max token
-  weight: number; // training weight
-  hidden?: boolean; // Disallow creation
-  defaultConfig?: Record<string, any>; // post request config
-  dbConfig?: Record<string, any>; // Custom parameters for storage
-  queryConfig?: Record<string, any>; // Custom parameters for query
-};
+export type LLMModelItemType = PriceType &
+  BaseModelItemType & {
+    type: ModelTypeEnum.llm;
+    maxContext: number;
+    maxResponse: number;
+    quoteMaxToken: number;
+    maxTemperature: number;
 
-export type ReRankModelItemType = PriceType & {
-  provider: ModelProviderIdType;
-  model: string;
-  name: string;
-  requestUrl: string;
-  requestAuth: string;
-};
+    censor?: boolean;
+    vision?: boolean;
 
-export type AudioSpeechModelType = PriceType & {
-  provider: ModelProviderIdType;
-  model: string;
-  name: string;
-  voices: { label: string; value: string; bufferId: string }[];
-};
+    // diff function model
+    datasetProcess?: boolean; // dataset
+    usedInClassify?: boolean; // classify
+    usedInExtractFields?: boolean; // extract fields
+    usedInToolCall?: boolean; // tool call
 
-export type STTModelType = PriceType & {
-  provider: ModelProviderIdType;
-  model: string;
-  name: string;
-};
+    functionCall: boolean;
+    toolChoice: boolean;
+
+    customCQPrompt: string;
+    customExtractPrompt: string;
+
+    defaultSystemChatPrompt?: string;
+    defaultConfig?: Record<string, any>;
+    fieldMap?: Record<string, string>;
+  };
+
+export type EmbeddingModelItemType = PriceType &
+  BaseModelItemType & {
+    type: ModelTypeEnum.embedding;
+    defaultToken: number; // split text default token
+    maxToken: number; // model max token
+    weight: number; // training weight
+    hidden?: boolean; // Disallow creation
+    defaultConfig?: Record<string, any>; // post request config
+    dbConfig?: Record<string, any>; // Custom parameters for storage
+    queryConfig?: Record<string, any>; // Custom parameters for query
+  };
+
+export type ReRankModelItemType = PriceType &
+  BaseModelItemType & {
+    type: ModelTypeEnum.rerank;
+  };
+
+export type TTSModelType = PriceType &
+  BaseModelItemType & {
+    type: ModelTypeEnum.tts;
+    voices: { label: string; value: string }[];
+  };
+
+export type STTModelType = PriceType &
+  BaseModelItemType & {
+    type: ModelTypeEnum.stt;
+  };

packages/global/core/ai/model.ts

@@ -1,9 +1,18 @@
 import { i18nT } from '../../../web/i18n/utils';
-import type { LLMModelItemType, STTModelType, VectorModelItemType } from './model.d';
+import type { LLMModelItemType, STTModelType, EmbeddingModelItemType } from './model.d';
 import { getModelProvider, ModelProviderIdType } from './provider';
 
+export enum ModelTypeEnum {
+  llm = 'llm',
+  embedding = 'embedding',
+  tts = 'tts',
+  stt = 'stt',
+  rerank = 'rerank'
+}
+
 export const defaultQAModels: LLMModelItemType[] = [
   {
+    type: ModelTypeEnum.llm,
     provider: 'OpenAI',
     model: 'gpt-4o-mini',
     name: 'gpt-4o-mini',
@@ -24,8 +33,9 @@ export const defaultQAModels: LLMModelItemType[] = [
   }
 ];
 
-export const defaultVectorModels: VectorModelItemType[] = [
+export const defaultVectorModels: EmbeddingModelItemType[] = [
   {
+    type: ModelTypeEnum.embedding,
     provider: 'OpenAI',
     model: 'text-embedding-3-small',
     name: 'Embedding-2',
@@ -36,12 +46,15 @@ export const defaultVectorModels: VectorModelItemType[] = [
   }
 ];
 
-export const defaultWhisperModel: STTModelType = {
-  provider: 'OpenAI',
-  model: 'whisper-1',
-  name: 'whisper-1',
-  charsPointsPrice: 0
-};
+export const defaultSTTModels: STTModelType[] = [
+  {
+    type: ModelTypeEnum.stt,
+    provider: 'OpenAI',
+    model: 'whisper-1',
+    name: 'whisper-1',
+    charsPointsPrice: 0
+  }
+];
 
 export const getModelFromList = (
   modelList: { provider: ModelProviderIdType; name: string; model: string }[],
@@ -55,15 +68,10 @@ export const getModelFromList = (
   };
 };
 
-export enum ModelTypeEnum {
-  chat = 'chat',
-  embedding = 'embedding',
-  tts = 'tts',
-  stt = 'stt'
-}
 export const modelTypeList = [
-  { label: i18nT('common:model.type.chat'), value: ModelTypeEnum.chat },
+  { label: i18nT('common:model.type.chat'), value: ModelTypeEnum.llm },
   { label: i18nT('common:model.type.embedding'), value: ModelTypeEnum.embedding },
   { label: i18nT('common:model.type.tts'), value: ModelTypeEnum.tts },
-  { label: i18nT('common:model.type.stt'), value: ModelTypeEnum.stt }
+  { label: i18nT('common:model.type.stt'), value: ModelTypeEnum.stt },
+  { label: i18nT('common:model.type.reRank'), value: ModelTypeEnum.rerank }
 ];

packages/global/core/ai/provider.ts

@@ -7,6 +7,7 @@ export type ModelProviderIdType =
   | 'Meta'
   | 'MistralAI'
   | 'Groq'
+  | 'Grok'
   | 'AliCloud'
   | 'Qwen'
   | 'Doubao'
@@ -20,6 +21,7 @@ export type ModelProviderIdType =
   | 'Baichuan'
   | 'StepFun'
   | 'Yi'
+  | 'Siliconflow'
   | 'Ollama'
   | 'BAAI'
   | 'FishAudio'
@@ -29,7 +31,7 @@ export type ModelProviderIdType =
 
 export type ModelProviderType = {
   id: ModelProviderIdType;
-  name: string;
+  name: any;
   avatar: string;
 };
 
@@ -59,6 +61,11 @@ export const ModelProviderList: ModelProviderType[] = [
     name: 'MistralAI',
     avatar: 'model/mistral'
   },
+  {
+    id: 'Grok',
+    name: 'Grok',
+    avatar: 'model/grok'
+  },
   {
     id: 'Groq',
     name: 'Groq',
@@ -155,6 +162,11 @@ export const ModelProviderList: ModelProviderType[] = [
     name: i18nT('common:model_moka'),
     avatar: 'model/moka'
   },
+  {
+    id: 'Siliconflow',
+    name: i18nT('common:model_siliconflow'),
+    avatar: 'model/siliconflow'
+  },
   {
     id: 'Other',
     name: i18nT('common:model_other'),
@@ -165,6 +177,7 @@ export const ModelProviderMap = Object.fromEntries(
   ModelProviderList.map((item, index) => [item.id, { ...item, order: index }])
 );
 
-export const getModelProvider = (provider: ModelProviderIdType) => {
+export const getModelProvider = (provider?: ModelProviderIdType) => {
+  if (!provider) return ModelProviderMap.Other;
   return ModelProviderMap[provider] ?? ModelProviderMap.Other;
 };

packages/global/core/chat/constants.ts

@@ -75,5 +75,3 @@ export enum ChatStatusEnum {
   running = 'running',
   finish = 'finish'
 }
-
-export const MARKDOWN_QUOTE_SIGN = 'QUOTE SIGN';

packages/global/core/dataset/type.d.ts

@@ -1,4 +1,4 @@
-import type { LLMModelItemType, VectorModelItemType } from '../../core/ai/model.d';
+import type { LLMModelItemType, EmbeddingModelItemType } from '../../core/ai/model.d';
 import { PermissionTypeEnum } from '../../support/permission/constant';
 import { PushDatasetDataChunkProps } from './api';
 import {
@@ -152,7 +152,7 @@ export type DatasetSimpleItemType = {
   _id: string;
   avatar: string;
   name: string;
-  vectorModel: VectorModelItemType;
+  vectorModel: EmbeddingModelItemType;
 };
 export type DatasetListItemType = {
   _id: string;
@@ -163,14 +163,14 @@ export type DatasetListItemType = {
   intro: string;
   type: `${DatasetTypeEnum}`;
   permission: DatasetPermission;
-  vectorModel: VectorModelItemType;
+  vectorModel: EmbeddingModelItemType;
   inheritPermission: boolean;
   private?: boolean;
   sourceMember?: SourceMemberType;
 };
 
 export type DatasetItemType = Omit<DatasetSchemaType, 'vectorModel' | 'agentModel'> & {
-  vectorModel: VectorModelItemType;
+  vectorModel: EmbeddingModelItemType;
   agentModel: LLMModelItemType;
   permission: DatasetPermission;
 };

packages/global/core/workflow/api.d.ts

@@ -1,4 +1,4 @@
-import { VectorModelItemType } from '../ai/model.d';
+import { EmbeddingModelItemType } from '../ai/model.d';
 import { NodeInputKeyEnum } from './constants';
 
 export type SelectedDatasetType = { datasetId: string }[];

packages/global/core/workflow/runtime/utils.ts

@@ -176,6 +176,7 @@ export const checkNodeRunStatus = ({
       }
       visited.add(edge.source);
 
+      // 递归检测后面的 edge，如果有其中一个成环，则返回 true
       const nextEdges = allEdges.filter((item) => item.target === edge.source);
       return nextEdges.some((nextEdge) => checkIsCircular(nextEdge, new Set(visited)));
     };
@@ -207,7 +208,23 @@ export const checkNodeRunStatus = ({
     currentNode: node
   });
 
-  // check skip（其中一组边，全 skip）
+  // check active（其中一组边，至少有一个 active，且没有 waiting 即可运行）
+  if (
+    commonEdges.length > 0 &&
+    commonEdges.some((item) => item.status === 'active') &&
+    commonEdges.every((item) => item.status !== 'waiting')
+  ) {
+    return 'run';
+  }
+  if (
+    recursiveEdges.length > 0 &&
+    recursiveEdges.some((item) => item.status === 'active') &&
+    recursiveEdges.every((item) => item.status !== 'waiting')
+  ) {
+    return 'run';
+  }
+
+  // check skip（其中一组边，全是 skiped 则跳过运行）
   if (commonEdges.length > 0 && commonEdges.every((item) => item.status === 'skipped')) {
     return 'skip';
   }
@@ -215,14 +232,6 @@ export const checkNodeRunStatus = ({
     return 'skip';
   }
 
-  // check active（有一类边，不全是 wait 即可运行）
-  if (commonEdges.length > 0 && commonEdges.every((item) => item.status !== 'waiting')) {
-    return 'run';
-  }
-  if (recursiveEdges.length > 0 && recursiveEdges.every((item) => item.status !== 'waiting')) {
-    return 'run';
-  }
-
   return 'wait';
 };
 

packages/global/core/workflow/template/system/queryExtension.ts

@@ -31,10 +31,7 @@ export const AiQueryExtension: FlowNodeTemplateType = {
   showStatus: true,
   version: '481',
   inputs: [
-    {
-      ...Input_Template_SelectAIModel,
-      llmModelType: LLMModelTypeEnum.queryExtension
-    },
+    Input_Template_SelectAIModel,
     {
       key: NodeInputKeyEnum.aiSystemPrompt,
       renderTypeList: [FlowNodeInputTypeEnum.textarea, FlowNodeInputTypeEnum.reference],

packages/global/support/wallet/usage/api.d.ts

@@ -6,6 +6,22 @@ export type CreateTrainingUsageProps = {
   datasetId: string;
 };
 
