update doc (#3136)

* fix: null pointer

* perf: not input text

* update doc url

docSite/content/zh-cn/docs/development/upgrading/464.md

@@ -32,7 +32,7 @@ curl --location --request POST 'https://{{host}}/api/admin/initv464' \
 4. 优化 - 历史记录模块。弃用旧的历史记录模块，直接在对应地方填写数值即可。
 5. 调整 - 知识库搜索模块 topk 逻辑，采用 MaxToken 计算，兼容不同长度的文本块
 6. 调整鉴权顺序，提高 apikey 的优先级，避免cookie抢占 apikey 的鉴权。
-7. 链接读取支持多选择器。参考[Web 站点同步用法](/docs/guide/knowledge_base/websync/)
+7. 链接读取支持多选择器。参考[Web 站点同步用法](/docs/course/websync)
 8. 修复 - 分享链接图片上传鉴权问题
 9. 修复 - Mongo 连接池未释放问题。
 10. 修复 - Dataset Intro 无法更新

docSite/content/zh-cn/docs/development/upgrading/465.md

@@ -21,10 +21,10 @@ weight: 831
 
 ## V4.6.5 功能介绍
 
-1. 新增 - [问题优化模块](/docs/guide/workbench/workflow/coreferenceresolution/)
-2. 新增 - [文本编辑模块](/docs/guide/workbench/workflow/text_editor/)
-3. 新增 - [判断器模块](/docs/guide/workbench/workflow/tfswitch//)
-4. 新增 - [自定义反馈模块](/docs/guide/workbench/workflow/custom_feedback/)
+1. 新增 - [问题优化模块](/docs/workflow/modules/coreferenceresolution/)
+2. 新增 - [文本编辑模块](/docs/workflow/modules/text_editor/)
+3. 新增 - [判断器模块](/docs/workflow/modules/tfswitch/)
+4. 新增 - [自定义反馈模块](/docs/workflow/modules/custom_feedback/)
 5. 新增 - 【内容提取】模块支持选择模型，以及字段枚举
 6. 优化 - docx读取，兼容表格（表格转markdown）
 7. 优化 - 高级编排连接线交互

docSite/content/zh-cn/docs/development/upgrading/466.md

@@ -25,7 +25,7 @@ weight: 830
 
 1. 查看 [FastGPT 2024 RoadMap](https://github.com/labring/FastGPT?tab=readme-ov-file#-%E5%9C%A8%E7%BA%BF%E4%BD%BF%E7%94%A8)
 2. 新增 - Http 模块请求头支持 Json 编辑器。
-3. 新增 - [ReRank模型部署](/docs/development/custom-models/bge-rerank/)
+3. 新增 - [ReRank模型部署](/docs/development/custom-models/reranker/)
 4. 新增 - 搜索方式：分离向量语义检索，全文检索和重排，通过 RRF 进行排序合并。
 5. 优化 - 问题分类提示词，id引导。测试国产商用 api 模型（百度阿里智谱讯飞）使用 Prompt 模式均可分类。
 6. UI 优化，未来将逐步替换新的UI设计。

docSite/content/zh-cn/docs/development/upgrading/468.md

@@ -91,7 +91,7 @@ curl --location --request POST 'https://{{host}}/api/init/v468' \
 
 1. 新增 - 知识库搜索合并模块。
 2. 新增 - 新的 Http 模块，支持更加灵活的参数传入。同时支持了输入输出自动数据类型转化，例如：接口输出的 JSON 类型会自动转成字符串类型，直接给其他模块使用。此外，还补充了一些例子，可在文档中查看。
-3. 优化 - 内容补全。将内容补全内置到【知识库搜索】中，并实现了一次内容补全，即可完成“指代消除”和“问题扩展”。FastGPT知识库搜索详细流程可查看：[知识库搜索介绍](/docs/guide/workbench/workflow/dataset_search/)
+3. 优化 - 内容补全。将内容补全内置到【知识库搜索】中，并实现了一次内容补全，即可完成“指代消除”和“问题扩展”。FastGPT知识库搜索详细流程可查看：[知识库搜索介绍](/docs/course/data_search/)
 4. 优化 - LLM 模型配置，不再区分对话、分类、提取模型。同时支持模型的默认参数，避免不同模型参数冲突，可通过`defaultConfig`传入默认的配置。
 5. 优化 - 流响应，参考了`ChatNextWeb`的流，更加丝滑。此外，之前提到的乱码、中断，刷新后又正常了，可能会修复）
 6. 修复 - 语音输入文件无法上传。

docSite/content/zh-cn/docs/development/upgrading/4813.md

@@ -13,8 +13,8 @@ weight: 811
 
 ### 2. 修改镜像
 
-- 更新 FastGPT 镜像 tag: v4.8.13-beta
-- 更新 FastGPT 商业版镜像 tag: v4.8.13-beta （fastgpt-pro镜像）
+- 更新 FastGPT 镜像 tag: v4.8.13-alpha
+- 更新 FastGPT 管理端镜像 tag: v4.8.13-alpha （fastgpt-pro镜像）
 - Sandbox 镜像，可以不更新
 
 ### 3. 调整文件上传编排
@@ -39,7 +39,6 @@ weight: 811
 14. 优化 - Markdown 组件自动空格，避免分割 url 中的中文。  
 15. 优化 - 工作流上下文拆分，性能优化。 
 16. 优化 - 语音播报，不支持 mediaSource 的浏览器可等待完全生成语音后输出。 
-17. 优化 - 对话引导 csv 读取，自动识别编码。
-18. 修复 - Dockerfile pnpm install 支持代理。 
-19. 修复 - BI 图表生成无法写入文件。同时优化其解析，支持数字类型数组。
-20. 修复 - 分享链接首次加载时，标题显示不正确。 
+17. 修复 - Dockerfile pnpm install 支持代理。 
+18. 修复 - BI 图表生成无法写入文件。同时优化其解析，支持数字类型数组。
+19. 修复 - 分享链接首次加载时，标题显示不正确。 

docSite/content/zh-cn/docs/guide/course/ai_settings.md

@@ -66,7 +66,7 @@ Tips: 可以通过点击上下文按键查看完整的上下文组成，便于
 
 FastGPT 知识库采用 QA 对(不一定都是问答格式，仅代表两个变量)的格式存储，在转义成字符串时候会根据**引用模板**来进行格式化。知识库包含多个可用变量： q, a, sourceId（数据的ID）, index(第n个数据), source(数据的集合名、文件名)，score(距离得分，0-1) 可以通过 {{q}} {{a}} {{sourceId}} {{index}} {{source}} {{score}} 按需引入。下面一个模板例子：
 
-可以通过 [知识库结构讲解](/docs/guide/knowledge_base/dataset_engine/) 了解详细的知识库的结构。
+可以通过 [知识库结构讲解](/docs/course/dataset_engine/) 了解详细的知识库的结构。
 
