V4.8.20 feature (#3686)

* Aiproxy (#3649)

* model config

* feat: model config ui

* perf: rename variable

* feat: custom request url

* perf: model buffer

* perf: init model

* feat: json model config

* auto login

* fix: ts

* update packages

* package

* fix: dockerfile

* feat: usage filter & export & dashbord (#3538)

* feat: usage filter & export & dashbord

* adjust ui

* fix tmb scroll

* fix code & selecte all

* merge

* perf: usages list；perf: move components (#3654)

* perf: usages list

* team sub plan load

* perf: usage dashboard code

* perf: dashboard ui

* perf: move components

* add default model config (#3653)

* 4.8.20 test (#3656)

* provider

* perf: model config

* model perf (#3657)

* fix: model

* dataset quote

* perf: model config

* model tag

* doubao model config

* perf: config model

* feat: model test

* fix: POST 500 error on dingtalk bot (#3655)

* feat: default model (#3662)

* move model config

* feat: default model

* fix: false triggerd org selection (#3661)

* export usage csv i18n (#3660)

* export usage csv i18n

* fix build

* feat: markdown extension (#3663)

* feat: markdown extension

* media cros

* rerank test

* default price

* perf: default model

* fix: cannot custom provider

* fix: default model select

* update bg

* perf: default model selector

* fix: usage export

* i18n

* fix: rerank

* update init extension

* perf: ip limit check

* doubao model order

* web default modle

* perf: tts selector

* perf: tts error

* qrcode package

* reload buffer (#3665)

* reload buffer

* reload buffer

* tts selector

* fix: err tip (#3666)

* fix: err tip

* perf: training queue

* doc

* fix interactive edge (#3659)

* fix interactive edge

* fix

* comment

* add gemini model

* fix: chat model select

* perf: supplement assistant empty response (#3669)

* perf: supplement assistant empty response

* check array

* perf: max_token count;feat: support resoner output;fix: member scroll (#3681)

* perf: supplement assistant empty response

* check array

* perf: max_token count

* feat: support resoner output

* member scroll

* update provider order

* i18n

* fix: stream response (#3682)

* perf: supplement assistant empty response

* check array

* fix: stream response

* fix: model config cannot set to null

* fix: reasoning response (#3684)

* perf: supplement assistant empty response

* check array

* fix: reasoning response

* fix: reasoning response

* doc (#3685)

* perf: supplement assistant empty response

* check array

* doc

* lock

* animation

* update doc

* update compose

* doc

* doc

---------

Co-authored-by: heheer <heheer@sealos.io>
Co-authored-by: a.e. <49438478+I-Info@users.noreply.github.com>

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 +1,48 @@
+{
+  "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": null,
+      "vision": false,
+      "reasoning": 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/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 +1,252 @@
+{
+  "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": "o3-mini",
+      "name": "o3-mini",
+      "maxContext": 200000,
+      "maxResponse": 100000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": null,
+      "vision": false,
+      "toolChoice": true,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {
+        "stream": false
+      },
+      "fieldMap": {
+        "max_tokens": "max_completion_tokens"
+      },
+      "type": "llm"
+    },
+    {
+      "model": "o1-mini",
+      "name": "o1-mini",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": null,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {
+        "stream": false
+      },
+      "fieldMap": {
+        "max_tokens": "max_completion_tokens"
+      },
+      "type": "llm"
+    },
+    {
+      "model": "o1",
+      "name": "o1",
+      "maxContext": 195000,
+      "maxResponse": 8000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": null,
+      "vision": true,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {
+        "stream": false
+      },
+      "fieldMap": {
+        "max_tokens": "max_completion_tokens"
+      },
+      "type": "llm"
+    },
+    {
+      "model": "o1-preview",
+      "name": "o1-preview",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "quoteMaxToken": 120000,
+      "maxTemperature": null,
+      "vision": false,
+      "toolChoice": false,
+      "functionCall": false,
+      "defaultSystemChatPrompt": "",
+      "datasetProcess": true,
+      "usedInClassify": true,
+      "customCQPrompt": "",
+      "usedInExtractFields": true,
+      "usedInQueryExtension": true,
+      "customExtractPrompt": "",
+      "usedInToolCall": true,
+      "defaultConfig": {
+        "stream": false
+      },
+      "fieldMap": {
+        "max_tokens": "max_completion_tokens"
+      },
+      "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/functions/queryExtension.ts

@@ -2,10 +2,12 @@ import { replaceVariable } from '@fastgpt/global/common/string/tools';
 import { createChatCompletion } from '../config';
 import { ChatItemType } from '@fastgpt/global/core/chat/type';
 import { countGptMessagesTokens, countPromptTokens } from '../../../common/string/tiktoken/index';
-import { chatValue2RuntimePrompt } from '@fastgpt/global/core/chat/adapt';
+import { chats2GPTMessages } from '@fastgpt/global/core/chat/adapt';
 import { getLLMModel } from '../model';
 import { llmCompletionsBodyFormat } from '../utils';
 import { addLog } from '../../../common/system/log';
+import { filterGPTMessageByMaxContext } from '../../chat/utils';
+import json5 from 'json5';
 
