model perf (#3657)

* fix: model * dataset quote * perf: model config * model tag * doubao model config * perf: config model * feat: model test
2025-01-24 14:10:14 +08:00 · 2025-01-24 14:10:14 +08:00 · 60c72d05d1
commit 60c72d05d1
parent 99ce976b06
171 changed files with 1902 additions and 3126 deletions
--- a/docSite/assets/imgs/image-100.png
+++ b/docSite/assets/imgs/image-100.png
--- a/docSite/assets/imgs/image-101.png
+++ b/docSite/assets/imgs/image-101.png
--- a/docSite/assets/imgs/image-102.png
+++ b/docSite/assets/imgs/image-102.png
--- a/docSite/assets/imgs/image-103.png
+++ b/docSite/assets/imgs/image-103.png
--- a/docSite/assets/imgs/image-104.png
+++ b/docSite/assets/imgs/image-104.png
--- a/docSite/assets/imgs/image-105.png
+++ b/docSite/assets/imgs/image-105.png
--- a/docSite/assets/imgs/image-88.png
+++ b/docSite/assets/imgs/image-88.png
--- a/docSite/assets/imgs/image-89.png
+++ b/docSite/assets/imgs/image-89.png
--- a/docSite/assets/imgs/image-90.png
+++ b/docSite/assets/imgs/image-90.png
--- a/docSite/assets/imgs/image-91.png
+++ b/docSite/assets/imgs/image-91.png
--- a/docSite/assets/imgs/image-92.png
+++ b/docSite/assets/imgs/image-92.png
--- a/docSite/assets/imgs/image-93.png
+++ b/docSite/assets/imgs/image-93.png
--- a/docSite/assets/imgs/image-94.png
+++ b/docSite/assets/imgs/image-94.png
--- a/docSite/assets/imgs/image-95.png
+++ b/docSite/assets/imgs/image-95.png
--- a/docSite/assets/imgs/image-96.png
+++ b/docSite/assets/imgs/image-96.png
--- a/docSite/assets/imgs/image-97.png
+++ b/docSite/assets/imgs/image-97.png
--- a/docSite/assets/imgs/image-98.png
+++ b/docSite/assets/imgs/image-98.png
--- a/docSite/assets/imgs/image-99.png
+++ b/docSite/assets/imgs/image-99.png
--- a/docSite/content/zh-cn/docs/development/configuration.md
+++ b/docSite/content/zh-cn/docs/development/configuration.md
@ -25,247 +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）
-      "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
  }
 }
-```
-
-##  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
- MistralAI
- Groq
- 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"
-        }
-    ]
-}
-```
+```
--- a/docSite/content/zh-cn/docs/development/custom-models/bge-rerank.md
+++ b/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。
--- a/docSite/content/zh-cn/docs/development/docker.md
+++ b/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
--- a/docSite/content/zh-cn/docs/development/faq.md
+++ b/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)

--- a/docSite/content/zh-cn/docs/development/modelConfig/intro.md
+++ b/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
+  }
+}
+```
--- a/docSite/content/zh-cn/docs/development/modelConfig/one-api.md
+++ b/docSite/content/zh-cn/docs/development/modelConfig/one-api.md
@ -94,69 +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
-      "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

--- a/docSite/content/zh-cn/docs/development/modelConfig/siliconCloud.md
+++ b/docSite/content/zh-cn/docs/development/modelConfig/siliconCloud.md
@ -27,137 +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）
-      "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,
-      "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

--- a/docSite/content/zh-cn/docs/development/sealos.md
+++ b/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

 ```
--- a/docSite/content/zh-cn/docs/development/upgrading/4820.md
+++ b/docSite/content/zh-cn/docs/development/upgrading/4820.md
@ -9,6 +9,10 @@ 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：


@ -26,6 +30,7 @@ curl --location --request POST 'https://{{host}}/api/admin/initv4820' \

 ## 完整更新内容

-1. 新增 - 可视化模型配置。预设超过 100 个模型，方便进行模型配置。
+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. 优化 - 页面组件抽离，减少页面组件路由。
+3. 优化 - 页面组件抽离，减少页面组件路由。
+4. 优化 - 全文检索，忽略大小写。
--- a/packages/global/core/ai/provider.ts
+++ b/packages/global/core/ai/provider.ts
@ -7,6 +7,7 @@ export type ModelProviderIdType =
  | 'Meta'
  | 'MistralAI'
  | 'Groq'
+  | 'Grok'
  | 'AliCloud'
  | 'Qwen'
  | 'Doubao'
@ -60,6 +61,11 @@ export const ModelProviderList: ModelProviderType[] = [
    name: 'MistralAI',
    avatar: 'model/mistral'
  },
+  {
+    id: 'Grok',
+    name: 'Grok',
+    avatar: 'model/grok'
+  },
  {
    id: 'Groq',
    name: 'Groq',
--- a/packages/global/core/chat/constants.ts
+++ b/packages/global/core/chat/constants.ts
@ -75,5 +75,3 @@ export enum ChatStatusEnum {
  running = 'running',
  finish = 'finish'
 }
-
-export const MARKDOWN_QUOTE_SIGN = 'QUOTE SIGN';
--- a/packages/service/core/ai/audio/speech.ts
+++ b/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);
--- a/packages/service/core/ai/config.ts
+++ b/packages/service/core/ai/config.ts
@ -14,8 +14,7 @@ export const openaiBaseUrl = process.env.OPENAI_BASE_URL || 'https://api.openai.