+export type GetUsageProps = {
+  dateStart: Date;
+  dateEnd: Date;
+  sources?: UsageSourceEnum[];
+  teamMemberIds?: string[];
+  projectName?: string;
+};
+
+export type GetUsageDashboardProps = GetUsageProps & {
+  unit: 'day' | 'month';
+};
+export type GetUsageDashboardResponseItem = {
+  date: Date;
+  totalPoints: number;
+};
+
 export type ConcatUsageProps = UsageListItemCountType & {
   teamId: string;
   tmbId: string;

packages/global/support/wallet/usage/constants.ts

@@ -18,30 +18,30 @@ export const UsageSourceMap = {
     label: i18nT('common:core.chat.logs.online')
   },
   [UsageSourceEnum.api]: {
-    label: 'Api'
+    label: 'API'
   },
   [UsageSourceEnum.shareLink]: {
     label: i18nT('common:core.chat.logs.free_login')
   },
   [UsageSourceEnum.training]: {
-    label: 'dataset.Training Name'
+    label: i18nT('common:dataset.Training Name')
   },
   [UsageSourceEnum.cronJob]: {
     label: i18nT('common:cron_job_run_app')
   },
   [UsageSourceEnum.feishu]: {
-    label: i18nT('user:usage.feishu')
+    label: i18nT('account_usage:feishu')
   },
   [UsageSourceEnum.official_account]: {
-    label: i18nT('user:usage.official_account')
+    label: i18nT('account_usage:official_account')
   },
   [UsageSourceEnum.share]: {
-    label: i18nT('user:usage.share')
+    label: i18nT('account_usage:share')
   },
   [UsageSourceEnum.wecom]: {
-    label: i18nT('user:usage.wecom')
+    label: i18nT('account_usage:wecom')
   },
   [UsageSourceEnum.dingtalk]: {
-    label: i18nT('user:usage.dingtalk')
+    label: i18nT('account_usage:dingtalk')
   }
 };

packages/global/support/wallet/usage/type.d.ts

@@ -1,3 +1,4 @@
+import { SourceMemberType } from '../../../support/user/type';
 import { CreateUsageProps } from './api';
 import { UsageSourceEnum } from './constants';
 
@@ -10,6 +11,7 @@ export type UsageListItemCountType = {
   // deprecated
   tokens?: number;
 };
+
 export type UsageListItemType = UsageListItemCountType & {
   moduleName: string;
   amount: number;
@@ -28,4 +30,5 @@ export type UsageItemType = {
   source: UsageSchemaType['source'];
   totalPoints: number;
   list: UsageSchemaType['list'];
+  sourceMember: SourceMemberType;
 };

packages/service/common/middle/reqFrequencyLimit.ts

@@ -1,6 +1,5 @@
 import { ApiRequestProps } from '../../type/next';
 import requestIp from 'request-ip';
-import { ERROR_ENUM } from '@fastgpt/global/common/error/errorCode';
 import { authFrequencyLimit } from '../system/frequencyLimit/utils';
 import { addSeconds } from 'date-fns';
 import { NextApiResponse } from 'next';
@@ -9,7 +8,17 @@ import { jsonRes } from '../response';
 // unit: times/s
 // how to use?
 // export default NextAPI(useQPSLimit(10), handler); // limit 10 times per second for a ip
-export function useReqFrequencyLimit(seconds: number, limit: number, force = false) {
+export function useIPFrequencyLimit({
+  id,
+  seconds,
+  limit,
+  force = false
+}: {
+  id: string;
+  seconds: number;
+  limit: number;
+  force?: boolean;
+}) {
   return async (req: ApiRequestProps, res: NextApiResponse) => {
     const ip = requestIp.getClientIp(req);
     if (!ip || (process.env.USE_IP_LIMIT !== 'true' && !force)) {
@@ -17,14 +26,14 @@ export function useReqFrequencyLimit(seconds: number, limit: number, force = fal
     }
     try {
       await authFrequencyLimit({
-        eventId: 'ip-qps-limit' + ip,
+        eventId: `ip-qps-limit-${id}-` + ip,
         maxAmount: limit,
         expiredTime: addSeconds(new Date(), seconds)
       });
     } catch (_) {
       jsonRes(res, {
         code: 429,
-        error: ERROR_ENUM.tooManyRequest
+        error: `Too many request, request ${limit} times every ${seconds} seconds`
       });
     }
   };

packages/service/common/response/index.ts

@@ -33,7 +33,15 @@ export const jsonRes = <T = any>(
 
     addLog.error(`Api response error: ${url}`, ERROR_RESPONSE[errResponseKey]);
 
-    return res.status(code).json(ERROR_RESPONSE[errResponseKey]);
+    res.status(code);
+
+    if (message) {
+      res.send(message);
+    } else {
+      res.json(ERROR_RESPONSE[errResponseKey]);
+    }
+
+    return;
   }
 
   // another error

packages/service/common/system/config/controller.ts

@@ -6,8 +6,7 @@ import { FastGPTProUrl } from '../constants';
 export const getFastGPTConfigFromDB = async () => {
   if (!FastGPTProUrl) {
     return {
-      config: {} as FastGPTConfigFileType,
-      configId: undefined
+      config: {} as FastGPTConfigFileType
     };
   }
 
@@ -18,9 +17,35 @@ export const getFastGPTConfigFromDB = async () => {
   });
 
   const config = res?.value || {};
+  // 利用配置文件的创建时间（更新时间）来做缓存，如果前端命中缓存，则不需要再返回配置文件
+  global.systemInitBufferId = res ? res.createTime.getTime().toString() : undefined;
 
   return {
-    configId: res ? String(res._id) : undefined,
     config: config as FastGPTConfigFileType
   };
 };
+
+export const updateFastGPTConfigBuffer = async () => {
+  const res = await MongoSystemConfigs.findOne({
+    type: SystemConfigsTypeEnum.fastgpt
+  }).sort({
+    createTime: -1
+  });
+
+  if (!res) return;
+
+  res.createTime = new Date();
+  await res.save();
+
+  global.systemInitBufferId = res.createTime.getTime().toString();
+};
+
+export const reloadFastGPTConfigBuffer = async () => {
+  const res = await MongoSystemConfigs.findOne({
+    type: SystemConfigsTypeEnum.fastgpt
+  }).sort({
+    createTime: -1
+  });
+  if (!res) return;
+  global.systemInitBufferId = res.createTime.getTime().toString();
+};

packages/service/common/system/tools.ts

@@ -13,15 +13,6 @@ export const initFastGPTConfig = (config?: FastGPTConfigFileType) => {
   global.feConfigs = config.feConfigs;
   global.systemEnv = config.systemEnv;
   global.subPlans = config.subPlans;
-
-  global.llmModels = config.llmModels;
-  global.llmModelPriceType = global.llmModels.some((item) => typeof item.inputPrice === 'number')
-    ? 'IO'
-    : 'Tokens';
-  global.vectorModels = config.vectorModels;
-  global.audioSpeechModels = config.audioSpeechModels;
-  global.whisperModel = config.whisperModel;
-  global.reRankModels = config.reRankModels;
 };
 
 export const systemStartCb = () => {

packages/service/common/vectorStore/controller.ts

@@ -2,7 +2,7 @@
 import { PgVectorCtrl } from './pg/class';
 import { getVectorsByText } from '../../core/ai/embedding';
 import { InsertVectorProps } from './controller.d';
-import { VectorModelItemType } from '@fastgpt/global/core/ai/model.d';
+import { EmbeddingModelItemType } from '@fastgpt/global/core/ai/model.d';
 import { MILVUS_ADDRESS, PG_ADDRESS } from './constants';
 import { MilvusCtrl } from './milvus/class';
 
@@ -28,7 +28,7 @@ export const insertDatasetDataVector = async ({
   ...props
 }: InsertVectorProps & {
   query: string;
-  model: VectorModelItemType;
+  model: EmbeddingModelItemType;
 }) => {
   const { vectors, tokens } = await getVectorsByText({
     model,

packages/service/core/ai/audio/speech.ts

@@ -1,5 +1,6 @@
 import type { NextApiResponse } from 'next';
 import { getAIApi } from '../config';
+import { getTTSModel } from '../model';
 
 export async function text2Speech({
   res,
@@ -18,15 +19,26 @@ export async function text2Speech({
   voice: string;
   speed?: number;
 }) {
+  const modelData = getTTSModel(model)!;
   const ai = getAIApi();
-  const response = await ai.audio.speech.create({
-    model,
-    // @ts-ignore
-    voice,
-    input,
-    response_format: 'mp3',
-    speed
-  });
+  const response = await ai.audio.speech.create(
+    {
+      model,
+      // @ts-ignore
+      voice,
+      input,
+      response_format: 'mp3',
+      speed
+    },
+    modelData.requestUrl && modelData.requestAuth
+      ? {
+          path: modelData.requestUrl,
+          headers: {
+            Authorization: `Bearer ${modelData.requestAuth}`
+          }
+        }
+      : {}
+  );
 
   const readableStream = response.body as unknown as NodeJS.ReadableStream;
   readableStream.pipe(res);

packages/service/core/ai/audio/transcriptions.ts

@@ -2,6 +2,7 @@ import fs from 'fs';
 import { getAxiosConfig } from '../config';
 import axios from 'axios';
 import FormData from 'form-data';
+import { getSTTModel } from '../model';
 
 export const aiTranscriptions = async ({
   model,
@@ -14,13 +15,21 @@ export const aiTranscriptions = async ({
   data.append('model', model);
   data.append('file', fileStream);
 
+  const modelData = getSTTModel(model);
   const aiAxiosConfig = getAxiosConfig();
+
   const { data: result } = await axios<{ text: string }>({
     method: 'post',
-    baseURL: aiAxiosConfig.baseUrl,
-    url: '/audio/transcriptions',
+    ...(modelData.requestUrl
+      ? { url: modelData.requestUrl }
+      : {
+          baseURL: aiAxiosConfig.baseUrl,
+          url: modelData.requestUrl || '/audio/transcriptions'
+        }),
     headers: {
-      Authorization: aiAxiosConfig.authorization,
+      Authorization: modelData.requestAuth
+        ? `Bearer ${modelData.requestAuth}`
+        : aiAxiosConfig.authorization,
       ...data.getHeaders()
     },
     data: data

packages/service/core/ai/config.ts

@@ -7,14 +7,14 @@ import { getErrText } from '@fastgpt/global/common/error/utils';
 import { addLog } from '../../common/system/log';
 import { i18nT } from '../../../web/i18n/utils';
 import { OpenaiAccountType } from '@fastgpt/global/support/user/team/type';
+import { getLLMModel } from './model';
 
 export const openaiBaseUrl = process.env.OPENAI_BASE_URL || 'https://api.openai.com/v1';
 
 export const getAIApi = (props?: { userKey?: OpenaiAccountType; timeout?: number }) => {
   const { userKey, timeout } = props || {};
 