 #### 引用模板
 

docSite/content/zh-cn/docs/guide/workbench/workflow/ai_chat.md

@@ -30,5 +30,5 @@ weight: 232
 
 
 {{% alert icon="🍅" context="success" %}}
-具体配置参数介绍可以参考: [AI参数配置说明](/docs/guide/course/ai_settings/)
+具体配置参数介绍可以参考: [AI参数配置说明](/docs/course/ai_settings)
 {{% /alert %}}

docSite/content/zh-cn/docs/guide/workbench/workflow/coreferenceResolution.md

@@ -36,4 +36,4 @@ weight: 264
 
 ## 示例
 
-- [接入谷歌搜索](/docs/use-cases/app-cases/google_search/)
+- [接入谷歌搜索](/docs/workflow/examples/google_search/)

docSite/content/zh-cn/docs/guide/workbench/workflow/form_input.md

@@ -5,28 +5,4 @@ icon: "form_input"
 draft: false
 toc: true
 weight: 244
----
-
-## 特点 
-
-- 用户交互
-- 可重复添加
-- 触发执行
-
-![](/imgs/form_input1.png)
-
-## 功能 
-
-「表单输入」节点属于用户交互节点，当触发这个节点时，对话会进入“交互”状态，会记录工作流的状态，等用户完成交互后，继续向下执行工作流
-
-![](/imgs/form_input2.png)
-
-比如上图中的例子，当触发表单输入节点时，对话框隐藏，对话进入“交互状态”
-
-![](/imgs/form_input3.png)
-
-当用户填完必填的信息并点击提交后，节点能够收集用户填写的表单信息，传递到后续的节点中使用
-
-## 作用
-
-能够精准收集需要的用户信息，再根据用户信息进行后续操作
+---

docSite/content/zh-cn/docs/guide/workbench/workflow/http.md

@@ -250,6 +250,6 @@ export default async function (ctx: FunctionContext) {
 
 ## 相关示例
 
-- [谷歌搜索](/docs/use-cases/app-cases/google_search/)
-- [发送飞书webhook](/docs/use-cases/app-cases/feishu_webhook/)
-- [实验室预约（操作数据库）](/docs/use-cases/app-cases/lab_appointment/)
+- [谷歌搜索](/docs/workflow/examples/google_search/)
+- [发送飞书webhook](/docs/workflow/examples/feishu_webhook/)
+- [实验室预约（操作数据库）](/docs/workflow/examples/lab_appointment/)

docSite/content/zh-cn/docs/guide/workbench/workflow/text_editor.md

@@ -29,4 +29,4 @@ weight: 246
 
 ## 示例
 
-- [接入谷歌搜索](/docs/use-cases/app-cases/google_search/)
+- [接入谷歌搜索](/docs/workflow/examples/google_search/)

docSite/content/zh-cn/docs/guide/workbench/workflow/tool.md

@@ -7,21 +7,20 @@ toc: true
 weight: 236
 ---
 
-
 ![](/imgs/flow-tool1.png)
 
-### **什么是工具**
+## 什么是工具
 
 工具可以是一个系统模块，例如：AI对话、知识库搜索、HTTP模块等。也可以是一个插件。
 
 工具调用可以让 LLM 更动态的决策流程，而不都是固定的流程。（当然，缺点就是费tokens）
 
-### **工具的组成**
+## 工具的组成
 
 1. 工具介绍。通常是模块的介绍或插件的介绍，这个介绍会告诉LLM，这个工具的作用是什么。
 2. 工具参数。对于系统模块来说，工具参数已经是固定的，无需额外配置。对于插件来说，工具参数是一个可配置项。
 
-### **工具是如何运行的**
+## 工具是如何运行的
 
 要了解工具如何运行的，首先需要知道它的运行条件。
 
@@ -30,57 +29,43 @@ weight: 236
 
 结合工具的介绍、参数介绍和参数是否必须，LLM会决定是否调用这个工具。有以下几种情况：
 
+
 1. 无参数的工具：直接根据工具介绍，决定是否需要执行。例如：获取当前时间。
 2. 有参数的工具：
    1. 无必须的参数：尽管上下文中，没有适合的参数，也可以调用该工具。但有时候，LLM会自己伪造一个参数。
    2. 有必须的参数：如果没有适合的参数，LLM可能不会调用该工具。可以通过提示词，引导用户提供参数。
 
-#### **工具调用逻辑**
-
 在支持`函数调用`的模型中，可以一次性调用多个工具，调用逻辑如下：
 
 ![](/imgs/flow-tool2.png)
 
-### **怎么用**
+## 怎么用
 
-<div style="display: flex; gap: 10px;">
-    <img src="/imgs/flow-tool3.png" alt="工具调用模块示例 3" width="40%" />
-    <img src="/imgs/flow-tool4.png" alt="工具调用模块示例 4" width="60%" />
-</div>
+| 有工具调用模块 | 无工具调用模块 |
+| --- | --- |
+| ![](/imgs/flow-tool3.png) | ![](/imgs/flow-tool4.png) |
 
-<!-- ![](/imgs/flow-tool3.png)!![](/imgs/flow-tool4.png) -->
+高级编排中，托动工具调用的连接点，可用的工具头部会出现一个菱形，可以将它与工具调用模块底部的菱形相连接。
 
-高级编排中，拖动工具调用的连接点，可用的工具头部会出现一个菱形，可以将它与工具调用模块底部的菱形相连接。
-
-被连接的工具，会自动分离工具输入与普通的输入，并且可以编辑`介绍`，可以通过调整介绍，使得该工具调用时机更加精确。
+被连接的工具，会自动分离工具输入与普通的输入，并且可以编辑`描述`，可以通过调整介绍，使得该工具调用时机更加精确。对于一些内置的节点，务必修改`描述`才能让模型正常调用。
 
 关于工具调用，如何调试仍然是一个玄学，所以建议，不要一次性增加太多工具，选择少量工具调优后再进一步尝试。
 
-#### 用途
+## 组合节点
 
-默认清空下，工具调用节点，在决定调用工具后，会将工具运行的结果，返回给AI，让 AI 对工具运行的结果进行总结输出。有时候，如果你不需要 AI 进行进一步的总结输出，可以使用该节点，将其接入对于工具流程的末尾。
+### 工具调用终止
 
-如下图，在执行知识库搜索后，发送给了 HTTP 请求，搜索将不会返回搜索的结果给工具调用进行 AI 总结。
+工具调用默认会把子流程运行的结果作为`工具结果`，返回给模型进行回答。有时候，你可能不希望模型做回答，你可以给对应子流程的末尾增加上一个`工具调用终止`节点，这样，子流程的结果就不会被返回给模型。
 
-![](/imgs/flow-tool5.png)
-
-### 附加节点
-
-当您使用了工具调用节点，同时就会出现工具调用终止节点和自定义变量节点，能够进一步提升工具调用的使用体验。
-
-#### 工具调用终止
-
-工具调用终止可用于结束本次调用，即可以接在某个工具后面，当工作流执行到这个节点时，便会强制结束本次工具调用，不再调用其他工具，也不会再调用 AI 针对工具调用结果回答问题。
-
-![](/imgs/flow-tool6.png)
+![alt text](/imgs/image-3.png)
 