 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({
@ -30,8 +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 {
--- a/packages/service/core/ai/config/embedding/siliconflow-bge-m3.json
+++ b/packages/service/core/ai/config/embedding/siliconflow-bge-m3.json
@ -0,0 +1,10 @@
+{
+  "provider": "Siliconflow",
+  "model": "BAAI/bge-m3",
+  "name": "BAAI/bge-m3",
+
+  "defaultToken": 512,
+  "maxToken": 8000,
+
+  "charsPointsPrice": 0
+}
--- a/packages/service/core/ai/config/embedding/text-embedding-3-large.json
+++ b/packages/service/core/ai/config/embedding/text-embedding-3-large.json
@ -4,7 +4,7 @@
  "name": "text-embedding-3-large",

  "defaultToken": 512,
-  "maxToken": 3000,
+  "maxToken": 8000,

  "charsPointsPrice": 0,

--- a/packages/service/core/ai/config/embedding/text-embedding-3-small.json
+++ b/packages/service/core/ai/config/embedding/text-embedding-3-small.json
@ -4,7 +4,7 @@
  "name": "text-embedding-3-small",

  "defaultToken": 512,
-  "maxToken": 3000,
+  "maxToken": 8000,

  "charsPointsPrice": 0
 }
--- a/packages/service/core/ai/config/embedding/text-embedding-ada-002.json
+++ b/packages/service/core/ai/config/embedding/text-embedding-ada-002.json
@ -4,7 +4,7 @@
  "name": "text-embedding-ada-002",

  "defaultToken": 512,
-  "maxToken": 3000,
+  "maxToken": 8000,

  "charsPointsPrice": 0
 }
--- a/packages/service/core/ai/config/llm/Doubao-lite-128k.json
+++ b/packages/service/core/ai/config/llm/Doubao-lite-128k.json
@ -3,26 +3,23 @@
  "model": "Doubao-lite-128k",
  "name": "Doubao-lite-128k",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 128000,
  "maxResponse": 4000,
  "quoteMaxToken": 120000,
  "maxTemperature": 1,

  "vision": false,
-  "toolChoice": false,
+  "toolChoice": true,
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": false,
+  "usedInToolCall": true,

  "defaultConfig": {},
  "fieldMap": {}
--- a/packages/service/core/ai/config/llm/Doubao-lite-32k.json
+++ b/packages/service/core/ai/config/llm/Doubao-lite-32k.json
@ -3,16 +3,13 @@
  "model": "Doubao-lite-32k",
  "name": "Doubao-lite-32k",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 32000,
  "maxResponse": 4000,
-  "quoteMaxToken": 30000,
+  "quoteMaxToken": 32000,
  "maxTemperature": 1,

  "vision": false,
-  "toolChoice": false,
+  "toolChoice": true,
  "functionCall": false,
  "defaultSystemChatPrompt": "",

@ -22,7 +19,7 @@
  "usedInExtractFields": true,
  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": false,
+  "usedInToolCall": true,

  "defaultConfig": {},
  "fieldMap": {}
--- a/packages/service/core/ai/config/llm/Doubao-lite-4k.json
+++ b/packages/service/core/ai/config/llm/Doubao-lite-4k.json
@ -0,0 +1,26 @@
+{
+  "provider": "Doubao",
+  "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": {}
+}
--- a/packages/service/core/ai/config/llm/Doubao-pro-128k.json
+++ b/packages/service/core/ai/config/llm/Doubao-pro-128k.json
@ -3,26 +3,23 @@
  "model": "Doubao-pro-128k",
  "name": "Doubao-pro-128k",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 128000,
  "maxResponse": 4000,
  "quoteMaxToken": 120000,
  "maxTemperature": 1,

  "vision": false,
-  "toolChoice": false,
+  "toolChoice": true,
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": false,
+  "usedInToolCall": true,

  "defaultConfig": {},
  "fieldMap": {}
--- a/packages/service/core/ai/config/llm/Doubao-pro-32k.json
+++ b/packages/service/core/ai/config/llm/Doubao-pro-32k.json
@ -3,16 +3,13 @@
  "model": "Doubao-pro-32k",
  "name": "Doubao-pro-32k",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 32000,
  "maxResponse": 4000,
-  "quoteMaxToken": 30000,
+  "quoteMaxToken": 32000,
  "maxTemperature": 1,

  "vision": false,
-  "toolChoice": false,
+  "toolChoice": true,
  "functionCall": false,
  "defaultSystemChatPrompt": "",

@ -22,7 +19,7 @@