-  const baseUrl =
-    userKey?.baseUrl || global?.systemEnv?.oneapiUrl || process.env.ONEAPI_URL || openaiBaseUrl;
+  const baseUrl = userKey?.baseUrl || global?.systemEnv?.oneapiUrl || openaiBaseUrl;
   const apiKey = userKey?.key || global?.systemEnv?.chatApiKey || process.env.CHAT_API_KEY || '';
 
   return new OpenAI({
@@ -29,8 +29,7 @@ export const getAIApi = (props?: { userKey?: OpenaiAccountType; timeout?: number
 export const getAxiosConfig = (props?: { userKey?: OpenaiAccountType }) => {
   const { userKey } = props || {};
 
-  const baseUrl =
-    userKey?.baseUrl || global?.systemEnv?.oneapiUrl || process.env.ONEAPI_URL || openaiBaseUrl;
+  const baseUrl = userKey?.baseUrl || global?.systemEnv?.oneapiUrl || openaiBaseUrl;
   const apiKey = userKey?.key || global?.systemEnv?.chatApiKey || process.env.CHAT_API_KEY || '';
 
   return {
@@ -63,12 +62,23 @@ export const createChatCompletion = async <T extends CompletionsBodyType>({
   getEmptyResponseTip: () => string;
 }> => {
   try {
+    const modelConstantsData = getLLMModel(body.model);
+
     const formatTimeout = timeout ? timeout : body.stream ? 60000 : 600000;
     const ai = getAIApi({
       userKey,
       timeout: formatTimeout
     });
-    const response = await ai.chat.completions.create(body, options);
+    const response = await ai.chat.completions.create(body, {
+      ...options,
+      ...(modelConstantsData.requestUrl ? { path: modelConstantsData.requestUrl } : {}),
+      headers: {
+        ...options?.headers,
+        ...(modelConstantsData.requestAuth
+          ? { Authorization: `Bearer ${modelConstantsData.requestAuth}` }
+          : {})
+      }
+    });
 
     const isStreamResponse =
       typeof response === 'object' &&

packages/service/core/ai/config/embedding/text-embedding-ada-002.json

@@ -1,11 +0,0 @@
-{
-  "provider": "OpenAI",
-  "model": "text-embedding-ada-002",
-  "name": "text-embedding-ada-002",
-
-  "defaultToken": 512, // 默认分块 token
-  "maxToken": 3000, // 最大分块 token
-  "weight": 0, // 权重
-
-  "charsPointsPrice": 0 // 积分/1k token
-}

packages/service/core/ai/config/llm/gpt-4o-mini.json

@@ -1,33 +0,0 @@
-{
-  "provider": "OpenAI",
-  "model": "gpt-4o-mini",
-  "name": "GPT-4o-mini", // alias
-
-  "maxContext": 125000, // 最大上下文
-  "maxResponse": 16000, // 最大回复
-  "quoteMaxToken": 60000, // 最大引用
-  "maxTemperature": 1.2, // 最大温度
-  "presencePenaltyRange": [-2, 2], // 惩罚系数范围
-  "frequencyPenaltyRange": [-2, 2], // 频率惩罚系数范围
-  "responseFormatList": ["text", "json_object", "json_schema"], // 响应格式
-  "showStopSign": true, // 是否显示停止符号
-
-  "vision": true, // 是否支持图片识别
-  "toolChoice": true, // 是否支持工具调用
-  "functionCall": false, // 是否支持函数调用（一般都可以 false 了，基本不用了）
-  "defaultSystemChatPrompt": "", // 默认系统提示
-
-  "datasetProcess": true, // 用于知识库文本处理
-  "usedInClassify": true, // 用于问题分类
-  "customCQPrompt": "", // 自定义问题分类提示
-  "usedInExtractFields": true, // 用于提取字段
-  "customExtractPrompt": "", // 自定义提取提示
-  "usedInToolCall": true, // 用于工具调用
-  "usedInQueryExtension": true, // 用于问题优化
-
-  "defaultConfig": {}, // 额外的自定义 body
-  "fieldMap": {}, // body 字段映射
-
-  "censor": false, // 是否开启敏感词过滤
-  "charsPointsPrice": 0 // n 积分/1k token
-}

packages/service/core/ai/config/provider/AliCloud.json

@@ -0,0 +1,4 @@
+{
+  "provider": "AliCloud",
+  "list": []
+}

packages/service/core/ai/config/provider/BAAI.json

@@ -0,0 +1,17 @@
+{
+  "provider": "BAAI",
+  "list": [
+    {
+      "model": "bge-m3",
+      "name": "bge-m3",
+      "defaultToken": 512,
+      "maxToken": 8000,
+      "type": "embedding"
+    },
+    {
+      "model": "bge-reranker-v2-m3",
+      "name": "bge-reranker-v2-m3",
+      "type": "rerank"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Baichuan.json

@@ -0,0 +1,4 @@
+{
+  "provider": "Baichuan",
+  "list": []
+}

packages/service/core/ai/config/provider/ChatGLM.json

@@ -0,0 +1,147 @@
+{
+  "provider": "ChatGLM",
+  "list": [
+    {
+      "model": "glm-4-air",
+      "name": "glm-4-air",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 0.99,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "glm-4-flash",
+      "name": "glm-4-flash",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 0.99,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "glm-4-long",
+      "name": "glm-4-long",
+      "maxContext": 1000000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 900000,
+      "maxTemperature": 0.99,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "glm-4-plus",
+      "name": "GLM-4-plus",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 0.99,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "glm-4v-flash",
+      "name": "glm-4v-flash",
+      "maxContext": 8000,
+      "maxResponse": 1000,
+      "quoteMaxToken": 6000,
+      "maxTemperature": 0.99,
+      "vision": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "glm-4v-plus",
+      "name": "GLM-4v-plus",
+      "maxContext": 8000,
+      "maxResponse": 1000,
+      "quoteMaxToken": 6000,
+      "maxTemperature": 0.99,
+      "vision": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "embedding-3",
+      "name": "embedding-3",
+      "defaultToken": 512,
+      "maxToken": 8000,
+      "defaultConfig": {
+        "dimensions": 1024
+      },
+      "type": "embedding"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Claude.json

@@ -0,0 +1,93 @@
+{
+  "provider": "Claude",
+  "list": [
+    {
+      "model": "claude-3-5-haiku-20241022",
+      "name": "claude-3-5-haiku-20241022",
+      "maxContext": 200000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 100000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "claude-3-5-sonnet-20240620",
+      "name": "Claude-3-5-sonnet-20240620",
+      "maxContext": 200000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 100000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "claude-3-5-sonnet-20241022",
+      "name": "Claude-3-5-sonnet-20241022",
+      "maxContext": 200000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 100000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "claude-3-opus-20240229",
+      "name": "claude-3-opus-20240229",
+      "maxContext": 200000,
+      "maxResponse": 4096,
+      "quoteMaxToken": 100000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    }
+  ]
+}

packages/service/core/ai/config/provider/DeepSeek.json

@@ -0,0 +1,49 @@
+{
+  "provider": "DeepSeek",
+  "list": [
+    {
+      "model": "deepseek-chat",
+      "name": "Deepseek-chat",
+      "maxContext": 64000,
+      "maxResponse": 4096,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1.5,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "type": "llm"
+    },
+    {
+      "model": "deepseek-reasoner",
+      "name": "Deepseek-reasoner",
+      "maxContext": 64000,
+      "maxResponse": 4096,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1.5,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {
+        "temperature": null
+      },
+      "fieldMap": {},
+      "type": "llm"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Doubao.json

@@ -0,0 +1,195 @@
+{
+  "provider": "Doubao",
+  "list": [
+    {
+      "model": "Doubao-lite-4k",
+      "name": "Doubao-lite-4k",
+      "maxContext": 4000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 4000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "Doubao-lite-32k",
+      "name": "Doubao-lite-32k",
+      "maxContext": 32000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "Doubao-lite-128k",
+      "name": "Doubao-lite-128k",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "Doubao-vision-lite-32k",
+      "name": "Doubao-vision-lite-32k",
+      "maxContext": 32000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "Doubao-pro-4k",
+      "name": "Doubao-pro-4k",
+      "maxContext": 4000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 4000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "Doubao-pro-32k",
+      "name": "Doubao-pro-32k",
+      "maxContext": 32000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "Doubao-pro-128k",
+      "name": "Doubao-pro-128k",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "Doubao-vision-pro-32k",
+      "name": "Doubao-vision-pro-32k",
+      "maxContext": 32000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "Doubao-embedding-large",
+      "name": "Doubao-embedding-large",
+      "defaultToken": 512,
+      "maxToken": 4096,
+      "type": "embedding"
+    },
+    {
+      "model": "Doubao-embedding",
+      "name": "Doubao-embedding",
+      "defaultToken": 512,
+      "maxToken": 4096,
+      "type": "embedding"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Ernie.json

@@ -0,0 +1,107 @@
+{
+  "provider": "Ernie",
+  "list": [
+    {
+      "model": "ERNIE-4.0-8K",
+      "name": "ERNIE-4.0-8K",
+      "maxContext": 8000,
+      "maxResponse": 2048,
+      "quoteMaxToken": 5000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "ERNIE-4.0-Turbo-8K",
+      "name": "ERNIE-4.0-Turbo-8K",
+      "maxContext": 8000,
+      "maxResponse": 2048,
+      "quoteMaxToken": 5000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "ERNIE-Lite-8K",
+      "name": "ERNIE-lite-8k",
+      "maxContext": 8000,
+      "maxResponse": 2048,
+      "quoteMaxToken": 6000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "ERNIE-Speed-128K",
+      "name": "ERNIE-Speed-128K",
+      "maxContext": 128000,
+      "maxResponse": 4096,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "Embedding-V1",
+      "name": "Embedding-V1",
+      "defaultToken": 512,
+      "maxToken": 1000,
+      "type": "embedding"
+    },
+    {
+      "model": "tao-8k",
+      "name": "tao-8k",
+      "defaultToken": 512,
+      "maxToken": 8000,
+      "type": "embedding"
+    }
+  ]
+}

packages/service/core/ai/config/provider/FishAudio.json

@@ -0,0 +1,4 @@
+{
+  "provider": "FishAudio",
+  "list": []
+}

packages/service/core/ai/config/provider/Gemini.json

@@ -0,0 +1,144 @@
+{
+  "provider": "Gemini",
+  "list": [
+    {
+      "model": "gemini-1.5-flash",
+      "name": "gemini-1.5-flash",
+      "maxContext": 1000000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "gemini-1.5-pro",
+      "name": "gemini-1.5-pro",
+      "maxContext": 2000000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "gemini-2.0-flash-exp",
+      "name": "gemini-2.0-flash-exp",
+      "maxContext": 1000000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "gemini-2.0-flash-thinking-exp-1219",
+      "name": "gemini-2.0-flash-thinking-exp-1219",
+      "maxContext": 1000000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "gemini-2.0-flash-thinking-exp-01-21",
+      "name": "gemini-2.0-flash-thinking-exp-01-21",
+      "maxContext": 1000000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "gemini-exp-1206",
+      "name": "gemini-exp-1206",
+      "maxContext": 128000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "text-embedding-004",
+      "name": "text-embedding-004",
+      "defaultToken": 512,
+      "maxToken": 2000,
+      "type": "embedding"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Grok.json