 ### 自定义工具变量
 
-自定义变量可以扩展工具的变量输入，即对于一些未被视作工具参数或无法工具调用的节点，可以自定义工具变量，填上对应的参数描述，那么工具调用便会相对应的调用这个节点，进而调用其之后的工作流。
+工具调用的子流程运行，有时候会依赖`AI`生成的一些变量，为了简化交互流程，我们给系统内置的节点都指定了`工具变量`。然而，有些时候，你需要的变量不仅是目标流程的`首个节点`的变量，而是需要更复杂的变量，此时你可以使用`自定义工具变量`。它允许你完全自定义该`工具流程`的变量。
 
-![](/imgs/flow-tool7.png)
+![alt text](/imgs/image-4.png)
 
-### **相关示例**
+## 相关示例
 
-- [谷歌搜索](https://doc.fastgpt.in/docs/use-cases/app-cases/google_search/)
-- [发送飞书webhook](https://doc.fastgpt.in/docs/use-cases/app-cases/feishu_webhook/)
+- [谷歌搜索](/docs/workflow/examples/google_search/)
+- [发送飞书webhook](/docs/workflow/examples/feishu_webhook/)

docSite/content/zh-cn/docs/use-cases/external-integration/onwechat.md

@@ -11,7 +11,7 @@ weight: 509
 
 [chatgpt-on-wechat GitHub 地址](https://github.com/zhayujie/chatgpt-on-wechat)
 
-由于 FastGPT 的 API 接口和 OpenAI 的规范一致，可以无需变更原来的应用即可使用 FastGPT 上编排好的应用。API 使用可参考 [这篇文章](/docs/use-cases/external-integration/openapi/)。编排示例，可参考 [高级编排介绍](/docs/workflow/intro)
+由于 FastGPT 的 API 接口和 OpenAI 的规范一致，可以无需变更原来的应用即可使用 FastGPT 上编排好的应用。API 使用可参考 [这篇文章](/docs/course/openapi/)。编排示例，可参考 [高级编排介绍](/docs/workflow/intro)
 
 ## 1. 获取 OpenAPI 密钥
 

packages/global/common/file/constants.ts

@@ -16,7 +16,7 @@ export const bucketNameMap = {
   }
 };
 
-export const ReadFileBaseUrl = `${process.env.FE_DOMAIN || ''}${process.env.NEXT_PUBLIC_BASE_URL || ''}/api/common/file/read`;
+export const ReadFileBaseUrl = `${process.env.FE_DOMAIN || ''}${process.env.NEXT_PUBLIC_BASE_URL}/api/common/file/read`;
 
 export const documentFileType = '.txt, .docx, .csv, .xlsx, .pdf, .md, .html, .pptx';
 export const imageFileType =

packages/global/core/chat/utils.ts

@@ -78,15 +78,11 @@ export const getHistoryPreview = (
 };
 
 export const filterPublicNodeResponseData = ({
-  flowResponses = [],
-  responseDetail = false
+  flowResponses = []
 }: {
   flowResponses?: ChatHistoryItemResType[];
-  responseDetail?: boolean;
 }) => {
-  const filedList = responseDetail
-    ? ['quoteList', 'moduleType', 'pluginOutput', 'runningTime']
-    : ['moduleType', 'pluginOutput', 'runningTime'];
+  const filedList = ['quoteList', 'moduleType', 'pluginOutput', 'runningTime'];
   const filterModuleTypeList: any[] = [
     FlowNodeTypeEnum.pluginModule,
     FlowNodeTypeEnum.datasetSearchNode,

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

@@ -95,10 +95,10 @@ export const DatasetSearchModule: FlowNodeTemplateType = {
     },
     {
       key: NodeInputKeyEnum.collectionFilterMatch,
-      renderTypeList: [FlowNodeInputTypeEnum.textarea, FlowNodeInputTypeEnum.reference],
+      renderTypeList: [FlowNodeInputTypeEnum.JSONEditor, FlowNodeInputTypeEnum.reference],
       label: i18nT('workflow:collection_metadata_filter'),
 
-      valueType: WorkflowIOValueTypeEnum.string,
+      valueType: WorkflowIOValueTypeEnum.object,
       isPro: true,
       description: i18nT('workflow:filter_description')
     }

packages/service/core/ai/config.ts

@@ -1,11 +1,5 @@
 import type { UserModelSchema } from '@fastgpt/global/support/user/type';
 import OpenAI from '@fastgpt/global/core/ai';
-import {
-  ChatCompletionCreateParamsNonStreaming,
-  ChatCompletionCreateParamsStreaming
-} from '@fastgpt/global/core/ai/type';
-import { getErrText } from '@fastgpt/global/common/error/utils';
-import { addLog } from '../../common/system/log';
 
 export const openaiBaseUrl = process.env.OPENAI_BASE_URL || 'https://api.openai.com/v1';
 
@@ -40,55 +34,3 @@ export const getAxiosConfig = (props?: { userKey?: UserModelSchema['openaiAccoun
     authorization: `Bearer ${apiKey}`
   };
 };
-
-type CompletionsBodyType =
-  | ChatCompletionCreateParamsNonStreaming
-  | ChatCompletionCreateParamsStreaming;
-type InferResponseType<T extends CompletionsBodyType> =
-  T extends ChatCompletionCreateParamsStreaming
-    ? OpenAI.Chat.Completions.ChatCompletionChunk
-    : OpenAI.Chat.Completions.ChatCompletion;
-
-export const createChatCompletion = async <T extends CompletionsBodyType>({
-  body,
-  userKey,
-  timeout,
-  options
-}: {
-  body: T;
-  userKey?: UserModelSchema['openaiAccount'];
-  timeout?: number;
-  options?: OpenAI.RequestOptions;
-}): Promise<{
-  response: InferResponseType<T>;
-  isStreamResponse: boolean;
-}> => {
-  try {
-    const formatTimeout = timeout ? timeout : body.stream ? 60000 : 600000;
-    const ai = getAIApi({
-      userKey,
-      timeout: formatTimeout
-    });
-    const response = await ai.chat.completions.create(body, options);
-
-    const isStreamResponse =
-      typeof response === 'object' &&
-      response !== null &&
-      ('iterator' in response || 'controller' in response);
-
-    return {
-      response: response as InferResponseType<T>,
-      isStreamResponse
-    };
-  } catch (error) {
-    addLog.error(`LLM response error`, error);
-    addLog.warn(`LLM response error`, {
-      baseUrl: userKey?.baseUrl,
-      requestBody: body
-    });
-    if (userKey?.baseUrl) {
-      return Promise.reject(`您的 OpenAI key 出错了: ${getErrText(error)}`);
-    }
-    return Promise.reject(error);
-  }
-};