 /* 
     query extension - 问题扩展
@@ -13,72 +15,73 @@ import { addLog } from '../../../common/system/log';
 */
 
 const title = global.feConfigs?.systemTitle || 'FastAI';
-const defaultPrompt = `作为一个向量检索助手，你的任务是结合历史记录，从不同角度，为“原问题”生成个不同版本的“检索词”，从而提高向量检索的语义丰富度，提高向量检索的精度。
+const defaultPrompt = `## 你的任务
+你作为一个向量检索助手，你的任务是结合历史记录，从不同角度，为“原问题”生成个不同版本的“检索词”，从而提高向量检索的语义丰富度，提高向量检索的精度。
 生成的问题要求指向对象清晰明确，并与“原问题语言相同”。
 
-参考 <Example></Example> 标中的示例来完成任务。
+## 参考示例
 
-<Example>
 历史记录: 
 """
+null
 """
 原问题: 介绍下剧情。
 检索词: ["介绍下故事的背景。","故事的主题是什么？","介绍下故事的主要人物。"]
 ----------------
 历史记录: 
 """
-Q: 对话背景。
-A: 当前对话是关于 Nginx 的介绍和使用等。
+user: 对话背景。
+assistant: 当前对话是关于 Nginx 的介绍和使用等。
 """
 原问题: 怎么下载
 检索词: ["Nginx 如何下载？","下载 Nginx 需要什么条件？","有哪些渠道可以下载 Nginx？"]
 ----------------
 历史记录: 
 """
-Q: 对话背景。
-A: 当前对话是关于 Nginx 的介绍和使用等。
-Q: 报错 "no connection"
-A: 报错"no connection"可能是因为……
+user: 对话背景。
+assistant: 当前对话是关于 Nginx 的介绍和使用等。
+user: 报错 "no connection"
+assistant: 报错"no connection"可能是因为……
 """
 原问题: 怎么解决
 检索词: ["Nginx报错"no connection"如何解决？","造成'no connection'报错的原因。","Nginx提示'no connection'，要怎么办？"]
 ----------------
 历史记录: 
 """
-Q: 护产假多少天?
-A: 护产假的天数根据员工所在的城市而定。请提供您所在的城市，以便我回答您的问题。
+user: How long is the maternity leave?
+assistant: The number of days of maternity leave depends on the city in which the employee is located. Please provide your city so that I can answer your questions.
 """
-原问题: 沈阳
-检索词: ["沈阳的护产假多少天？","沈阳的护产假政策。","沈阳的护产假标准。"]
+原问题: ShenYang
+检索词: ["How many days is maternity leave in Shenyang?","Shenyang's maternity leave policy.","The standard of maternity leave in Shenyang."]
 ----------------
 历史记录: 
 """
-Q: 作者是谁？
-A: ${title} 的作者是 labring。
+user: 作者是谁？
+assistant: ${title} 的作者是 labring。
 """
 原问题: Tell me about him
 检索词: ["Introduce labring, the author of ${title}." ," Background information on author labring." "," Why does labring do ${title}?"]
 ----------------
 历史记录:
 """
-Q: 对话背景。
-A: 关于 ${title} 的介绍和使用等问题。
+user: 对话背景。
+assistant: 关于 ${title} 的介绍和使用等问题。
 """
 原问题: 你好。
 检索词: ["你好"]
 ----------------
 历史记录:
 """
-Q: ${title} 如何收费？
-A: ${title} 收费可以参考……
+user: ${title} 如何收费？
+assistant: ${title} 收费可以参考……
 """
 原问题: 你知道 laf 么？
 检索词: ["laf 的官网地址是多少？","laf 的使用教程。","laf 有什么特点和优势。"]
 ----------------
 历史记录:
 """
-Q: ${title} 的优势
-A: 1. 开源
+user: ${title} 的优势
+assistant: 1. 开源
    2. 简便
    3. 扩展性强
 """
@@ -87,18 +90,20 @@ A: 1. 开源
 ----------------
 历史记录:
 """
-Q: 什么是 ${title}？
-A: ${title} 是一个 RAG 平台。
-Q: 什么是 Laf？
-A: Laf 是一个云函数开发平台。
+user: 什么是 ${title}？
+assistant: ${title} 是一个 RAG 平台。
+user: 什么是 Laf？
+assistant: Laf 是一个云函数开发平台。
 """
 原问题: 它们有什么关系？
 检索词: ["${title}和Laf有什么关系？","介绍下${title}","介绍下Laf"]
-</Example>
 
------
+## 输出要求
 
-下面是正式的任务：
+1. 输出格式为 JSON 数组，数组中每个元素为字符串。无需对输出进行任何解释。
+2. 输出语言与原问题相同。原问题为中文则输出中文；原问题为英文则输出英文。
+
+## 开始任务
 