@@ -0,0 +1,4 @@
+{
+  "provider": "Grok",
+  "list": []
+}

packages/service/core/ai/config/provider/Groq.json

@@ -0,0 +1,47 @@
+{
+  "provider": "Groq",
+  "list": [
+    {
+      "model": "llama-3.1-8b-instant",
+      "name": "Groq-llama-3.1-8b-instant",
+      "maxContext": 128000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1.2,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "type": "llm"
+    },
+    {
+      "model": "llama-3.3-70b-versatile",
+      "name": "Groq-llama-3.3-70b-versatile",
+      "maxContext": 128000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1.2,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "type": "llm"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Hunyuan.json

@@ -0,0 +1,166 @@
+{
+  "provider": "Hunyuan",
+  "list": [
+    {
+      "model": "hunyuan-large",
+      "name": "hunyuan-large",
+      "maxContext": 28000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 20000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "hunyuan-lite",
+      "name": "hunyuan-lite",
+      "maxContext": 250000,
+      "maxResponse": 6000,
+      "quoteMaxToken": 100000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "hunyuan-pro",
+      "name": "hunyuan-pro",
+      "maxContext": 28000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 28000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "hunyuan-standard",
+      "name": "hunyuan-standard",
+      "maxContext": 32000,
+      "maxResponse": 2000,
+      "quoteMaxToken": 20000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "hunyuan-turbo-vision",
+      "name": "hunyuan-turbo-vision",
+      "maxContext": 6000,
+      "maxResponse": 2000,
+      "quoteMaxToken": 6000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "hunyuan-turbo",
+      "name": "hunyuan-turbo",
+      "maxContext": 28000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 20000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "hunyuan-vision",
+      "name": "hunyuan-vision",
+      "maxContext": 6000,
+      "maxResponse": 2000,
+      "quoteMaxToken": 4000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "hunyuan-embedding",
+      "name": "hunyuan-embedding",
+      "defaultToken": 512,
+      "maxToken": 1024,
+      "type": "embedding"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Intern.json

@@ -0,0 +1,49 @@
+{
+  "provider": "Intern",
+  "list": [
+    {
+      "model": "internlm2-pro-chat",
+      "name": "internlm2-pro-chat",
+      "maxContext": 32000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "internlm3-8b-instruct",
+      "name": "internlm3-8b-instruct",
+      "maxContext": 32000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Meta.json

@@ -0,0 +1,4 @@
+{
+  "provider": "Meta",
+  "list": []
+}

packages/service/core/ai/config/provider/MiniMax.json

@@ -0,0 +1,240 @@
+{
+  "provider": "MiniMax",
+  "list": [
+    {
+      "model": "MiniMax-Text-01",
+      "name": "MiniMax-Text-01",
+      "maxContext": 1000000,
+      "maxResponse": 1000000,
+      "quoteMaxToken": 100000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "abab6.5s-chat",
+      "name": "MiniMax-abab6.5s",
+      "maxContext": 245000,
+      "maxResponse": 10000,
+      "quoteMaxToken": 240000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "speech-01-turbo",
+      "name": "speech-01-turbo",
+      "voices": [
+        {
+          "label": "male-qn-qingse",
+          "value": "male-qn-qingse"
+        },
+        {
+          "label": "male-qn-jingying",
+          "value": "male-qn-jingying"
+        },
+        {
+          "label": "male-qn-badao",
+          "value": "male-qn-badao"
+        },
+        {
+          "label": "male-qn-daxuesheng",
+          "value": "male-qn-daxuesheng"
+        },
+        {
+          "label": "female-shaonv",
+          "value": "female-shaonv"
+        },
+        {
+          "label": "female-yujie",
+          "value": "female-yujie"
+        },
+        {
+          "label": "female-chengshu",
+          "value": "female-chengshu"
+        },
+        {
+          "label": "female-tianmei",
+          "value": "female-tianmei"
+        },
+        {
+          "label": "presenter_male",
+          "value": "presenter_male"
+        },
+        {
+          "label": "presenter_female",
+          "value": "presenter_female"
+        },
+        {
+          "label": "audiobook_male_1",
+          "value": "audiobook_male_1"
+        },
+        {
+          "label": "audiobook_male_2",
+          "value": "audiobook_male_2"
+        },
+        {
+          "label": "audiobook_female_1",
+          "value": "audiobook_female_1"
+        },
+        {
+          "label": "audiobook_female_2",
+          "value": "audiobook_female_2"
+        },
+        {
+          "label": "male-qn-qingse-jingpin",
+          "value": "male-qn-qingse-jingpin"
+        },
+        {
+          "label": "male-qn-jingying-jingpin",
+          "value": "male-qn-jingying-jingpin"
+        },
+        {
+          "label": "male-qn-badao-jingpin",
+          "value": "male-qn-badao-jingpin"
+        },
+        {
+          "label": "male-qn-daxuesheng-jingpin",
+          "value": "male-qn-daxuesheng-jingpin"
+        },
+        {
+          "label": "female-shaonv-jingpin",
+          "value": "female-shaonv-jingpin"
+        },
+        {
+          "label": "female-yujie-jingpin",
+          "value": "female-yujie-jingpin"
+        },
+        {
+          "label": "female-chengshu-jingpin",
+          "value": "female-chengshu-jingpin"
+        },
+        {
+          "label": "female-tianmei-jingpin",
+          "value": "female-tianmei-jingpin"
+        },
+        {
+          "label": "clever_boy",
+          "value": "clever_boy"
+        },
+        {
+          "label": "cute_boy",
+          "value": "cute_boy"
+        },
+        {
+          "label": "lovely_girl",
+          "value": "lovely_girl"
+        },
+        {
+          "label": "cartoon_pig",
+          "value": "cartoon_pig"
+        },
+        {
+          "label": "bingjiao_didi",
+          "value": "bingjiao_didi"
+        },
+        {
+          "label": "junlang_nanyou",
+          "value": "junlang_nanyou"
+        },
+        {
+          "label": "chunzhen_xuedi",
+          "value": "chunzhen_xuedi"
+        },
+        {
+          "label": "lengdan_xiongzhang",
+          "value": "lengdan_xiongzhang"
+        },
+        {
+          "label": "badao_shaoye",
+          "value": "badao_shaoye"
+        },
+        {
+          "label": "tianxin_xiaoling",
+          "value": "tianxin_xiaoling"
+        },
+        {
+          "label": "qiaopi_mengmei",
+          "value": "qiaopi_mengmei"
+        },
+        {
+          "label": "wumei_yujie",
+          "value": "wumei_yujie"
+        },
+        {
+          "label": "diadia_xuemei",
+          "value": "diadia_xuemei"
+        },
+        {
+          "label": "danya_xuejie",
+          "value": "danya_xuejie"
+        },
+        {
+          "label": "Santa_Claus",
+          "value": "Santa_Claus"
+        },
+        {
+          "label": "Grinch",
+          "value": "Grinch"
+        },
+        {
+          "label": "Rudolph",
+          "value": "Rudolph"
+        },
+        {
+          "label": "Arnold",
+          "value": "Arnold"
+        },
+        {
+          "label": "Charming_Santa",
+          "value": "Charming_Santa"
+        },
+        {
+          "label": "Charming_Lady",
+          "value": "Charming_Lady"
+        },
+        {
+          "label": "Sweet_Girl",
+          "value": "Sweet_Girl"
+        },
+        {
+          "label": "Cute_Elf",
+          "value": "Cute_Elf"
+        },
+        {
+          "label": "Attractive_Girl",
+          "value": "Attractive_Girl"
+        },
+        {
+          "label": "Serene_Woman",
+          "value": "Serene_Woman"
+        }
+      ],
+      "type": "tts"
+    }
+  ]
+}

packages/service/core/ai/config/provider/MistralAI.json

@@ -0,0 +1,93 @@
+{
+  "provider": "MistralAI",
+  "list": [
+    {
+      "model": "ministral-3b-latest",
+      "name": "Ministral-3b-latest",
+      "maxContext": 130000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1.2,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "ministral-8b-latest",
+      "name": "Ministral-8b-latest",
+      "maxContext": 130000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1.2,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "mistral-large-latest",
+      "name": "Mistral-large-latest",
+      "maxContext": 130000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1.2,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "mistral-small-latest",
+      "name": "Mistral-small-latest",
+      "maxContext": 32000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1.2,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Moka.json

@@ -0,0 +1,4 @@
+{
+  "provider": "Moka",
+  "list": []
+}

packages/service/core/ai/config/provider/Moonshot.json

@@ -0,0 +1,71 @@
+{
+  "provider": "Moonshot",
+  "list": [
+    {
+      "model": "moonshot-v1-8k",
+      "name": "moonshot-v1-8k",
+      "maxContext": 8000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 6000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "moonshot-v1-32k",
+      "name": "moonshot-v1-32k",
+      "maxContext": 32000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "moonshot-v1-128k",
+      "name": "moonshot-v1-128k",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Ollama.json

@@ -0,0 +1,4 @@
+{
+  "provider": "Ollama",
+  "list": []
+}

packages/service/core/ai/config/provider/OpenAI.json

@@ -0,0 +1,222 @@
+{
+  "provider": "OpenAI",
+  "list": [
+    {
+      "model": "gpt-4o-mini",
+      "name": "GPT-4o-mini",
+      "maxContext": 128000,
+      "maxResponse": 16000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1.2,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": true,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "gpt-4o",
+      "name": "GPT-4o",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1.2,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": true,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "o1-mini",
+      "name": "o1-mini",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 1.2,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": true,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {
+        "temperature": 1,
+        "max_tokens": null
+      },
+      "type": "llm"
+    },
+    {
+      "model": "o1-preview",
+      "name": "o1-preview",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 1.2,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": true,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {
+        "temperature": 1,
+        "max_tokens": null,
+        "stream": false
+      },
+      "type": "llm"
+    },
+    {
+      "model": "o1",
+      "name": "o1",
+      "maxContext": 195000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": 1.2,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": true,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {
+        "temperature": 1,
+        "max_tokens": null,
+        "stream": false
+      },
+      "type": "llm"
+    },
+    {
+      "model": "gpt-3.5-turbo",
+      "name": "gpt-3.5-turbo",
+      "maxContext": 16000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 13000,
+      "maxTemperature": 1.2,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": true,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "type": "llm"
+    },
+    {
+      "model": "gpt-4-turbo",
+      "name": "gpt-4-turbo",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1.2,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": true,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "type": "llm"
+    },
+    {
+      "model": "text-embedding-3-large",
+      "name": "text-embedding-3-large",
+      "defaultToken": 512,
+      "maxToken": 8000,
+      "defaultConfig": {
+        "dimensions": 1024
+      },
+      "type": "embedding"
+    },
+    {
+      "model": "text-embedding-3-small",
+      "name": "text-embedding-3-small",
+      "defaultToken": 512,
+      "maxToken": 8000,
+      "type": "embedding"
+    },
+    {
+      "model": "text-embedding-ada-002",
+      "name": "text-embedding-ada-002",
+      "defaultToken": 512,
+      "maxToken": 8000,
+      "type": "embedding"
+    },
+    {
+      "model": "tts-1",
+      "name": "TTS1",
+      "voices": [
+        {
+          "label": "Alloy",
+          "value": "alloy"
+        },
+        {
+          "label": "Echo",
+          "value": "echo"
+        },
+        {
+          "label": "Fable",
+          "value": "fable"
+        },
+        {
+          "label": "Onyx",
+          "value": "onyx"
+        },
+        {
+          "label": "Nova",
+          "value": "nova"
+        },
+        {
+          "label": "Shimmer",
+          "value": "shimmer"
+        }
+      ],
+      "type": "tts"
+    },
+    {
+      "model": "whisper-1",
+      "name": "whisper-1",
+      "type": "stt"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Other.json