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

@@ -55,7 +55,7 @@ export async function getVectorsByText({ model, input, type }: GetVectorProps) {
 
     return result;
   } catch (error) {
-    addLog.error(`Embedding Error`, error);
+    console.log(`Embedding Error`, error);
 
     return Promise.reject(error);
   }

packages/service/core/ai/functions/createQuestionGuide.ts

@@ -1,5 +1,5 @@
 import type { ChatCompletionMessageParam } from '@fastgpt/global/core/ai/type.d';
-import { createChatCompletion } from '../config';
+import { getAIApi } from '../config';
 import { countGptMessagesTokens } from '../../../common/string/tiktoken/index';
 import { loadRequestMessages } from '../../chat/utils';
 import { llmCompletionsBodyFormat } from '../utils';
@@ -29,8 +29,11 @@ export async function createQuestionGuide({
     }
   ];
 
-  const { response: data } = await createChatCompletion({
-    body: llmCompletionsBodyFormat(
+  const ai = getAIApi({
+    timeout: 480000
+  });
+  const data = await ai.chat.completions.create(
+    llmCompletionsBodyFormat(
       {
         model,
         temperature: 0.1,
@@ -43,7 +46,7 @@ export async function createQuestionGuide({
       },
       model
     )
-  });
+  );
 
   const answer = data.choices?.[0]?.message?.content || '';
 

packages/service/core/ai/functions/queryExtension.ts

@@ -1,7 +1,8 @@
 import { replaceVariable } from '@fastgpt/global/common/string/tools';
-import { createChatCompletion } from '../config';
+import { getAIApi } from '../config';
 import { ChatItemType } from '@fastgpt/global/core/chat/type';
 import { countGptMessagesTokens } from '../../../common/string/tiktoken/index';
+import { ChatCompletion, ChatCompletionMessageParam } from '@fastgpt/global/core/ai/type';
 import { chatValue2RuntimePrompt } from '@fastgpt/global/core/chat/adapt';
 import { getLLMModel } from '../model';
 import { llmCompletionsBodyFormat } from '../utils';
@@ -137,6 +138,10 @@ A: ${chatBg}
 
   const modelData = getLLMModel(model);
 
+  const ai = getAIApi({
+    timeout: 480000
+  });
+
   const messages = [
     {
       role: 'user',
@@ -145,19 +150,20 @@ A: ${chatBg}
         histories: concatFewShot
       })
     }
-  ] as any;
+  ] as ChatCompletionMessageParam[];
 
-  const { response: result } = await createChatCompletion({
-    body: llmCompletionsBodyFormat(
+  const result = (await ai.chat.completions.create(
+    llmCompletionsBodyFormat(
       {
         stream: false,
         model: modelData.model,
         temperature: 0.01,
+        // @ts-ignore
         messages
       },
       modelData
     )
-  });
+  )) as ChatCompletion;
 
   let answer = result.choices?.[0]?.message?.content || '';
   if (!answer) {

packages/service/core/ai/utils.ts

@@ -48,17 +48,14 @@ export const computedTemperature = ({
 type CompletionsBodyType =
   | ChatCompletionCreateParamsNonStreaming
   | ChatCompletionCreateParamsStreaming;
-type InferCompletionsBody<T> = T extends { stream: true }
-  ? ChatCompletionCreateParamsStreaming
-  : ChatCompletionCreateParamsNonStreaming;
 
 export const llmCompletionsBodyFormat = <T extends CompletionsBodyType>(
   body: T,
   model: string | LLMModelItemType
-): InferCompletionsBody<T> => {
+) => {
   const modelData = typeof model === 'string' ? getLLMModel(model) : model;
   if (!modelData) {
-    return body as InferCompletionsBody<T>;
+    return body;
   }
 
   const requestBody: T = {
@@ -84,5 +81,5 @@ export const llmCompletionsBodyFormat = <T extends CompletionsBodyType>(
 
   // console.log(requestBody);
 
-  return requestBody as InferCompletionsBody<T>;
+  return requestBody;
 };

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

@@ -118,10 +118,7 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
     let createTimeCollectionIdList: string[] | undefined = undefined;
 
     try {
-      const jsonMatch =
-        typeof collectionFilterMatch === 'object'
-          ? collectionFilterMatch
-          : json5.parse(collectionFilterMatch);
+      const jsonMatch = json5.parse(collectionFilterMatch);
 
       // Tag
       let andTags = jsonMatch?.tags?.$and as (string | null)[] | undefined;
@@ -350,7 +347,7 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
                 teamId: new Types.ObjectId(teamId),
                 datasetId: new Types.ObjectId(id),
                 $text: { $search: jiebaSplit({ text: query }) },
-                ...(filterCollectionIdList
+                ...(filterCollectionIdList && filterCollectionIdList.length > 0
                   ? {
                       collectionId: {
                         $in: filterCollectionIdList.map((id) => new Types.ObjectId(id))

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

@@ -2,7 +2,7 @@ import { chats2GPTMessages } from '@fastgpt/global/core/chat/adapt';
 import { countMessagesTokens } from '../../../../common/string/tiktoken/index';
 import type { ChatItemType } from '@fastgpt/global/core/chat/type.d';
 import { ChatItemValueTypeEnum, ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
-import { createChatCompletion } from '../../../ai/config';
+import { getAIApi } from '../../../ai/config';
 import type { ClassifyQuestionAgentItemType } from '@fastgpt/global/core/workflow/template/system/classifyQuestion/type';
 import { NodeInputKeyEnum, NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
 import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
@@ -120,8 +120,13 @@ const completions = async ({
     useVision: false
   });
 
-  const { response: data } = await createChatCompletion({
-    body: llmCompletionsBodyFormat(
+  const ai = getAIApi({
+    userKey: user.openaiAccount,
+    timeout: 480000
+  });
+
+  const data = await ai.chat.completions.create(
+    llmCompletionsBodyFormat(
       {
         model: cqModel.model,
         temperature: 0.01,
@@ -129,9 +134,8 @@ const completions = async ({
         stream: false
       },
       cqModel
-    ),
-    userKey: user.openaiAccount
-  });
+    )
+  );
   const answer = data.choices?.[0].message?.content || '';
 
   // console.log(JSON.stringify(chats2GPTMessages({ messages, reserveId: false }), null, 2));

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

@@ -6,7 +6,7 @@ import {
   countGptMessagesTokens
 } from '../../../../common/string/tiktoken/index';
 import { ChatItemValueTypeEnum, ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
-import { createChatCompletion } from '../../../ai/config';
+import { getAIApi } from '../../../ai/config';
 import type { ContextExtractAgentItemType } from '@fastgpt/global/core/workflow/template/system/contextExtract/type';
 import { NodeInputKeyEnum, NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
 import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
@@ -222,8 +222,13 @@ const toolChoice = async (props: ActionProps) => {
     }
   ];
 