  "usedInExtractFields": true,
  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": false,
+  "usedInToolCall": true,

  "defaultConfig": {},
  "fieldMap": {}
--- a/packages/service/core/ai/config/llm/Doubao-pro-4k.json
+++ b/packages/service/core/ai/config/llm/Doubao-pro-4k.json
@ -0,0 +1,26 @@
+{
+  "provider": "Doubao",
+  "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": {}
+}
--- a/packages/service/core/ai/config/llm/Doubao-vision-lite-32k.json
+++ b/packages/service/core/ai/config/llm/Doubao-vision-lite-32k.json
@ -3,12 +3,9 @@
  "model": "Doubao-vision-lite-32k",
  "name": "Doubao-vision-lite-32k",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 32000,
  "maxResponse": 4000,
-  "quoteMaxToken": 30000,
+  "quoteMaxToken": 32000,
  "maxTemperature": 1,

  "vision": true,
@ -22,7 +19,7 @@
  "usedInExtractFields": true,
  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": false,
+  "usedInToolCall": true,

  "defaultConfig": {},
  "fieldMap": {}
--- a/packages/service/core/ai/config/llm/Doubao-vision-pro-32k.json
+++ b/packages/service/core/ai/config/llm/Doubao-vision-pro-32k.json
@ -3,12 +3,9 @@
  "model": "Doubao-vision-pro-32k",
  "name": "Doubao-vision-pro-32k",

-  "censor": false,
-  "charsPointsPrice": 2,
-
  "maxContext": 32000,
  "maxResponse": 4000,
-  "quoteMaxToken": 30000,
+  "quoteMaxToken": 32000,
  "maxTemperature": 1,

  "vision": true,
@ -22,7 +19,7 @@
  "usedInExtractFields": true,
  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": false,
+  "usedInToolCall": true,

  "defaultConfig": {},
  "fieldMap": {}
--- a/packages/service/core/ai/config/llm/ERNIE-4.0-8K.json
+++ b/packages/service/core/ai/config/llm/ERNIE-4.0-8K.json
@ -3,9 +3,6 @@
  "model": "ERNIE-4.0-8K",
  "name": "ERNIE-4.0-8K",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 8000,
  "maxResponse": 2048,
  "quoteMaxToken": 5000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/ERNIE-4.0-Turbo-8K.json
+++ b/packages/service/core/ai/config/llm/ERNIE-4.0-Turbo-8K.json
@ -3,9 +3,6 @@
  "model": "ERNIE-4.0-Turbo-8K",
  "name": "ERNIE-4.0-Turbo-8K",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 8000,
  "maxResponse": 2048,
  "quoteMaxToken": 5000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/ERNIE-Lite-8K.json
+++ b/packages/service/core/ai/config/llm/ERNIE-Lite-8K.json
@ -3,9 +3,6 @@
  "model": "ERNIE-Lite-8K",
  "name": "ERNIE-lite-8k",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 8000,
  "maxResponse": 2048,
  "quoteMaxToken": 6000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/ERNIE-Speed-128K.json
+++ b/packages/service/core/ai/config/llm/ERNIE-Speed-128K.json
@ -1,10 +1,7 @@
 {
  "provider": "Ernie",
  "model": "ERNIE-Speed-128K",
-  "name": "ERNIE-Speed-128K(测试)",
-
-  "censor": false,
-  "charsPointsPrice": 0,
+  "name": "ERNIE-Speed-128K",

  "maxContext": 128000,
  "maxResponse": 4096,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/MiniMax-Text-01.json
+++ b/packages/service/core/ai/config/llm/MiniMax-Text-01.json
@ -3,9 +3,6 @@
  "model": "MiniMax-Text-01",
  "name": "MiniMax-Text-01",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 1000000,
  "maxResponse": 1000000,
  "quoteMaxToken": 100000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/SparkDesk-lite.json
+++ b/packages/service/core/ai/config/llm/SparkDesk-lite.json
@ -0,0 +1,20 @@
+{
+  "provider": "SparkDesk",
+  "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": ""
+}
--- a/packages/service/core/ai/config/llm/SparkDesk-max-32k.json
+++ b/packages/service/core/ai/config/llm/SparkDesk-max-32k.json
@ -0,0 +1,26 @@
+{
+  "provider": "SparkDesk",
+  "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": {}
+}
--- a/packages/service/core/ai/config/llm/SparkDesk-max.json
+++ b/packages/service/core/ai/config/llm/SparkDesk-max.json