@@ -0,0 +1,4 @@
+{
+  "provider": "Other",
+  "list": []
+}

packages/service/core/ai/config/provider/Qwen.json

@@ -0,0 +1,223 @@
+{
+  "provider": "Qwen",
+  "list": [
+    {
+      "model": "qwen-turbo",
+      "name": "Qwen-turbo",
+      "maxContext": 128000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 100000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "qwen-plus",
+      "name": "Qwen-plus",
+      "maxContext": 64000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 60000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "qwen-vl-plus",
+      "name": "qwen-vl-plus",
+      "maxContext": 32000,
+      "maxResponse": 2000,
+      "quoteMaxToken": 20000,
+      "maxTemperature": 1.2,
+      "vision": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "type": "llm"
+    },
+    {
+      "model": "qwen-max",
+      "name": "Qwen-max",
+      "maxContext": 8000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 6000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "qwen-vl-max",
+      "name": "qwen-vl-max",
+      "maxContext": 32000,
+      "maxResponse": 2000,
+      "quoteMaxToken": 20000,
+      "maxTemperature": 1.2,
+      "vision": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "qwen-coder-turbo",
+      "name": "qwen-coder-turbo",
+      "maxContext": 128000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 50000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "qwen2.5-7b-instruct",
+      "name": "qwen2.5-7b-instruct",
+      "maxContext": 128000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 50000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "qwen2.5-14b-instruct",
+      "name": "qwen2.5-14b-instruct",
+      "maxContext": 128000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 50000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "qwen2.5-32b-instruct",
+      "name": "qwen2.5-32b-instruct",
+      "maxContext": 128000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 50000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "qwen2.5-72b-instruct",
+      "name": "Qwen2.5-72B-instruct",
+      "maxContext": 128000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 50000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Siliconflow.json

@@ -0,0 +1,204 @@
+{
+  "provider": "Siliconflow",
+  "list": [
+    {
+      "model": "Qwen/Qwen2.5-72B-Instruct",
+      "name": "Qwen/Qwen2.5-72B-Instruct",
+      "maxContext": 128000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 50000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "Qwen/Qwen2-VL-72B-Instruct",
+      "name": "Qwen/Qwen2-VL-72B-Instruct",
+      "maxContext": 32000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1,
+      "censor": false,
+      "vision": true,
+      "datasetProcess": false,
+      "usedInClassify": false,
+      "usedInExtractFields": false,
+      "usedInToolCall": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "defaultConfig": {},
+      "type": "llm"
+    },
+    {
+      "model": "deepseek-ai/DeepSeek-V2.5",
+      "name": "deepseek-ai/DeepSeek-V2.5",
+      "maxContext": 32000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "BAAI/bge-m3",
+      "name": "BAAI/bge-m3",
+      "defaultToken": 512,
+      "maxToken": 8000,
+      "type": "embedding"
+    },
+    {
+      "model": "FunAudioLLM/CosyVoice2-0.5B",
+      "name": "FunAudioLLM/CosyVoice2-0.5B",
+      "voices": [
+        {
+          "label": "alex",
+          "value": "FunAudioLLM/CosyVoice2-0.5B:alex"
+        },
+        {
+          "label": "anna",
+          "value": "FunAudioLLM/CosyVoice2-0.5B:anna"
+        },
+        {
+          "label": "bella",
+          "value": "FunAudioLLM/CosyVoice2-0.5B:bella"
+        },
+        {
+          "label": "benjamin",
+          "value": "FunAudioLLM/CosyVoice2-0.5B:benjamin"
+        },
+        {
+          "label": "charles",
+          "value": "FunAudioLLM/CosyVoice2-0.5B:charles"
+        },
+        {
+          "label": "claire",
+          "value": "FunAudioLLM/CosyVoice2-0.5B:claire"
+        },
+        {
+          "label": "david",
+          "value": "FunAudioLLM/CosyVoice2-0.5B:david"
+        },
+        {
+          "label": "diana",
+          "value": "FunAudioLLM/CosyVoice2-0.5B:diana"
+        }
+      ],
+      "type": "tts"
+    },
+    {
+      "model": "RVC-Boss/GPT-SoVITS",
+      "name": "RVC-Boss/GPT-SoVITS",
+      "voices": [
+        {
+          "label": "alex",
+          "value": "RVC-Boss/GPT-SoVITS:alex"
+        },
+        {
+          "label": "anna",
+          "value": "RVC-Boss/GPT-SoVITS:anna"
+        },
+        {
+          "label": "bella",
+          "value": "RVC-Boss/GPT-SoVITS:bella"
+        },
+        {
+          "label": "benjamin",
+          "value": "RVC-Boss/GPT-SoVITS:benjamin"
+        },
+        {
+          "label": "charles",
+          "value": "RVC-Boss/GPT-SoVITS:charles"
+        },
+        {
+          "label": "claire",
+          "value": "RVC-Boss/GPT-SoVITS:claire"
+        },
+        {
+          "label": "david",
+          "value": "RVC-Boss/GPT-SoVITS:david"
+        },
+        {
+          "label": "diana",
+          "value": "RVC-Boss/GPT-SoVITS:diana"
+        }
+      ],
+      "type": "tts"
+    },
+    {
+      "model": "fishaudio/fish-speech-1.5",
+      "name": "fish-speech-1.5",
+      "voices": [
+        {
+          "label": "alex",
+          "value": "fishaudio/fish-speech-1.5:alex"
+        },
+        {
+          "label": "anna",
+          "value": "fishaudio/fish-speech-1.5:anna"
+        },
+        {
+          "label": "bella",
+          "value": "fishaudio/fish-speech-1.5:bella"
+        },
+        {
+          "label": "benjamin",
+          "value": "fishaudio/fish-speech-1.5:benjamin"
+        },
+        {
+          "label": "charles",
+          "value": "fishaudio/fish-speech-1.5:charles"
+        },
+        {
+          "label": "claire",
+          "value": "fishaudio/fish-speech-1.5:claire"
+        },
+        {
+          "label": "david",
+          "value": "fishaudio/fish-speech-1.5:david"
+        },
+        {
+          "label": "diana",
+          "value": "fishaudio/fish-speech-1.5:diana"
+        }
+      ],
+      "type": "tts"
+    },
+    {
+      "model": "FunAudioLLM/SenseVoiceSmall",
+      "name": "FunAudioLLM/SenseVoiceSmall",
+      "type": "stt"
+    },
+    {
+      "model": "BAAI/bge-reranker-v2-m3",
+      "name": "BAAI/bge-reranker-v2-m3",
+      "type": "rerank"
+    }
+  ]
+}

packages/service/core/ai/config/provider/SparkDesk.json

@@ -0,0 +1,129 @@
+{
+  "provider": "SparkDesk",
+  "list": [
+    {
+      "model": "lite",
+      "name": "SparkDesk-lite",
+      "maxContext": 32000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "generalv3",
+      "name": "SparkDesk-Pro",
+      "maxContext": 8000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 8000,
+      "maxTemperature": 1,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "pro-128k",
+      "name": "SparkDesk-Pro-128k",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 128000,
+      "maxTemperature": 1,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "generalv3.5",
+      "name": "SparkDesk-max",
+      "maxContext": 8000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 8000,
+      "maxTemperature": 1,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "max-32k",
+      "name": "SparkDesk-max-32k",
+      "maxContext": 32000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "4.0Ultra",
+      "name": "SparkDesk-v4.0 Ultra",
+      "maxContext": 8000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 8000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    }
+  ]
+}

packages/service/core/ai/config/provider/StepFun.json

@@ -0,0 +1,308 @@
+{
+  "provider": "StepFun",
+  "list": [
+    {
+      "model": "step-1-flash",
+      "name": "step-1-flash",
+      "maxContext": 8000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 6000,
+      "maxTemperature": 2,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "step-1-8k",
+      "name": "step-1-8k",
+      "maxContext": 8000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 8000,
+      "maxTemperature": 2,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "step-1-32k",
+      "name": "step-1-32k",
+      "maxContext": 32000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 32000,
+      "maxTemperature": 2,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "step-1-128k",
+      "name": "step-1-128k",
+      "maxContext": 128000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 128000,
+      "maxTemperature": 2,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "step-1-256k",
+      "name": "step-1-256k",
+      "maxContext": 256000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 256000,
+      "maxTemperature": 2,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "step-1o-vision-32k",
+      "name": "step-1o-vision-32k",
+      "maxContext": 32000,
+      "quoteMaxToken": 32000,
+      "maxResponse": 8000,
+      "maxTemperature": 2,
+      "vision": true,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "step-1v-8k",
+      "name": "step-1v-8k",
+      "maxContext": 8000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 8000,
+      "maxTemperature": 2,
+      "vision": true,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "step-1v-32k",
+      "name": "step-1v-32k",
+      "maxContext": 32000,
+      "quoteMaxToken": 32000,
+      "maxResponse": 8000,
+      "maxTemperature": 2,
+      "vision": true,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "step-2-mini",
+      "name": "step-2-mini",
+      "maxContext": 8000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 6000,
+      "maxTemperature": 2,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "step-2-16k",
+      "name": "step-2-16k",
+      "maxContext": 16000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 4000,
+      "maxTemperature": 2,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "step-2-16k-exp",
+      "name": "step-2-16k-exp",
+      "maxContext": 16000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 4000,
+      "maxTemperature": 2,
+      "vision": false,
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "usedInExtractFields": true,
+      "usedInToolCall": true,
+      "usedInQueryExtension": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "customCQPrompt": "",
+      "customExtractPrompt": "",
+      "defaultSystemChatPrompt": "",
+      "type": "llm"
+    },
+    {
+      "model": "step-tts-mini",
+      "name": "step-tts-mini",
+      "voices": [
+        {
+          "label": "cixingnansheng",
+          "value": "cixingnansheng"
+        },
+        {
+          "label": "zhengpaiqingnian",
+          "value": "zhengpaiqingnian"
+        },
+        {
+          "label": "yuanqinansheng",
+          "value": "yuanqinansheng"
+        },
+        {
+          "label": "qingniandaxuesheng",
+          "value": "qingniandaxuesheng"
+        },
+        {
+          "label": "boyinnansheng",
+          "value": "boyinnansheng"
+        },
+        {
+          "label": "ruyananshi",
+          "value": "ruyananshi"
+        },
+        {
+          "label": "shenchennanyin",
+          "value": "shenchennanyin"
+        },
+        {
+          "label": "qinqienvsheng",
+          "value": "qinqienvsheng"
+        },
+        {
+          "label": "wenrounvsheng",
+          "value": "wenrounvsheng"
+        },
+        {
+          "label": "jilingshaonv",
+          "value": "jilingshaonv"
+        },
+        {
+          "label": "yuanqishaonv",
+          "value": "yuanqishaonv"
+        },
+        {
+          "label": "ruanmengnvsheng",
+          "value": "ruanmengnvsheng"
+        },
+        {
+          "label": "youyanvsheng",
+          "value": "youyanvsheng"
+        },
+        {
+          "label": "lengyanyujie",
+          "value": "lengyanyujie"
+        },
+        {
+          "label": "shuangkuaijiejie",
+          "value": "shuangkuaijiejie"
+        },
+        {
+          "label": "wenjingxuejie",
+          "value": "wenjingxuejie"
+        },
+        {
+          "label": "linjiajiejie",
+          "value": "linjiajiejie"
+        },
+        {
+          "label": "linjiameimei",
+          "value": "linjiameimei"
+        },
+        {
+          "label": "zhixingjiejie",
+          "value": "zhixingjiejie"
+        }
+      ],
+      "type": "tts"
+    }
+  ]
+}