-  const { response } = await createChatCompletion({
-    body: llmCompletionsBodyFormat(
+  const ai = getAIApi({
+    userKey: user.openaiAccount,
+    timeout: 480000
+  });
+
+  const response = await ai.chat.completions.create(
+    llmCompletionsBodyFormat(
       {
         model: extractModel.model,
         temperature: 0.01,
@@ -232,9 +237,8 @@ const toolChoice = async (props: ActionProps) => {
         tool_choice: { type: 'function', function: { name: agentFunName } }
       },
       extractModel
-    ),
-    userKey: user.openaiAccount
-  });
+    )
+  );
 
   const arg: Record<string, any> = (() => {
     try {
@@ -268,8 +272,13 @@ const functionCall = async (props: ActionProps) => {
   const { agentFunction, filterMessages } = await getFunctionCallSchema(props);
   const functions: ChatCompletionCreateParams.Function[] = [agentFunction];
 
-  const { response } = await createChatCompletion({
-    body: llmCompletionsBodyFormat(
+  const ai = getAIApi({
+    userKey: user.openaiAccount,
+    timeout: 480000
+  });
+
+  const response = await ai.chat.completions.create(
+    llmCompletionsBodyFormat(
       {
         model: extractModel.model,
         temperature: 0.01,
@@ -280,9 +289,8 @@ const functionCall = async (props: ActionProps) => {
         functions
       },
       extractModel
-    ),
-    userKey: user.openaiAccount
-  });
+    )
+  );
 
   try {
     const arg = JSON.parse(response?.choices?.[0]?.message?.function_call?.arguments || '');
@@ -350,8 +358,12 @@ Human: ${content}`
     useVision: false
   });
 
-  const { response: data } = await createChatCompletion({
-    body: llmCompletionsBodyFormat(
+  const ai = getAIApi({
+    userKey: user.openaiAccount,
+    timeout: 480000
+  });
+  const data = await ai.chat.completions.create(
+    llmCompletionsBodyFormat(
       {
         model: extractModel.model,
         temperature: 0.01,
@@ -359,9 +371,8 @@ Human: ${content}`
         stream: false
       },
       extractModel
-    ),
-    userKey: user.openaiAccount
-  });
+    )
+  );
   const answer = data.choices?.[0].message?.content || '';
 
   // parse response

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

@@ -1,4 +1,5 @@
-import { createChatCompletion } from '../../../../ai/config';
+import { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
+import { getAIApi } from '../../../../ai/config';
 import { filterGPTMessageByMaxTokens, loadRequestMessages } from '../../../../chat/utils';
 import {
   ChatCompletion,
@@ -21,12 +22,12 @@ import { DispatchFlowResponse, WorkflowResponseType } from '../../type';
 import { countGptMessagesTokens } from '../../../../../common/string/tiktoken/index';
 import { getNanoid, sliceStrStartEnd } from '@fastgpt/global/common/string/tools';
 import { AIChatItemType } from '@fastgpt/global/core/chat/type';
-import { GPTMessages2Chats } from '@fastgpt/global/core/chat/adapt';
+import { chats2GPTMessages, GPTMessages2Chats } from '@fastgpt/global/core/chat/adapt';
 import { formatToolResponse, initToolCallEdges, initToolNodes } from './utils';
 import { computedMaxToken, llmCompletionsBodyFormat } from '../../../../ai/utils';
 import { toolValueTypeList } from '@fastgpt/global/core/workflow/constants';
 import { WorkflowInteractiveResponseType } from '@fastgpt/global/core/workflow/template/system/interactive/type';
-import { ChatItemValueTypeEnum } from '@fastgpt/global/core/chat/constants';
+import { ChatItemValueTypeEnum, ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
 import { i18nT } from '../../../../../../web/i18n/utils';
 
 type FunctionRunResponseType = {
@@ -44,7 +45,7 @@ export const runToolWithFunctionCall = async (
     requestOrigin,
     runtimeNodes,
     runtimeEdges,
-    user,
+    node,
     stream,
     workflowStreamResponse,
     params: { temperature = 0, maxToken = 4000, aiChatVision }
@@ -216,18 +217,17 @@ export const runToolWithFunctionCall = async (
 
   // console.log(JSON.stringify(requestMessages, null, 2));
   /* Run llm */
-  const { response: aiResponse, isStreamResponse } = await createChatCompletion({
-    body: requestBody,
-    userKey: user.openaiAccount,
-    options: {
-      headers: {
-        Accept: 'application/json, text/plain, */*'
-      }
+  const ai = getAIApi({
+    timeout: 480000
+  });
+  const aiResponse = await ai.chat.completions.create(requestBody, {
+    headers: {
+      Accept: 'application/json, text/plain, */*'
     }
   });
 
   const { answer, functionCalls } = await (async () => {
-    if (res && isStreamResponse) {
+    if (res && stream) {
       return streamResponse({
         res,
         toolNodes,

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

@@ -29,7 +29,6 @@ import { getFileContentFromLinks, getHistoryFileLinks } from '../../tools/readFi
 import { parseUrlToFileType } from '@fastgpt/global/common/file/tools';
 import { Prompt_DocumentQuote } from '@fastgpt/global/core/ai/prompt/AIChat';
 import { FlowNodeTypeEnum } from '@fastgpt/global/core/workflow/node/constant';
-import { postTextCensor } from '../../../../../common/api/requestPlusApi';
 
 type Response = DispatchNodeResultType<{
   [NodeOutputKeyEnum.answerText]: string;
@@ -46,7 +45,6 @@ export const dispatchRunTools = async (props: DispatchToolModuleProps): Promise<
     requestOrigin,
     chatConfig,
     runningAppInfo: { teamId },
-    user,
     params: {
       model,
       systemPrompt,
@@ -152,15 +150,6 @@ export const dispatchRunTools = async (props: DispatchToolModuleProps): Promise<
     return value;
   })();
 
-  // censor model and system key
-  if (toolModel.censor && !user.openaiAccount?.key) {
-    await postTextCensor({
-      text: `${systemPrompt}
-          ${userChatInput}
-        `
-    });
-  }
-
   const {
     toolWorkflowInteractiveResponse,
     dispatchFlowResponse, // tool flow response
@@ -228,14 +217,13 @@ export const dispatchRunTools = async (props: DispatchToolModuleProps): Promise<
     tokens: toolNodeTokens,
     modelType: ModelTypeEnum.llm
   });
-  const toolAIUsage = user.openaiAccount?.key ? 0 : totalPoints;
 
   // flat child tool response
   const childToolResponse = dispatchFlowResponse.map((item) => item.flowResponses).flat();
 
   // concat tool usage
   const totalPointsUsage =
-    toolAIUsage +
+    totalPoints +
     dispatchFlowResponse.reduce((sum, item) => {
       const childrenTotal = item.flowUsages.reduce((sum, item) => sum + item.totalPoints, 0);
       return sum + childrenTotal;
@@ -252,7 +240,6 @@ export const dispatchRunTools = async (props: DispatchToolModuleProps): Promise<
       .join(''),
     [DispatchNodeResponseKeyEnum.assistantResponses]: previewAssistantResponses,
     [DispatchNodeResponseKeyEnum.nodeResponse]: {
-      // 展示的积分消耗
       totalPoints: totalPointsUsage,
       toolCallTokens: toolNodeTokens,
       childTotalPoints: flatUsages.reduce((sum, item) => sum + item.totalPoints, 0),
@@ -267,14 +254,12 @@ export const dispatchRunTools = async (props: DispatchToolModuleProps): Promise<
       mergeSignId: nodeId
     },
     [DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
-      // 工具调用本身的积分消耗
       {
         moduleName: name,
-        totalPoints: toolAIUsage,
+        totalPoints,
         model: modelName,
         tokens: toolNodeTokens
       },
-      // 工具的消耗
       ...flatUsages
     ],
     [DispatchNodeResponseKeyEnum.interactive]: toolWorkflowInteractiveResponse