@ -0,0 +1,20 @@
+{
+  "provider": "SparkDesk",
+  "model": "generalv3.5",
+  "name": "SparkDesk-max",
+  "maxContext": 32000,
+  "maxResponse": 8000,
+  "quoteMaxToken": 32000,
+  "maxTemperature": 1,
+  "vision": false,
+  "datasetProcess": true,
+  "usedInClassify": true,
+  "usedInExtractFields": true,
+  "usedInToolCall": true,
+  "usedInQueryExtension": true,
+  "toolChoice": false,
+  "functionCall": false,
+  "customCQPrompt": "",
+  "customExtractPrompt": "",
+  "defaultSystemChatPrompt": ""
+}
--- a/packages/service/core/ai/config/llm/SparkDesk-pro-128k.json
+++ b/packages/service/core/ai/config/llm/SparkDesk-pro-128k.json
@ -0,0 +1,20 @@
+{
+  "provider": "SparkDesk",
+  "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": ""
+}
--- a/packages/service/core/ai/config/llm/SparkDesk-v3.5.json
+++ b/packages/service/core/ai/config/llm/SparkDesk-v3.5.json
@ -1,15 +1,13 @@
 {
  "provider": "SparkDesk",
-  "model": "SparkDesk-v3.5",
-  "name": "SparkDesk-v3.5",
+  "model": "generalv3",
+  "name": "SparkDesk-Pro",
  "maxContext": 8000,
  "maxResponse": 8000,
-  "quoteMaxToken": 6000,
+  "quoteMaxToken": 8000,
  "maxTemperature": 1,
-  "charsPointsPrice": 0.3,
-  "censor": false,
  "vision": false,
-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "usedInExtractFields": true,
  "usedInToolCall": true,
--- a/packages/service/core/ai/config/llm/SparkDesk-v4.0.json
+++ b/packages/service/core/ai/config/llm/SparkDesk-v4.0.json
@ -1,14 +1,11 @@
 {
  "provider": "SparkDesk",
-  "model": "SparkDesk-v4.0",
-  "name": "SparkDesk-v4.0",
-
-  "censor": false,
-  "charsPointsPrice": 0,
+  "model": "4.0Ultra",
+  "name": "SparkDesk-v4.0 Ultra",

  "maxContext": 8000,
  "maxResponse": 8000,
-  "quoteMaxToken": 6000,
+  "quoteMaxToken": 8000,
  "maxTemperature": 1,

  "vision": false,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/abab6.5s-chat.json
+++ b/packages/service/core/ai/config/llm/abab6.5s-chat.json
@ -3,9 +3,6 @@
  "model": "abab6.5s-chat",
  "name": "MiniMax-abab6.5s",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 245000,
  "maxResponse": 10000,
  "quoteMaxToken": 240000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/claude-3-5-haiku-20241022.json
+++ b/packages/service/core/ai/config/llm/claude-3-5-haiku-20241022.json
@ -3,9 +3,6 @@
  "model": "claude-3-5-haiku-20241022",
  "name": "claude-3-5-haiku-20241022",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 200000,
  "maxResponse": 8000,
  "quoteMaxToken": 100000,
--- a/packages/service/core/ai/config/llm/claude-3-5-sonnet-20240620.json
+++ b/packages/service/core/ai/config/llm/claude-3-5-sonnet-20240620.json
@ -3,9 +3,6 @@
  "model": "claude-3-5-sonnet-20240620",
  "name": "Claude-3-5-sonnet-20240620",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 200000,
  "maxResponse": 8000,
  "quoteMaxToken": 100000,
--- a/packages/service/core/ai/config/llm/claude-3-5-sonnet-20241022.json
+++ b/packages/service/core/ai/config/llm/claude-3-5-sonnet-20241022.json
@ -3,9 +3,6 @@
  "model": "claude-3-5-sonnet-20241022",
  "name": "Claude-3-5-sonnet-20241022",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 200000,
  "maxResponse": 8000,
  "quoteMaxToken": 100000,
--- a/packages/service/core/ai/config/llm/claude-3-opus-20240229.json
+++ b/packages/service/core/ai/config/llm/claude-3-opus-20240229.json
@ -3,9 +3,6 @@
  "model": "claude-3-opus-20240229",
  "name": "claude-3-opus-20240229",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 200000,
  "maxResponse": 4096,
  "quoteMaxToken": 100000,
--- a/packages/service/core/ai/config/llm/deepseek-chat.json
+++ b/packages/service/core/ai/config/llm/deepseek-chat.json
@ -3,9 +3,6 @@
  "model": "deepseek-chat",
  "name": "Deepseek-chat",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 64000,
  "maxResponse": 4096,