packages/service/core/ai/config/provider/Yi.json

@@ -0,0 +1,49 @@
+{
+  "provider": "Yi",
+  "list": [
+    {
+      "model": "yi-lightning",
+      "name": "yi-lightning",
+      "maxContext": 16000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 12000,
+      "maxTemperature": 1,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    },
+    {
+      "model": "yi-vision-v2",
+      "name": "yi-vision-v2",
+      "maxContext": 16000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 12000,
+      "maxTemperature": 1,
+      "vision": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {},
+      "fieldMap": {},
+      "type": "llm"
+    }
+  ]
+}

packages/service/core/ai/config/rerank/bge-reranker-v2-m3.json

@@ -1,6 +0,0 @@
-{
-  "provider": "BAAI",
-  "model": "bge-reranker-v2-m3",
-  "name": "bge-reranker-v2-m3",
-  "charsPointsPrice": 0
-}

packages/service/core/ai/config/schema.ts

@@ -0,0 +1,21 @@
+import { connectionMongo, getMongoModel } from '../../../common/mongo';
+const { Schema } = connectionMongo;
+import type { SystemModelSchemaType } from '../type';
+
+const SystemModelSchema = new Schema({
+  model: {
+    type: String,
+    required: true,
+    unique: true
+  },
+  metadata: {
+    type: Object,
+    required: true,
+    default: {}
+  }
+});
+
+export const MongoSystemModel = getMongoModel<SystemModelSchemaType>(
+  'system_models',
+  SystemModelSchema
+);

packages/service/core/ai/config/stt/whisper-1.json

@@ -1,6 +0,0 @@
-{
-  "provider": "OpenAI",
-  "model": "whisper-1",
-  "name": "whisper-1",
-  "charsPointsPrice": 0
-}

packages/service/core/ai/config/tts/tts-1.json

@@ -1,32 +0,0 @@
-{
-  "provider": "OpenAI",
-  "model": "tts-1",
-  "name": "TTS1",
-  "charsPointsPrice": 0,
-  "voices": [
-    {
-      "label": "Alloy",
-      "value": "alloy"
-    },
-    {
-      "label": "Echo",
-      "value": "echo"
-    },
-    {
-      "label": "Fable",
-      "value": "fable"
-    },
-    {
-      "label": "Onyx",
-      "value": "onyx"
-    },
-    {
-      "label": "Nova",
-      "value": "nova"
-    },
-    {
-      "label": "Shimmer",
-      "value": "shimmer"
-    }
-  ]
-}

packages/service/core/ai/config/utils.ts

@@ -0,0 +1,195 @@
+import path from 'path';
+import * as fs from 'fs';
+import { SystemModelItemType } from '../type';
+import { ModelTypeEnum } from '@fastgpt/global/core/ai/model';
+import { MongoSystemModel } from './schema';
+import {
+  LLMModelItemType,
+  EmbeddingModelItemType,
+  TTSModelType,
+  STTModelType,
+  ReRankModelItemType
+} from '@fastgpt/global/core/ai/model.d';
+import { debounce } from 'lodash';
+import { ModelProviderType } from '@fastgpt/global/core/ai/provider';
+import { findModelFromAlldata } from '../model';
+import {
+  reloadFastGPTConfigBuffer,
+  updateFastGPTConfigBuffer
+} from '../../../common/system/config/controller';
+import { delay } from '@fastgpt/global/common/system/utils';
+
+/* 
+  TODO: 分优先级读取：
+  1. 有外部挂载目录，则读取外部的
+  2. 没有外部挂载目录，则读取本地的。然后试图拉取云端的进行覆盖。
+*/
+export const loadSystemModels = async (init = false) => {
+  const getProviderList = () => {
+    const currentFileUrl = new URL(import.meta.url);
+    const modelsPath = path.join(path.dirname(currentFileUrl.pathname), 'provider');
+
+    return fs.readdirSync(modelsPath) as string[];
+  };
+  const pushModel = (model: SystemModelItemType) => {
+    global.systemModelList.push(model);
+
+    if (model.isActive) {
+      global.systemActiveModelList.push(model);
+
+      if (model.type === ModelTypeEnum.llm) {
+        global.llmModelMap.set(model.model, model);
+        global.llmModelMap.set(model.name, model);
+        if (model.isDefault) {
+          global.systemDefaultModel.llm = model;
+        }
+      } else if (model.type === ModelTypeEnum.embedding) {
+        global.embeddingModelMap.set(model.model, model);
+        global.embeddingModelMap.set(model.name, model);
+        if (model.isDefault) {
+          global.systemDefaultModel.embedding = model;
+        }
+      } else if (model.type === ModelTypeEnum.tts) {
+        global.ttsModelMap.set(model.model, model);
+        global.ttsModelMap.set(model.name, model);
+        if (model.isDefault) {
+          global.systemDefaultModel.tts = model;
+        }
+      } else if (model.type === ModelTypeEnum.stt) {
+        global.sttModelMap.set(model.model, model);
+        global.sttModelMap.set(model.name, model);
+        if (model.isDefault) {
+          global.systemDefaultModel.stt = model;
+        }
+      } else if (model.type === ModelTypeEnum.rerank) {
+        global.reRankModelMap.set(model.model, model);
+        global.reRankModelMap.set(model.name, model);
+        if (model.isDefault) {
+          global.systemDefaultModel.rerank = model;
+        }
+      }
+    }
+  };
+
+  if (!init && global.systemModelList) return;
+
+  global.systemModelList = [];
+  global.systemActiveModelList = [];
+  global.llmModelMap = new Map<string, LLMModelItemType>();
+  global.embeddingModelMap = new Map<string, EmbeddingModelItemType>();
+  global.ttsModelMap = new Map<string, TTSModelType>();
+  global.sttModelMap = new Map<string, STTModelType>();
+  global.reRankModelMap = new Map<string, ReRankModelItemType>();
+  // @ts-ignore
+  global.systemDefaultModel = {};
+
+  try {
+    const dbModels = await MongoSystemModel.find({}).lean();
+    const providerList = getProviderList();
+
+    // System model
+    await Promise.all(
+      providerList.map(async (name) => {
+        const fileContent = (await import(`./provider/${name}`))?.default as {
+          provider: ModelProviderType;
+          list: SystemModelItemType[];
+        };
+
+        fileContent.list.forEach((fileModel) => {
+          const dbModel = dbModels.find((item) => item.model === fileModel.model);
+
+          const modelData: any = {
+            ...fileModel,
+            ...dbModel?.metadata,
+            provider: dbModel?.metadata?.provider || fileContent.provider,
+            type: dbModel?.metadata?.type || fileModel.type,
+            isCustom: false
+          };
+
+          pushModel(modelData);
+        });
+      })
+    );
+
+    // Custom model
+    dbModels.forEach((dbModel) => {
+      if (global.systemModelList.find((item) => item.model === dbModel.model)) return;
+
+      pushModel({
+        ...dbModel.metadata,
+        isCustom: true
+      });
+    });
+
+    // Default model check
+    if (!global.systemDefaultModel.llm) {
+      global.systemDefaultModel.llm = Array.from(global.llmModelMap.values())[0];
+    }
+    if (!global.systemDefaultModel.embedding) {
+      global.systemDefaultModel.embedding = Array.from(global.embeddingModelMap.values())[0];
+    }
+    if (!global.systemDefaultModel.tts) {
+      global.systemDefaultModel.tts = Array.from(global.ttsModelMap.values())[0];
+    }
+    if (!global.systemDefaultModel.stt) {
+      global.systemDefaultModel.stt = Array.from(global.sttModelMap.values())[0];
+    }
+    if (!global.systemDefaultModel.rerank) {
+      global.systemDefaultModel.rerank = Array.from(global.reRankModelMap.values())[0];
+    }
+
+    console.log('Load models success', JSON.stringify(global.systemActiveModelList, null, 2));
+  } catch (error) {
+    console.error('Load models error', error);
+    // @ts-ignore
+    global.systemModelList = undefined;
+  }
+};
+
+export const getSystemModelConfig = async (model: string): Promise<SystemModelItemType> => {
+  const modelData = findModelFromAlldata(model);
+  if (!modelData) return Promise.reject('Model is not found');
+  if (modelData.isCustom) return Promise.reject('Custom model not data');
+
+  // Read file
+  const fileContent = (await import(`./provider/${modelData.provider}`))?.default as {
+    provider: ModelProviderType;
+    list: SystemModelItemType[];
+  };
+
+  const config = fileContent.list.find((item) => item.model === model);
+
+  if (!config) return Promise.reject('Model config is not found');
+
+  return {
+    ...config,
+    provider: modelData.provider,
+    isCustom: false
+  };
+};
+
+export const watchSystemModelUpdate = () => {
+  const changeStream = MongoSystemModel.watch();
+
+  changeStream.on(
+    'change',
+    debounce(async () => {
+      try {
+        // Main node will reload twice
+        await loadSystemModels(true);
+        // All node reaload buffer
+        await reloadFastGPTConfigBuffer();
+      } catch (error) {}
+    }, 500)
+  );
+};
+
+// 更新完模型后，需要重载缓存
+export const updatedReloadSystemModel = async () => {
+  // 1. 更新模型（所有节点都会触发）
+  await loadSystemModels(true);
+  // 2. 更新缓存（仅主节点触发）
+  await updateFastGPTConfigBuffer();
+  // 3. 延迟1秒，等待其他节点刷新
+  await delay(1000);
+};

packages/service/core/ai/embedding/index.ts

@@ -1,11 +1,11 @@
-import { VectorModelItemType } from '@fastgpt/global/core/ai/model.d';
+import { EmbeddingModelItemType } from '@fastgpt/global/core/ai/model.d';
 import { getAIApi } from '../config';
 import { countPromptTokens } from '../../../common/string/tiktoken/index';
 import { EmbeddingTypeEnm } from '@fastgpt/global/core/ai/constants';
 import { addLog } from '../../../common/system/log';
 
 type GetVectorProps = {
-  model: VectorModelItemType;
+  model: EmbeddingModelItemType;
   input: string;
   type?: `${EmbeddingTypeEnm}`;
 };
@@ -24,13 +24,23 @@ export async function getVectorsByText({ model, input, type }: GetVectorProps) {
 