 历史记录:
 """
@@ -125,26 +130,39 @@ export const queryExtension = async ({
   outputTokens: number;
 }> => {
   const systemFewShot = chatBg
-    ? `Q: 对话背景。
-A: ${chatBg}
+    ? `user: 对话背景。
+assistant: ${chatBg}
 `
     : '';
-  const historyFewShot = histories
-    .map((item) => {
-      const role = item.obj === 'Human' ? 'Q' : 'A';
-      return `${role}: ${chatValue2RuntimePrompt(item.value).text}`;
-    })
-    .join('\n');
-  const concatFewShot = `${systemFewShot}${historyFewShot}`.trim();
 
   const modelData = getLLMModel(model);
+  const filterHistories = await filterGPTMessageByMaxContext({
+    messages: chats2GPTMessages({ messages: histories, reserveId: false }),
+    maxContext: modelData.maxContext - 1000
+  });
+
+  const historyFewShot = filterHistories
+    .map((item) => {
+      const role = item.role;
+      const content = item.content;
+      if ((role === 'user' || role === 'assistant') && content) {
+        if (typeof content === 'string') {
+          return `${role}: ${content}`;
+        } else {
+          return `${role}: ${content.map((item) => (item.type === 'text' ? item.text : '')).join('\n')}`;
+        }
+      }
+    })
+    .filter(Boolean)
+    .join('\n');
+  const concatFewShot = `${systemFewShot}${historyFewShot}`.trim();
 
   const messages = [
     {
       role: 'user',
       content: replaceVariable(defaultPrompt, {
         query: `${query}`,
-        histories: concatFewShot
+        histories: concatFewShot || 'null'
       })
     }
   ] as any;
@@ -154,7 +172,7 @@ A: ${chatBg}
       {
         stream: false,
         model: modelData.model,
-        temperature: 0.01,
+        temperature: 0.1,
         messages
       },
       modelData
@@ -172,22 +190,41 @@ A: ${chatBg}
     };
   }
 
+  const start = answer.indexOf('[');
+  const end = answer.lastIndexOf(']');
+  if (start === -1 || end === -1) {
+    addLog.warn('Query extension failed, not a valid JSON', {
+      answer
+    });
+    return {
+      rawQuery: query,
+      extensionQueries: [],
+      model,
+      inputTokens: 0,
+      outputTokens: 0
+    };
+  }
+
   // Intercept the content of [] and retain []
-  answer = answer.match(/\[.*?\]/)?.[0] || '';
-  answer = answer.replace(/\\"/g, '"');
+  const jsonStr = answer
+    .substring(start, end + 1)
+    .replace(/(\\n|\\)/g, '')
+    .replace(/  /g, '');
 
   try {
-    const queries = JSON.parse(answer) as string[];
+    const queries = json5.parse(jsonStr) as string[];
 
     return {
       rawQuery: query,
-      extensionQueries: Array.isArray(queries) ? queries : [],
+      extensionQueries: (Array.isArray(queries) ? queries : []).slice(0, 5),
       model,
       inputTokens: await countGptMessagesTokens(messages),
       outputTokens: await countPromptTokens(answer)
     };
   } catch (error) {
-    addLog.error(`Query extension error`, error);
+    addLog.warn('Query extension failed, not a valid JSON', {
+      answer
+    });
     return {
       rawQuery: query,
       extensionQueries: [],

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

@@ -2,32 +2,23 @@ import { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
 import {
   ChatCompletionCreateParamsNonStreaming,
   ChatCompletionCreateParamsStreaming,
-  ChatCompletionMessageParam
+  StreamChatType
 } from '@fastgpt/global/core/ai/type';
-import { countGptMessagesTokens } from '../../common/string/tiktoken';
 import { getLLMModel } from './model';
 
-export const computedMaxToken = async ({
+/* 
+  Count response max token
+*/
+export const computedMaxToken = ({
   maxToken,
-  model,
-  filterMessages = []
+  model
 }: {
   maxToken?: number;
   model: LLMModelItemType;
-  filterMessages: ChatCompletionMessageParam[];
 }) => {
   if (maxToken === undefined) return;
 
   maxToken = Math.min(maxToken, model.maxResponse);
-  const tokensLimit = model.maxContext;
-
-  /* count response max token */
-  const promptsToken = await countGptMessagesTokens(filterMessages);
-  maxToken = promptsToken + maxToken > tokensLimit ? tokensLimit - promptsToken : maxToken;
-
-  if (maxToken <= 0) {
-    maxToken = 200;
-  }
   return maxToken;
 };
 
@@ -39,6 +30,7 @@ export const computedTemperature = ({
   model: LLMModelItemType;
   temperature: number;
 }) => {
+  if (typeof model.maxTemperature !== 'number') return undefined;
   temperature = +(model.maxTemperature * (temperature / 10)).toFixed(2);
   temperature = Math.max(temperature, 0.01);
 
@@ -87,3 +79,12 @@ 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;
+};