  "quoteMaxToken": 60000,
--- a/packages/service/core/ai/config/llm/deepseek-reasoner.json
+++ b/packages/service/core/ai/config/llm/deepseek-reasoner.json
@ -3,9 +3,6 @@
  "model": "deepseek-reasoner",
  "name": "Deepseek-reasoner",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 64000,
  "maxResponse": 4096,
  "quoteMaxToken": 60000,
--- a/packages/service/core/ai/config/llm/gemini-1.5-flash.json
+++ b/packages/service/core/ai/config/llm/gemini-1.5-flash.json
@ -3,9 +3,6 @@
  "model": "gemini-1.5-flash",
  "name": "Gemini-1.5-flash",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 1000000,
  "maxResponse": 8000,
  "quoteMaxToken": 60000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/gemini-1.5-pro.json
+++ b/packages/service/core/ai/config/llm/gemini-1.5-pro.json
@ -3,9 +3,6 @@
  "model": "gemini-1.5-pro",
  "name": "Gemini-1.5-pro",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 2000000,
  "maxResponse": 8000,
  "quoteMaxToken": 60000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/gemini-2.0-flash-exp.json
+++ b/packages/service/core/ai/config/llm/gemini-2.0-flash-exp.json
@ -3,9 +3,6 @@
  "model": "gemini-2.0-flash-exp",
  "name": "Gemini-2.0-flash-exp",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 1000000,
  "maxResponse": 8000,
  "quoteMaxToken": 60000,
--- a/packages/service/core/ai/config/llm/gemini-2.0-flash-thinking-exp.json
+++ b/packages/service/core/ai/config/llm/gemini-2.0-flash-thinking-exp.json
@ -3,9 +3,6 @@
  "model": "gemini-2.0-flash-thinking-exp-01-21",
  "name": "Gemini-2.0-flash-thinking-exp",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 1000000,
  "maxResponse": 8000,
  "quoteMaxToken": 60000,
--- a/packages/service/core/ai/config/llm/gemini-exp-1206.json
+++ b/packages/service/core/ai/config/llm/gemini-exp-1206.json
@ -3,9 +3,6 @@
  "model": "gemini-exp-1206",
  "name": "gemini-exp-1206",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 128000,
  "maxResponse": 8000,
  "quoteMaxToken": 120000,
--- a/packages/service/core/ai/config/llm/glm-4-air.json
+++ b/packages/service/core/ai/config/llm/glm-4-air.json
@ -3,9 +3,6 @@
  "model": "glm-4-air",
  "name": "glm-4-air",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 128000,
  "maxResponse": 4000,
  "quoteMaxToken": 120000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/glm-4-flash.json
+++ b/packages/service/core/ai/config/llm/glm-4-flash.json
@ -3,9 +3,6 @@
  "model": "glm-4-flash",
  "name": "glm-4-flash",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 128000,
  "maxResponse": 4000,
  "quoteMaxToken": 120000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/glm-4-long.json
+++ b/packages/service/core/ai/config/llm/glm-4-long.json
@ -3,9 +3,6 @@
  "model": "glm-4-long",
  "name": "glm-4-long",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 1000000,
  "maxResponse": 4000,
  "quoteMaxToken": 900000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/glm-4-plus.json
+++ b/packages/service/core/ai/config/llm/glm-4-plus.json
@ -3,9 +3,6 @@
  "model": "glm-4-plus",
  "name": "GLM-4-plus",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 128000,
  "maxResponse": 4000,
  "quoteMaxToken": 120000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/glm-4v-flash.json
+++ b/packages/service/core/ai/config/llm/glm-4v-flash.json
@ -3,9 +3,6 @@
  "model": "glm-4v-flash",
  "name": "glm-4v-flash",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 8000,
  "maxResponse": 1000,
  "quoteMaxToken": 6000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/glm-4v-plus.json
+++ b/packages/service/core/ai/config/llm/glm-4v-plus.json
@ -3,9 +3,6 @@
  "model": "glm-4v-plus",
  "name": "GLM-4v-plus",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 8000,
  "maxResponse": 1000,