     // input text to vector
     const result = await ai.embeddings
-      .create({
-        ...model.defaultConfig,
-        ...(type === EmbeddingTypeEnm.db && model.dbConfig),
-        ...(type === EmbeddingTypeEnm.query && model.queryConfig),
-        model: model.model,
-        input: [input]
-      })
+      .create(
+        {
+          ...model.defaultConfig,
+          ...(type === EmbeddingTypeEnm.db && model.dbConfig),
+          ...(type === EmbeddingTypeEnm.query && model.queryConfig),
+          model: model.model,
+          input: [input]
+        },
+        model.requestUrl && model.requestAuth
+          ? {
+              path: model.requestUrl,
+              headers: {
+                Authorization: `Bearer ${model.requestAuth}`
+              }
+            }
+          : {}
+      )
       .then(async (res) => {
         if (!res.data) {
           addLog.error('Embedding API is not responding', res);

packages/service/core/ai/model.ts

@@ -1,51 +1,52 @@
+import { SystemModelItemType } from './type';
+
+export const getDefaultLLMModel = () => global?.systemDefaultModel.llm!;
 export const getLLMModel = (model?: string) => {
-  return (
-    global.llmModels.find((item) => item.model === model || item.name === model) ??
-    global.llmModels[0]
-  );
+  if (!model) return getDefaultLLMModel();
+  return global.llmModelMap.get(model) || getDefaultLLMModel();
 };
 
 export const getDatasetModel = (model?: string) => {
   return (
-    global.llmModels
+    Array.from(global.llmModelMap.values())
       ?.filter((item) => item.datasetProcess)
-      ?.find((item) => item.model === model || item.name === model) ?? global.llmModels[0]
+      ?.find((item) => item.model === model || item.name === model) ?? getDefaultLLMModel()
   );
 };
 
-export const getVectorModel = (model?: string) => {
-  return (
-    global.vectorModels.find((item) => item.model === model || item.name === model) ||
-    global.vectorModels[0]
-  );
+export const getDefaultEmbeddingModel = () => global?.systemDefaultModel.embedding!;
+export const getEmbeddingModel = (model?: string) => {
+  if (!model) return getDefaultEmbeddingModel();
+  return global.embeddingModelMap.get(model) || getDefaultEmbeddingModel();
 };
 
-export function getAudioSpeechModel(model?: string) {
-  return (
-    global.audioSpeechModels.find((item) => item.model === model || item.name === model) ||
-    global.audioSpeechModels[0]
-  );
+export const getDefaultTTSModel = () => global?.systemDefaultModel.tts!;
+export function getTTSModel(model?: string) {
+  if (!model) return getDefaultTTSModel();
+  return global.ttsModelMap.get(model) || getDefaultTTSModel();
 }
 
-export function getWhisperModel(model?: string) {
-  return global.whisperModel;
+export const getDefaultSTTModel = () => global?.systemDefaultModel.stt!;
+export function getSTTModel(model?: string) {
+  if (!model) return getDefaultSTTModel();
+  return global.sttModelMap.get(model) || getDefaultSTTModel();
 }
 
+export const getDefaultRerankModel = () => global?.systemDefaultModel.rerank!;
 export function getReRankModel(model?: string) {
-  return global.reRankModels.find((item) => item.model === model);
+  if (!model) return getDefaultRerankModel();
+  return global.reRankModelMap.get(model) || getDefaultRerankModel();
 }
 
-export enum ModelTypeEnum {
-  llm = 'llm',
-  vector = 'vector',
-  audioSpeech = 'audioSpeech',
-  whisper = 'whisper',
-  rerank = 'rerank'
-}
-export const getModelMap = {
-  [ModelTypeEnum.llm]: getLLMModel,
-  [ModelTypeEnum.vector]: getVectorModel,
-  [ModelTypeEnum.audioSpeech]: getAudioSpeechModel,
-  [ModelTypeEnum.whisper]: getWhisperModel,
-  [ModelTypeEnum.rerank]: getReRankModel
+export const findAIModel = (model: string): SystemModelItemType | undefined => {
+  return (
+    global.llmModelMap.get(model) ||
+    global.embeddingModelMap.get(model) ||
+    global.ttsModelMap.get(model) ||
+    global.sttModelMap.get(model) ||
+    global.reRankModelMap.get(model)
+  );
+};
+export const findModelFromAlldata = (model: string) => {
+  return global.systemModelList.find((item) => item.model === model);
 };

packages/service/core/ai/rerank/index.ts

@@ -1,5 +1,8 @@
 import { addLog } from '../../../common/system/log';
 import { POST } from '../../../common/api/serverRequest';
+import { getDefaultRerankModel } from '../model';
+import { getAxiosConfig } from '../config';
+import { ReRankModelItemType } from '@fastgpt/global/core/ai/model.d';
 
 type PostReRankResponse = {
   id: string;
@@ -11,21 +14,23 @@ type PostReRankResponse = {
 type ReRankCallResult = { id: string; score?: number }[];
 
 export function reRankRecall({
+  model = getDefaultRerankModel(),
   query,
   documents
 }: {
+  model?: ReRankModelItemType;
   query: string;
   documents: { id: string; text: string }[];
 }): Promise<ReRankCallResult> {
-  const model = global.reRankModels[0];
-
-  if (!model || !model?.requestUrl) {
+  if (!model) {
     return Promise.reject('no rerank model');
   }
 
+  const { baseUrl, authorization } = getAxiosConfig({});
+
   let start = Date.now();
   return POST<PostReRankResponse>(
-    model.requestUrl,
+    model.requestUrl ? model.requestUrl : `${baseUrl}/rerank`,
     {
       model: model.model,
       query,
@@ -33,7 +38,7 @@ export function reRankRecall({
     },
     {
       headers: {
-        Authorization: `Bearer ${model.requestAuth}`
+        Authorization: model.requestAuth ? model.requestAuth : authorization
       },
       timeout: 30000
     }
@@ -53,6 +58,6 @@ export function reRankRecall({
     .catch((err) => {
       addLog.error('rerank error', err);
 
-      return [];
+      return Promise.reject(err);
     });
 }

packages/service/core/ai/type.d.ts

@@ -0,0 +1,42 @@
+import { ModelTypeEnum } from '@fastgpt/global/core/ai/model';
+import {
+  STTModelType,
+  ReRankModelItemType,
+  TTSModelType,
+  EmbeddingModelItemType,
+  LLMModelItemType
+} from '@fastgpt/global/core/ai/model.d';
+
+export type SystemModelSchemaType = {
+  _id: string;
+  model: string;
+  metadata: SystemModelItemType;
+};
+
+export type SystemModelItemType =
+  | LLMModelItemType
+  | EmbeddingModelItemType
+  | TTSModelType
+  | STTModelType
+  | ReRankModelItemType;
+
+export type SystemDefaultModelType = {
+  [ModelTypeEnum.llm]?: LLMModelItemType;
+  [ModelTypeEnum.embedding]?: EmbeddingModelItemType;
+  [ModelTypeEnum.tts]?: TTSModelType;
+  [ModelTypeEnum.stt]?: STTModelType;
+  [ModelTypeEnum.rerank]?: ReRankModelItemType;
+};
+
+declare global {
+  var systemModelList: SystemModelItemType[];
+  // var systemModelMap: Map<string, SystemModelItemType>;
+  var llmModelMap: Map<string, LLMModelItemType>;
+  var embeddingModelMap: Map<string, EmbeddingModelItemType>;
+  var ttsModelMap: Map<string, TTSModelType>;
+  var sttModelMap: Map<string, STTModelType>;
+  var reRankModelMap: Map<string, ReRankModelItemType>;
+
+  var systemActiveModelList: SystemModelItemType[];
+  var systemDefaultModel: SystemDefaultModelType;
+}

packages/service/core/ai/utils.ts

@@ -2,7 +2,8 @@ import { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
 import {
   ChatCompletionCreateParamsNonStreaming,
   ChatCompletionCreateParamsStreaming,
-  ChatCompletionMessageParam
+  ChatCompletionMessageParam,
+  StreamChatType
 } from '@fastgpt/global/core/ai/type';
 import { countGptMessagesTokens } from '../../common/string/tiktoken';
 import { getLLMModel } from './model';
@@ -87,3 +88,12 @@ export const llmCompletionsBodyFormat = <T extends CompletionsBodyType>(
 
   return requestBody as InferCompletionsBody<T>;
 };
+
+export const llmStreamResponseToText = async (response: StreamChatType) => {
+  let answer = '';
+  for await (const part of response) {
+    const content = part.choices?.[0]?.delta?.content || '';
+    answer += content;
+  }
+  return answer;
+};

packages/service/core/dataset/collection/controller.ts

@@ -19,7 +19,7 @@ import { predictDataLimitLength } from '../../../../global/core/dataset/utils';
 import { mongoSessionRun } from '../../../common/mongo/sessionRun';
 import { createTrainingUsage } from '../../../support/wallet/usage/controller';
 import { UsageSourceEnum } from '@fastgpt/global/support/wallet/usage/constants';
-import { getLLMModel, getVectorModel } from '../../ai/model';
+import { getLLMModel, getEmbeddingModel } from '../../ai/model';
 import { pushDataListToTrainingQueue } from '../training/controller';
 import { MongoImage } from '../../../common/file/image/schema';
 import { hashStr } from '@fastgpt/global/common/string/tools';
@@ -93,7 +93,7 @@ export const createCollectionAndInsertData = async ({
       tmbId,
       appName: usageName,
       billSource: UsageSourceEnum.training,
-      vectorModel: getVectorModel(dataset.vectorModel)?.name,
+      vectorModel: getEmbeddingModel(dataset.vectorModel)?.name,
       agentModel: getLLMModel(dataset.agentModel)?.name,
       session
     });

packages/service/core/dataset/data/dataTextSchema.ts

@@ -33,7 +33,18 @@ const DatasetDataTextSchema = new Schema({
 });
 
 try {
-  DatasetDataTextSchema.index({ teamId: 1, datasetId: 1, fullTextToken: 'text' });
+  DatasetDataTextSchema.index(
+    { teamId: 1, datasetId: 1, fullTextToken: 'text' },
+    {
+      name: 'teamId_1_datasetId_1_fullTextToken_text',
+      default_language: 'none',
+      collation: {
+        locale: 'simple', // 使用简单匹配规则
+        strength: 2, //  忽略大小写
+        caseLevel: false // 进一步确保大小写不敏感
+      }
+    }
+  );
   DatasetDataTextSchema.index({ dataId: 1 }, { unique: true });
 } catch (error) {
   console.log(error);

packages/service/core/dataset/search/controller.ts

@@ -5,10 +5,9 @@ import {
 } from '@fastgpt/global/core/dataset/constants';
 import { recallFromVectorStore } from '../../../common/vectorStore/controller';
 import { getVectorsByText } from '../../ai/embedding';
-import { getVectorModel } from '../../ai/model';
+import { getEmbeddingModel, getDefaultRerankModel } from '../../ai/model';
 import { MongoDatasetData } from '../data/schema';
 import {
-  DatasetDataSchemaType,
   DatasetDataTextSchemaType,
   SearchDataResponseItemType
 } from '@fastgpt/global/core/dataset/type';
@@ -67,7 +66,7 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
 
   /* init params */
   searchMode = DatasetSearchModeMap[searchMode] ? searchMode : DatasetSearchModeEnum.embedding;
-  usingReRank = usingReRank && global.reRankModels.length > 0;
+  usingReRank = usingReRank && !!getDefaultRerankModel();
 
   // Compatible with topk limit
   let set = new Set<string>();
@@ -253,7 +252,7 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
     filterCollectionIdList?: string[];
   }) => {
     const { vectors, tokens } = await getVectorsByText({
-      model: getVectorModel(model),
+      model: getEmbeddingModel(model),
       input: query,
       type: 'query'
     });
@@ -348,119 +347,6 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
       };
     }
 