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

@@ -1,4 +1,4 @@
-import { createChatCompletion } from '../../../../ai/config';
+import { getAIApi } from '../../../../ai/config';
 import { filterGPTMessageByMaxTokens, loadRequestMessages } from '../../../../chat/utils';
 import {
   ChatCompletion,
@@ -52,7 +52,7 @@ export const runToolWithPromptCall = async (
     requestOrigin,
     runtimeNodes,
     runtimeEdges,
-    user,
+    node,
     stream,
     workflowStreamResponse,
     params: { temperature = 0, maxToken = 4000, aiChatVision }
@@ -225,15 +225,18 @@ export const runToolWithPromptCall = async (
 
   // console.log(JSON.stringify(requestMessages, null, 2));
   /* Run llm */
-  const { response: aiResponse, isStreamResponse } = await createChatCompletion({
-    body: requestBody,
-    userKey: user.openaiAccount,
-    options: {
-      headers: {
-        Accept: 'application/json, text/plain, */*'
-      }
+  const ai = getAIApi({
+    timeout: 480000
+  });
+  const aiResponse = await ai.chat.completions.create(requestBody, {
+    headers: {
+      Accept: 'application/json, text/plain, */*'
     }
   });
+  const isStreamResponse =
+    typeof aiResponse === 'object' &&
+    aiResponse !== null &&
+    ('iterator' in aiResponse || 'controller' in aiResponse);
 
   const answer = await (async () => {
     if (res && isStreamResponse) {

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

@@ -1,4 +1,4 @@
-import { createChatCompletion } from '../../../../ai/config';
+import { getAIApi } from '../../../../ai/config';
 import { filterGPTMessageByMaxTokens, loadRequestMessages } from '../../../../chat/utils';
 import {
   ChatCompletion,
@@ -92,7 +92,6 @@ export const runToolWithToolChoice = async (
     runtimeNodes,
     runtimeEdges,
     stream,
-    user,
     workflowStreamResponse,
     params: { temperature = 0, maxToken = 4000, aiChatVision }
   } = workflowProps;
@@ -272,265 +271,277 @@ export const runToolWithToolChoice = async (
   );
   // console.log(JSON.stringify(requestBody, null, 2), '==requestBody');
   /* Run llm */
-  const { response: aiResponse, isStreamResponse } = await createChatCompletion({
-    body: requestBody,
-    userKey: user.openaiAccount,
-    options: {
+  const ai = getAIApi({
+    timeout: 480000
+  });
+
+  try {
+    const aiResponse = await ai.chat.completions.create(requestBody, {
       headers: {
         Accept: 'application/json, text/plain, */*'
       }
-    }
-  });
+    });
+    const isStreamResponse =
+      typeof aiResponse === 'object' &&
+      aiResponse !== null &&
+      ('iterator' in aiResponse || 'controller' in aiResponse);
 
-  const { answer, toolCalls } = await (async () => {
-    if (res && isStreamResponse) {
-      return streamResponse({
-        res,
-        workflowStreamResponse,
-        toolNodes,
-        stream: aiResponse
-      });
-    } else {
-      const result = aiResponse as ChatCompletion;
-      const calls = result.choices?.[0]?.message?.tool_calls || [];
-      const answer = result.choices?.[0]?.message?.content || '';
+    const { answer, toolCalls } = await (async () => {
+      if (res && isStreamResponse) {
+        return streamResponse({
+          res,
+          workflowStreamResponse,
+          toolNodes,
+          stream: aiResponse
+        });
+      } else {
+        const result = aiResponse as ChatCompletion;
+        const calls = result.choices?.[0]?.message?.tool_calls || [];
+        const answer = result.choices?.[0]?.message?.content || '';
 
-      // 加上name和avatar
-      const toolCalls = calls.map((tool) => {
-        const toolNode = toolNodes.find((item) => item.nodeId === tool.function?.name);
-        return {
-          ...tool,
-          toolName: toolNode?.name || '',
-          toolAvatar: toolNode?.avatar || ''
-        };
-      });
+        // 加上name和avatar
+        const toolCalls = calls.map((tool) => {
+          const toolNode = toolNodes.find((item) => item.nodeId === tool.function?.name);
+          return {
+            ...tool,
+            toolName: toolNode?.name || '',
+            toolAvatar: toolNode?.avatar || ''
+          };
+        });
 
-      // 不支持 stream 模式的模型的流失响应
-      toolCalls.forEach((tool) => {
-        workflowStreamResponse?.({
-          event: SseResponseEventEnum.toolCall,
-          data: {
-            tool: {
-              id: tool.id,
-              toolName: tool.toolName,
-              toolAvatar: tool.toolAvatar,
-              functionName: tool.function.name,
-              params: tool.function?.arguments ?? '',
-              response: ''
+        // 不支持 stream 模式的模型的流失响应
+        toolCalls.forEach((tool) => {
+          workflowStreamResponse?.({
+            event: SseResponseEventEnum.toolCall,
+            data: {
+              tool: {
+                id: tool.id,
+                toolName: tool.toolName,
+                toolAvatar: tool.toolAvatar,
+                functionName: tool.function.name,
+                params: tool.function?.arguments ?? '',
+                response: ''
+              }
             }
-          }
-        });
-      });
-      if (answer) {
-        workflowStreamResponse?.({
-          event: SseResponseEventEnum.fastAnswer,
-          data: textAdaptGptResponse({
-            text: answer
-          })
-        });
-      }
-
-      return {
-        answer,
-        toolCalls: toolCalls
-      };
-    }
-  })();
-
-  // Run the selected tool by LLM.
-  const toolsRunResponse = (
-    await Promise.all(
-      toolCalls.map(async (tool) => {
-        const toolNode = toolNodes.find((item) => item.nodeId === tool.function?.name);
-
-        if (!toolNode) return;
-
-        const startParams = (() => {
-          try {
-            return json5.parse(tool.function.arguments);
-          } catch (error) {
-            return {};
-          }
-        })();
-
-        initToolNodes(runtimeNodes, [toolNode.nodeId], startParams);
-        const toolRunResponse = await dispatchWorkFlow({
-          ...workflowProps,
-          isToolCall: true
-        });
-
-        const stringToolResponse = formatToolResponse(toolRunResponse.toolResponses);
-
-        const toolMsgParams: ChatCompletionToolMessageParam = {
-          tool_call_id: tool.id,
-          role: ChatCompletionRequestMessageRoleEnum.Tool,
-          name: tool.function.name,
-          content: stringToolResponse
-        };
-
-        workflowStreamResponse?.({
-          event: SseResponseEventEnum.toolResponse,
-          data: {
-            tool: {
-              id: tool.id,
-              toolName: '',
-              toolAvatar: '',
-              params: '',
-              response: sliceStrStartEnd(stringToolResponse, 5000, 5000)
-            }
-          }
+          });
         });
+        if (answer) {
+          workflowStreamResponse?.({
+            event: SseResponseEventEnum.fastAnswer,
+            data: textAdaptGptResponse({
+              text: answer
+            })
+          });
+        }
 