  "quoteMaxToken": 6000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/gpt-3.5-turbo.json
+++ b/packages/service/core/ai/config/llm/gpt-3.5-turbo.json
@ -1,10 +1,7 @@
 {
  "provider": "OpenAI",
  "model": "gpt-3.5-turbo",
-  "name": "gpt-3.5-turbo(abandon)",
-
-  "censor": true,
-  "charsPointsPrice": 1,
+  "name": "gpt-3.5-turbo",

  "maxContext": 16000,
  "maxResponse": 4000,
@ -16,15 +13,11 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": true,
-
-  "defaultConfig": {
-    "max_tokens": null
-  }
+  "usedInToolCall": true
 }
--- a/packages/service/core/ai/config/llm/gpt-4-turbo.json
+++ b/packages/service/core/ai/config/llm/gpt-4-turbo.json
@ -1,12 +1,9 @@
 {
  "provider": "OpenAI",
  "model": "gpt-4-turbo",
-  "name": "gpt-4-turbo(abandon)",
+  "name": "gpt-4-turbo",

-  "censor": true,
-  "charsPointsPrice": 15,
-
-  "maxContext": 125000,
+  "maxContext": 128000,
  "maxResponse": 4000,
  "quoteMaxToken": 60000,
  "maxTemperature": 1.2,
@ -16,15 +13,11 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": true,
-
-  "defaultConfig": {
-    "max_tokens": null
-  }
+  "usedInToolCall": true
 }
--- a/packages/service/core/ai/config/llm/gpt-4o-mini.json
+++ b/packages/service/core/ai/config/llm/gpt-4o-mini.json
@ -3,10 +3,7 @@
  "model": "gpt-4o-mini",
  "name": "GPT-4o-mini",

-  "censor": false,
-  "charsPointsPrice": 0,
-
-  "maxContext": 125000,
+  "maxContext": 128000,
  "maxResponse": 16000,
  "quoteMaxToken": 60000,
  "maxTemperature": 1.2,
--- a/packages/service/core/ai/config/llm/gpt-4o.json
+++ b/packages/service/core/ai/config/llm/gpt-4o.json
@ -3,10 +3,7 @@
  "model": "gpt-4o",
  "name": "GPT-4o",

-  "censor": false,
-  "charsPointsPrice": 0,
-
-  "maxContext": 125000,
+  "maxContext": 128000,
  "maxResponse": 4000,
  "quoteMaxToken": 60000,
  "maxTemperature": 1.2,
--- a/packages/service/core/ai/config/llm/groq-llama-3.1-8b-instant.json
+++ b/packages/service/core/ai/config/llm/groq-llama-3.1-8b-instant.json
@ -3,10 +3,7 @@
  "model": "llama-3.1-8b-instant",
  "name": "Groq-llama-3.1-8b-instant",

-  "censor": false,
-  "charsPointsPrice": 0,
-
-  "maxContext": 125000,
+  "maxContext": 128000,
  "maxResponse": 8000,
  "quoteMaxToken": 60000,
  "maxTemperature": 1.2,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/groq-llama-3.3-70b-versatile
+++ b/packages/service/core/ai/config/llm/groq-llama-3.3-70b-versatile
@ -3,10 +3,7 @@
  "model": "llama-3.3-70b-versatile",
  "name": "Groq-llama-3.3-70b-versatile",

-  "censor": false,
-  "charsPointsPrice": 0,
-
-  "maxContext": 125000,
+  "maxContext": 128000,
  "maxResponse": 8000,
  "quoteMaxToken": 60000,
  "maxTemperature": 1.2,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/hunyuan-large.json
+++ b/packages/service/core/ai/config/llm/hunyuan-large.json
@ -3,9 +3,6 @@
  "model": "hunyuan-large",
  "name": "hunyuan-large",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 28000,
  "maxResponse": 4000,
  "quoteMaxToken": 20000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/hunyuan-lite.json
+++ b/packages/service/core/ai/config/llm/hunyuan-lite.json
@ -3,9 +3,6 @@
  "model": "hunyuan-lite",
  "name": "hunyuan-lite",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 250000,
  "maxResponse": 6000,
  "quoteMaxToken": 100000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/hunyuan-pro-32k.json
+++ b/packages/service/core/ai/config/llm/hunyuan-pro-32k.json
@ -1,10 +1,7 @@
 {
  "provider": "Hunyuan",
-  "model": "hunyuan-pro-32k(测试)",
-  "name": "hunyuan-pro-32k(测试)",
-
-  "censor": false,
-  "charsPointsPrice": 0,
+  "model": "hunyuan-pro",
+  "name": "hunyuan-pro",

  "maxContext": 28000,
  "maxResponse": 4000,
--- a/packages/service/core/ai/config/llm/hunyuan-standard.json
+++ b/packages/service/core/ai/config/llm/hunyuan-standard.json
@ -3,10 +3,7 @@
  "model": "hunyuan-standard",
  "name": "hunyuan-standard",