-    const searchResults = (
-      await Promise.all(
-        datasetIds.map(async (id) => {
-          return MongoDatasetData.aggregate(
-            [
-              {
-                $match: {
-                  teamId: new Types.ObjectId(teamId),
-                  datasetId: new Types.ObjectId(id),
-                  $text: { $search: jiebaSplit({ text: query }) },
-                  ...(filterCollectionIdList
-                    ? {
-                        collectionId: {
-                          $in: filterCollectionIdList.map((id) => new Types.ObjectId(id))
-                        }
-                      }
-                    : {}),
-                  ...(forbidCollectionIdList && forbidCollectionIdList.length > 0
-                    ? {
-                        collectionId: {
-                          $nin: forbidCollectionIdList.map((id) => new Types.ObjectId(id))
-                        }
-                      }
-                    : {})
-                }
-              },
-              {
-                $sort: {
-                  score: { $meta: 'textScore' }
-                }
-              },
-              {
-                $limit: limit
-              },
-              {
-                $project: {
-                  _id: 1,
-                  datasetId: 1,
-                  collectionId: 1,
-                  updateTime: 1,
-                  q: 1,
-                  a: 1,
-                  chunkIndex: 1,
-                  score: { $meta: 'textScore' }
-                }
-              }
-            ],
-            {
-              ...readFromSecondary
-            }
-          );
-        })
-      )
-    ).flat() as (DatasetDataSchemaType & { score: number })[];
-
-    // Get data and collections
-    const collections = await MongoDatasetCollection.find(
-      {
-        _id: { $in: searchResults.map((item) => item.collectionId) }
-      },
-      '_id name fileId rawLink externalFileId externalFileUrl',
-      { ...readFromSecondary }
-    ).lean();
-
-    return {
-      fullTextRecallResults: searchResults
-        .map((data, index) => {
-          const collection = collections.find(
-            (col) => String(col._id) === String(data.collectionId)
-          );
-          if (!collection) {
-            console.log('Collection is not found', data);
-            return;
-          }
-
-          return {
-            id: String(data._id),
-            datasetId: String(data.datasetId),
-            collectionId: String(data.collectionId),
-            updateTime: data.updateTime,
-            q: data.q,
-            a: data.a,
-            chunkIndex: data.chunkIndex,
-            indexes: data.indexes,
-            ...getCollectionSourceData(collection),
-            score: [{ type: SearchScoreTypeEnum.fullText, value: data.score ?? 0, index }]
-          };
-        })
-        .filter(Boolean) as SearchDataResponseItemType[],
-      tokenLen: 0
-    };
-  };
-  const fullTextRecall2 = async ({
-    query,
-    limit,
-    filterCollectionIdList,
-    forbidCollectionIdList
-  }: {
-    query: string;
-    limit: number;
-    filterCollectionIdList?: string[];
-    forbidCollectionIdList: string[];
-  }): Promise<{
-    fullTextRecallResults: SearchDataResponseItemType[];
-    tokenLen: number;
-  }> => {
-    if (limit === 0) {
-      return {
-        fullTextRecallResults: [],
-        tokenLen: 0
-      };
-    }
-
     const searchResults = (
       await Promise.all(
         datasetIds.map(async (id) => {
@@ -637,7 +523,7 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
             filterCollectionIdList
           }),
           // FullText tmp
-          fullTextRecall2({
+          fullTextRecall({
             query,
             limit: fullTextLimit,
             filterCollectionIdList,

packages/service/core/dataset/training/controller.ts

@@ -7,7 +7,7 @@ import type {
 import { TrainingModeEnum } from '@fastgpt/global/core/dataset/constants';
 import { simpleText } from '@fastgpt/global/common/string/tools';
 import { ClientSession } from '../../../common/mongo';
-import { getLLMModel, getVectorModel } from '../../ai/model';
+import { getLLMModel, getEmbeddingModel } from '../../ai/model';
 import { addLog } from '../../../common/system/log';
 import { getCollectionWithDataset } from '../controller';
 import { mongoSessionRun } from '../../../common/mongo/sessionRun';
@@ -70,7 +70,7 @@ export async function pushDataListToTrainingQueue({
     if (!agentModelData) {
       return Promise.reject(`File model ${agentModel} is inValid`);
     }
-    const vectorModelData = getVectorModel(vectorModel);
+    const vectorModelData = getEmbeddingModel(vectorModel);
     if (!vectorModelData) {
       return Promise.reject(`Vector model ${vectorModel} is inValid`);
     }

packages/service/core/workflow/dispatch/agent/classifyQuestion.ts

@@ -13,7 +13,7 @@ import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/
 import { replaceVariable } from '@fastgpt/global/common/string/tools';
 import { Prompt_CQJson } from '@fastgpt/global/core/ai/prompt/agent';
 import { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
-import { ModelTypeEnum, getLLMModel } from '../../../ai/model';
+import { getLLMModel } from '../../../ai/model';
 import { getHistories } from '../utils';
 import { formatModelChars2Points } from '../../../../support/wallet/usage/utils';
 import { DispatchNodeResultType } from '@fastgpt/global/core/workflow/runtime/type';
@@ -22,6 +22,7 @@ import { getHandleId } from '@fastgpt/global/core/workflow/utils';
 import { loadRequestMessages } from '../../../chat/utils';
 import { llmCompletionsBodyFormat } from '../../../ai/utils';
 import { addLog } from '../../../../common/system/log';
+import { ModelTypeEnum } from '../../../../../global/core/ai/model';
 
 type Props = ModuleDispatchProps<{
   [NodeInputKeyEnum.aiModel]: string;

packages/service/core/workflow/dispatch/agent/extract.ts

@@ -16,7 +16,7 @@ import { Prompt_ExtractJson } from '@fastgpt/global/core/ai/prompt/agent';
 import { replaceVariable, sliceJsonStr } from '@fastgpt/global/common/string/tools';
 import { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
 import { getHistories } from '../utils';
-import { ModelTypeEnum, getLLMModel } from '../../../ai/model';
+import { getLLMModel } from '../../../ai/model';
 import { formatModelChars2Points } from '../../../../support/wallet/usage/utils';
 import json5 from 'json5';
 import {
@@ -28,6 +28,7 @@ import { ChatCompletionRequestMessageRoleEnum } from '@fastgpt/global/core/ai/co
 import { DispatchNodeResultType } from '@fastgpt/global/core/workflow/runtime/type';
 import { chatValue2RuntimePrompt } from '@fastgpt/global/core/chat/adapt';
 import { llmCompletionsBodyFormat } from '../../../ai/utils';
+import { ModelTypeEnum } from '../../../../../global/core/ai/model';
 
 type Props = ModuleDispatchProps<{
   [NodeInputKeyEnum.history]?: ChatItemType[];

packages/service/core/workflow/dispatch/agent/runTool/index.ts

@@ -4,7 +4,7 @@ import type {
   DispatchNodeResultType,
   RuntimeNodeItemType
 } from '@fastgpt/global/core/workflow/runtime/type';
-import { ModelTypeEnum, getLLMModel } from '../../../../ai/model';
+import { getLLMModel } from '../../../../ai/model';
 import { filterToolNodeIdByEdges, getHistories } from '../../utils';
 import { runToolWithToolChoice } from './toolChoice';
 import { DispatchToolModuleProps, ToolNodeItemType } from './type.d';
@@ -30,6 +30,7 @@ import { parseUrlToFileType } from '@fastgpt/global/common/file/tools';
 import { Prompt_DocumentQuote } from '@fastgpt/global/core/ai/prompt/AIChat';
 import { FlowNodeTypeEnum } from '@fastgpt/global/core/workflow/node/constant';
 import { postTextCensor } from '../../../../../common/api/requestPlusApi';
+import { ModelTypeEnum } from '@fastgpt/global/core/ai/model';
 
 type Response = DispatchNodeResultType<{
   [NodeOutputKeyEnum.answerText]: string;

packages/service/core/workflow/dispatch/chat/oneapi.ts

@@ -33,7 +33,7 @@ import type { AIChatNodeProps } from '@fastgpt/global/core/workflow/runtime/type
 import { replaceVariable } from '@fastgpt/global/common/string/tools';
 import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/type';
 import { responseWriteController } from '../../../../common/response';
-import { getLLMModel, ModelTypeEnum } from '../../../ai/model';
+import { getLLMModel } from '../../../ai/model';
 import type { SearchDataResponseItemType } from '@fastgpt/global/core/dataset/type';
 import { NodeInputKeyEnum, NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
 import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
@@ -47,6 +47,7 @@ import { AiChatQuoteRoleType } from '@fastgpt/global/core/workflow/template/syst
 import { getFileContentFromLinks, getHistoryFileLinks } from '../tools/readFiles';
 import { parseUrlToFileType } from '@fastgpt/global/common/file/tools';
 import { i18nT } from '../../../../../web/i18n/utils';
+import { ModelTypeEnum } from '@fastgpt/global/core/ai/model';
 
 export type ChatProps = ModuleDispatchProps<
   AIChatNodeProps & {
@@ -280,11 +281,12 @@ async function filterDatasetQuote({
 }) {
   function getValue(item: SearchDataResponseItemType, index: number) {
     return replaceVariable(quoteTemplate || Prompt_QuoteTemplateList[0].value, {
+      id: item.id,
       q: item.q,
       a: item.a,
       updateTime: formatTime2YMDHM(item.updateTime),
       source: item.sourceName,
-      sourceId: String(item.sourceId || 'UnKnow'),
+      sourceId: String(item.sourceId || ''),
       index: index + 1
     });
   }

packages/service/core/workflow/dispatch/dataset/search.ts

@@ -6,7 +6,7 @@ import { formatModelChars2Points } from '../../../../support/wallet/usage/utils'
 import type { SelectedDatasetType } from '@fastgpt/global/core/workflow/api.d';
 import type { SearchDataResponseItemType } from '@fastgpt/global/core/dataset/type';
 import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/type';
-import { ModelTypeEnum, getLLMModel, getVectorModel } from '../../../ai/model';
+import { getLLMModel, getEmbeddingModel } from '../../../ai/model';
 import { searchDatasetData } from '../../../dataset/search/controller';
 import { NodeInputKeyEnum, NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
 import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
@@ -18,6 +18,7 @@ import { checkTeamReRankPermission } from '../../../../support/permission/teamLi
 import { MongoDataset } from '../../../dataset/schema';
 import { i18nT } from '../../../../../web/i18n/utils';
 import { filterDatasetsByTmbId } from '../../../dataset/utils';
+import { ModelTypeEnum } from '@fastgpt/global/core/ai/model';
 
 type DatasetSearchProps = ModuleDispatchProps<{
   [NodeInputKeyEnum.datasetSelectList]: SelectedDatasetType;
@@ -110,7 +111,7 @@ export async function dispatchDatasetSearch(
   // console.log(concatQueries, rewriteQuery, aiExtensionResult);
 
   // get vector
-  const vectorModel = getVectorModel(
+  const vectorModel = getEmbeddingModel(
     (await MongoDataset.findById(datasets[0].datasetId, 'vectorModel').lean())?.vectorModel
   );
 
@@ -138,7 +139,7 @@ export async function dispatchDatasetSearch(
   const { totalPoints, modelName } = formatModelChars2Points({
     model: vectorModel.model,
     inputTokens: tokens,
-    modelType: ModelTypeEnum.vector
+    modelType: ModelTypeEnum.embedding
   });
   const responseData: DispatchNodeResponseType & { totalPoints: number } = {
     totalPoints,