         return {
-          toolRunResponse,
-          toolMsgParams
+          answer,
+          toolCalls: toolCalls
         };
-      })
-    )
-  ).filter(Boolean) as ToolRunResponseType;
-
-  const flatToolsResponseData = toolsRunResponse.map((item) => item.toolRunResponse).flat();
-  // concat tool responses
-  const dispatchFlowResponse = response
-    ? response.dispatchFlowResponse.concat(flatToolsResponseData)
-    : flatToolsResponseData;
-
-  if (toolCalls.length > 0 && !res?.closed) {
-    // Run the tool, combine its results, and perform another round of AI calls
-    const assistantToolMsgParams: ChatCompletionAssistantMessageParam[] = [
-      ...(answer
-        ? [
-            {
-              role: ChatCompletionRequestMessageRoleEnum.Assistant as 'assistant',
-              content: answer
-            }
-          ]
-        : []),
-      {
-        role: ChatCompletionRequestMessageRoleEnum.Assistant,
-        tool_calls: toolCalls
       }
-    ];
+    })();
 
-    /* 
+    // Run the selected tool by LLM.
+    const toolsRunResponse = (
+      await Promise.all(
+        toolCalls.map(async (tool) => {
+          const toolNode = toolNodes.find((item) => item.nodeId === tool.function?.name);
+
+          if (!toolNode) return;
+
+          const startParams = (() => {
+            try {
+              return json5.parse(tool.function.arguments);
+            } catch (error) {
+              return {};
+            }
+          })();
+
+          initToolNodes(runtimeNodes, [toolNode.nodeId], startParams);
+          const toolRunResponse = await dispatchWorkFlow({
+            ...workflowProps,
+            isToolCall: true
+          });
+
+          const stringToolResponse = formatToolResponse(toolRunResponse.toolResponses);
+
+          const toolMsgParams: ChatCompletionToolMessageParam = {
+            tool_call_id: tool.id,
+            role: ChatCompletionRequestMessageRoleEnum.Tool,
+            name: tool.function.name,
+            content: stringToolResponse
+          };
+
+          workflowStreamResponse?.({
+            event: SseResponseEventEnum.toolResponse,
+            data: {
+              tool: {
+                id: tool.id,
+                toolName: '',
+                toolAvatar: '',
+                params: '',
+                response: sliceStrStartEnd(stringToolResponse, 5000, 5000)
+              }
+            }
+          });
+
+          return {
+            toolRunResponse,
+            toolMsgParams
+          };
+        })
+      )
+    ).filter(Boolean) as ToolRunResponseType;
+
+    const flatToolsResponseData = toolsRunResponse.map((item) => item.toolRunResponse).flat();
+    // concat tool responses
+    const dispatchFlowResponse = response
+      ? response.dispatchFlowResponse.concat(flatToolsResponseData)
+      : flatToolsResponseData;
+
+    if (toolCalls.length > 0 && !res?.closed) {
+      // Run the tool, combine its results, and perform another round of AI calls
+      const assistantToolMsgParams: ChatCompletionAssistantMessageParam[] = [
+        ...(answer
+          ? [
+              {
+                role: ChatCompletionRequestMessageRoleEnum.Assistant as 'assistant',
+                content: answer
+              }
+            ]
+          : []),
+        {
+          role: ChatCompletionRequestMessageRoleEnum.Assistant,
+          tool_calls: toolCalls
+        }
+      ];
+
+      /* 
         ...
         user
         assistant: tool data
       */
-    const concatToolMessages = [
-      ...requestMessages,
-      ...assistantToolMsgParams
-    ] as ChatCompletionMessageParam[];
+      const concatToolMessages = [
+        ...requestMessages,
+        ...assistantToolMsgParams
+      ] as ChatCompletionMessageParam[];
 
-    // Only toolCall tokens are counted here, Tool response tokens count towards the next reply
-    const tokens = await countGptMessagesTokens(concatToolMessages, tools);
-    /* 
+      // Only toolCall tokens are counted here, Tool response tokens count towards the next reply
+      const tokens = await countGptMessagesTokens(concatToolMessages, tools);
+      /* 
         ...
         user
         assistant: tool data
         tool: tool response
       */
-    const completeMessages = [
-      ...concatToolMessages,
-      ...toolsRunResponse.map((item) => item?.toolMsgParams)
-    ];
+      const completeMessages = [
+        ...concatToolMessages,
+        ...toolsRunResponse.map((item) => item?.toolMsgParams)
+      ];
 
-    /* 
+      /* 
         Get tool node assistant response
         history assistant
         current tool assistant
         tool child assistant
       */
-    const toolNodeAssistant = GPTMessages2Chats([
-      ...assistantToolMsgParams,
-      ...toolsRunResponse.map((item) => item?.toolMsgParams)
-    ])[0] as AIChatItemType;
-    const toolChildAssistants = flatToolsResponseData
-      .map((item) => item.assistantResponses)
-      .flat()
-      .filter((item) => item.type !== ChatItemValueTypeEnum.interactive); // 交互节点留着下次记录
-    const toolNodeAssistants = [
-      ...assistantResponses,
-      ...toolNodeAssistant.value,
-      ...toolChildAssistants
-    ];
+      const toolNodeAssistant = GPTMessages2Chats([
+        ...assistantToolMsgParams,
+        ...toolsRunResponse.map((item) => item?.toolMsgParams)
+      ])[0] as AIChatItemType;
+      const toolChildAssistants = flatToolsResponseData
+        .map((item) => item.assistantResponses)
+        .flat()
+        .filter((item) => item.type !== ChatItemValueTypeEnum.interactive); // 交互节点留着下次记录
+      const toolNodeAssistants = [
+        ...assistantResponses,
+        ...toolNodeAssistant.value,
+        ...toolChildAssistants
+      ];
 
-    const runTimes =
-      (response?.runTimes || 0) +
-      flatToolsResponseData.reduce((sum, item) => sum + item.runTimes, 0);
-    const toolNodeTokens = response ? response.toolNodeTokens + tokens : tokens;
+      const runTimes =
+        (response?.runTimes || 0) +
+        flatToolsResponseData.reduce((sum, item) => sum + item.runTimes, 0);
+      const toolNodeTokens = response ? response.toolNodeTokens + tokens : tokens;
 