-  "censor": false,
-  "charsPointsPrice": 0,
-
-  "maxContext": 30000,
+  "maxContext": 32000,
  "maxResponse": 2000,
  "quoteMaxToken": 20000,
  "maxTemperature": 1,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/hunyuan-turbo-vision.json
+++ b/packages/service/core/ai/config/llm/hunyuan-turbo-vision.json
@ -3,9 +3,6 @@
  "model": "hunyuan-turbo-vision",
  "name": "hunyuan-turbo-vision",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 6000,
  "maxResponse": 2000,
  "quoteMaxToken": 6000,
@ -16,13 +13,13 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
-  "usedInClassify": false,
+  "datasetProcess": true,
+  "usedInClassify": true,
  "customCQPrompt": "",
-  "usedInExtractFields": false,
-  "usedInQueryExtension": false,
+  "usedInExtractFields": true,
+  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": false,
+  "usedInToolCall": true,

  "defaultConfig": {},
  "fieldMap": {}
--- a/packages/service/core/ai/config/llm/hunyuan-turbo.json
+++ b/packages/service/core/ai/config/llm/hunyuan-turbo.json
@ -3,9 +3,6 @@
  "model": "hunyuan-turbo",
  "name": "hunyuan-turbo",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 28000,
  "maxResponse": 4000,
  "quoteMaxToken": 20000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/hunyuan-vision.json
+++ b/packages/service/core/ai/config/llm/hunyuan-vision.json
@ -3,9 +3,6 @@
  "model": "hunyuan-vision",
  "name": "hunyuan-vision",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 6000,
  "maxResponse": 2000,
  "quoteMaxToken": 4000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/internlm2-pro-chat.json
+++ b/packages/service/core/ai/config/llm/internlm2-pro-chat.json
@ -0,0 +1,26 @@
+{
+  "provider": "Intern",
+  "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": {}
+}
--- a/packages/service/core/ai/config/llm/internlm3-8b-instruct.json
+++ b/packages/service/core/ai/config/llm/internlm3-8b-instruct.json
@ -0,0 +1,26 @@
+{
+  "provider": "Intern",
+  "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": {}
+}
--- a/packages/service/core/ai/config/llm/ministral-3b-latest.json
+++ b/packages/service/core/ai/config/llm/ministral-3b-latest.json
@ -3,9 +3,6 @@
  "model": "ministral-3b-latest",
  "name": "Ministral-3b-latest",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 130000,
  "maxResponse": 8000,
  "quoteMaxToken": 60000,
--- a/packages/service/core/ai/config/llm/ministral-8b-latest.json
+++ b/packages/service/core/ai/config/llm/ministral-8b-latest.json
@ -3,9 +3,6 @@
  "model": "ministral-8b-latest",
  "name": "Ministral-8b-latest",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 130000,
  "maxResponse": 8000,
  "quoteMaxToken": 60000,
--- a/packages/service/core/ai/config/llm/mistral-large-latest.json
+++ b/packages/service/core/ai/config/llm/mistral-large-latest.json
@ -3,9 +3,6 @@
  "model": "mistral-large-latest",
  "name": "Mistral-large-latest",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 130000,
  "maxResponse": 8000,
  "quoteMaxToken": 60000,
--- a/packages/service/core/ai/config/llm/mistral-small-latest.json
+++ b/packages/service/core/ai/config/llm/mistral-small-latest.json
@ -3,12 +3,9 @@
  "model": "mistral-small-latest",
  "name": "Mistral-small-latest",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 32000,
  "maxResponse": 4000,
-  "quoteMaxToken": 30000,
+  "quoteMaxToken": 32000,
  "maxTemperature": 1.2,

  "vision": false,
--- a/packages/service/core/ai/config/llm/moonshot-v1-128k.json
+++ b/packages/service/core/ai/config/llm/moonshot-v1-128k.json
@ -1,10 +1,7 @@
 {
  "provider": "Moonshot",
  "model": "moonshot-v1-128k",
-  "name": "月之暗面-128k",
-
-  "censor": false,
-  "charsPointsPrice": 0,
+  "name": "moonshot-v1-128k",

  "maxContext": 128000,
  "maxResponse": 4000,
@ -22,7 +19,7 @@
  "usedInExtractFields": true,
  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": false,
+  "usedInToolCall": true,

  "defaultConfig": {},
  "fieldMap": {}
--- a/packages/service/core/ai/config/llm/moonshot-v1-32k.json
+++ b/packages/service/core/ai/config/llm/moonshot-v1-32k.json
@ -1,14 +1,11 @@
 {
  "provider": "Moonshot",
  "model": "moonshot-v1-32k",
-  "name": "月之暗面-32k",
-
-  "censor": false,
-  "charsPointsPrice": 0,
+  "name": "moonshot-v1-32k",

  "maxContext": 32000,
  "maxResponse": 4000,
-  "quoteMaxToken": 30000,
+  "quoteMaxToken": 32000,
  "maxTemperature": 1,

  "vision": false,
@ -22,7 +19,7 @@
  "usedInExtractFields": true,
  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": false,
+  "usedInToolCall": true,

  "defaultConfig": {},
  "fieldMap": {}
--- a/packages/service/core/ai/config/llm/moonshot-v1-8k.json
+++ b/packages/service/core/ai/config/llm/moonshot-v1-8k.json
@ -1,10 +1,7 @@
 {
  "provider": "Moonshot",
  "model": "moonshot-v1-8k",
-  "name": "月之暗面-8k",
-
-  "censor": false,
-  "charsPointsPrice": 0,
+  "name": "moonshot-v1-8k",

  "maxContext": 8000,
  "maxResponse": 4000,
@ -16,13 +13,13 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": false,
+  "usedInToolCall": true,

  "defaultConfig": {},
  "fieldMap": {}
--- a/packages/service/core/ai/config/llm/o1-mini.json
+++ b/packages/service/core/ai/config/llm/o1-mini.json
@ -3,10 +3,7 @@
  "model": "o1-mini",
  "name": "o1-mini",

-  "censor": false,
-  "charsPointsPrice": 0,
-
-  "maxContext": 125000,
+  "maxContext": 128000,
  "maxResponse": 4000,
  "quoteMaxToken": 120000,
  "maxTemperature": 1.2,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/o1-preview.json
+++ b/packages/service/core/ai/config/llm/o1-preview.json
@ -3,10 +3,7 @@
  "model": "o1-preview",
  "name": "o1-preview",

-  "censor": false,
-  "charsPointsPrice": 0,
-
-  "maxContext": 125000,
+  "maxContext": 128000,
  "maxResponse": 4000,
  "quoteMaxToken": 120000,
  "maxTemperature": 1.2,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/o1.json
+++ b/packages/service/core/ai/config/llm/o1.json
@ -3,9 +3,6 @@
  "model": "o1",
  "name": "o1",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 195000,
  "maxResponse": 8000,
  "quoteMaxToken": 120000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/qwen-coder-turbo.json
+++ b/packages/service/core/ai/config/llm/qwen-coder-turbo.json
@ -3,9 +3,6 @@
  "model": "qwen-coder-turbo",
  "name": "qwen-coder-turbo",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 128000,
  "maxResponse": 8000,
  "quoteMaxToken": 50000,
@ -16,13 +13,13 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
-  "usedInClassify": false,
+  "datasetProcess": true,
+  "usedInClassify": true,
  "customCQPrompt": "",
-  "usedInExtractFields": false,
-  "usedInQueryExtension": false,
+  "usedInExtractFields": true,
+  "usedInQueryExtension": true,
  "customExtractPrompt": "",
-  "usedInToolCall": false,
+  "usedInToolCall": true,

  "defaultConfig": {},
  "fieldMap": {}
--- a/packages/service/core/ai/config/llm/qwen-max.json
+++ b/packages/service/core/ai/config/llm/qwen-max.json
@ -3,9 +3,6 @@
  "model": "qwen-max",
  "name": "Qwen-max",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 8000,
  "maxResponse": 4000,
  "quoteMaxToken": 6000,
@ -16,7 +13,7 @@
  "functionCall": false,
  "defaultSystemChatPrompt": "",

-  "datasetProcess": false,
+  "datasetProcess": true,
  "usedInClassify": true,
  "customCQPrompt": "",
  "usedInExtractFields": true,
--- a/packages/service/core/ai/config/llm/qwen-plus.json
+++ b/packages/service/core/ai/config/llm/qwen-plus.json
@ -3,9 +3,6 @@
  "model": "qwen-plus",
  "name": "Qwen-plus",

-  "censor": false,
-  "charsPointsPrice": 0,
-
  "maxContext": 64000,
  "maxResponse": 8000,
  "quoteMaxToken": 60000,
--- a/Show More
+++ b/Show More