-    // Check stop signal
-    const hasStopSignal = flatToolsResponseData.some(
-      (item) => !!item.flowResponses?.find((item) => item.toolStop)
-    );
-    // Check interactive response(Only 1 interaction is reserved)
-    const workflowInteractiveResponseItem = toolsRunResponse.find(
-      (item) => item.toolRunResponse.workflowInteractiveResponse
-    );
-    if (hasStopSignal || workflowInteractiveResponseItem) {
-      // Get interactive tool data
-      const workflowInteractiveResponse =
-        workflowInteractiveResponseItem?.toolRunResponse.workflowInteractiveResponse;
+      // Check stop signal
+      const hasStopSignal = flatToolsResponseData.some(
+        (item) => !!item.flowResponses?.find((item) => item.toolStop)
+      );
+      // Check interactive response(Only 1 interaction is reserved)
+      const workflowInteractiveResponseItem = toolsRunResponse.find(
+        (item) => item.toolRunResponse.workflowInteractiveResponse
+      );
+      if (hasStopSignal || workflowInteractiveResponseItem) {
+        // Get interactive tool data
+        const workflowInteractiveResponse =
+          workflowInteractiveResponseItem?.toolRunResponse.workflowInteractiveResponse;
 
-      // Flashback traverses completeMessages, intercepting messages that know the first user
-      const firstUserIndex = completeMessages.findLastIndex((item) => item.role === 'user');
-      const newMessages = completeMessages.slice(firstUserIndex + 1);
+        // Flashback traverses completeMessages, intercepting messages that know the first user
+        const firstUserIndex = completeMessages.findLastIndex((item) => item.role === 'user');
+        const newMessages = completeMessages.slice(firstUserIndex + 1);
 
-      const toolWorkflowInteractiveResponse: WorkflowInteractiveResponseType | undefined =
-        workflowInteractiveResponse
-          ? {
-              ...workflowInteractiveResponse,
-              toolParams: {
-                entryNodeIds: workflowInteractiveResponse.entryNodeIds,
-                toolCallId: workflowInteractiveResponseItem?.toolMsgParams.tool_call_id,
-                memoryMessages: newMessages
+        const toolWorkflowInteractiveResponse: WorkflowInteractiveResponseType | undefined =
+          workflowInteractiveResponse
+            ? {
+                ...workflowInteractiveResponse,
+                toolParams: {
+                  entryNodeIds: workflowInteractiveResponse.entryNodeIds,
+                  toolCallId: workflowInteractiveResponseItem?.toolMsgParams.tool_call_id,
+                  memoryMessages: newMessages
+                }
               }
-            }
-          : undefined;
+            : undefined;
+
+        return {
+          dispatchFlowResponse,
+          toolNodeTokens,
+          completeMessages,
+          assistantResponses: toolNodeAssistants,
+          runTimes,
+          toolWorkflowInteractiveResponse
+        };
+      }
+
+      return runToolWithToolChoice(
+        {
+          ...props,
+          maxRunToolTimes: maxRunToolTimes - 1,
+          messages: completeMessages
+        },
+        {
+          dispatchFlowResponse,
+          toolNodeTokens,
+          assistantResponses: toolNodeAssistants,
+          runTimes
+        }
+      );
+    } else {
+      // No tool is invoked, indicating that the process is over
+      const gptAssistantResponse: ChatCompletionAssistantMessageParam = {
+        role: ChatCompletionRequestMessageRoleEnum.Assistant,
+        content: answer
+      };
+      const completeMessages = filterMessages.concat(gptAssistantResponse);
+      const tokens = await countGptMessagesTokens(completeMessages, tools);
+
+      // concat tool assistant
+      const toolNodeAssistant = GPTMessages2Chats([gptAssistantResponse])[0] as AIChatItemType;
 
       return {
-        dispatchFlowResponse,
-        toolNodeTokens,
+        dispatchFlowResponse: response?.dispatchFlowResponse || [],
+        toolNodeTokens: response ? response.toolNodeTokens + tokens : tokens,
         completeMessages,
-        assistantResponses: toolNodeAssistants,
-        runTimes,
-        toolWorkflowInteractiveResponse
+        assistantResponses: [...assistantResponses, ...toolNodeAssistant.value],
+        runTimes: (response?.runTimes || 0) + 1
       };
     }
-
-    return runToolWithToolChoice(
-      {
-        ...props,
-        maxRunToolTimes: maxRunToolTimes - 1,
-        messages: completeMessages
-      },
-      {
-        dispatchFlowResponse,
-        toolNodeTokens,
-        assistantResponses: toolNodeAssistants,
-        runTimes
-      }
-    );
-  } else {
-    // No tool is invoked, indicating that the process is over
-    const gptAssistantResponse: ChatCompletionAssistantMessageParam = {
-      role: ChatCompletionRequestMessageRoleEnum.Assistant,
-      content: answer
-    };
-    const completeMessages = filterMessages.concat(gptAssistantResponse);
-    const tokens = await countGptMessagesTokens(completeMessages, tools);
-
-    // concat tool assistant
-    const toolNodeAssistant = GPTMessages2Chats([gptAssistantResponse])[0] as AIChatItemType;
-
-    return {
-      dispatchFlowResponse: response?.dispatchFlowResponse || [],
-      toolNodeTokens: response ? response.toolNodeTokens + tokens : tokens,
-      completeMessages,
-      assistantResponses: [...assistantResponses, ...toolNodeAssistant.value],
-      runTimes: (response?.runTimes || 0) + 1
-    };
+  } catch (error) {
+    console.log(error);
+    addLog.warn(`LLM response error`, {
+      requestBody
+    });
+    return Promise.reject(error);
   }
 };
 

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

@@ -4,7 +4,7 @@ import type { ChatItemType, UserChatItemValueItemType } from '@fastgpt/global/co
 import { ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
 import { SseResponseEventEnum } from '@fastgpt/global/core/workflow/runtime/constants';
 import { textAdaptGptResponse } from '@fastgpt/global/core/workflow/runtime/utils';
-import { createChatCompletion } from '../../../ai/config';
+import { getAIApi } from '../../../ai/config';
 import type { ChatCompletion, StreamChatType } from '@fastgpt/global/core/ai/type.d';
 import { formatModelChars2Points } from '../../../../support/wallet/usage/utils';
 import type { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
@@ -138,6 +138,7 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
       if (modelConstantsData.censor && !user.openaiAccount?.key) {
         return postTextCensor({
           text: `${systemPrompt}
+            ${datasetQuoteText}
             ${userChatInput}
           `
         });
@@ -170,16 +171,21 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
   );
   // console.log(JSON.stringify(requestBody, null, 2), '===');
   try {
-    const { response, isStreamResponse } = await createChatCompletion({
-      body: requestBody,
+    const ai = getAIApi({
       userKey: user.openaiAccount,
-      options: {
-        headers: {
-          Accept: 'application/json, text/plain, */*'
-        }
+      timeout: 480000
+    });
+    const response = await ai.chat.completions.create(requestBody, {
+      headers: {
+        Accept: 'application/json, text/plain, */*'
       }
     });
 
+    const isStreamResponse =
+      typeof response === 'object' &&
+      response !== null &&
+      ('iterator' in response || 'controller' in response);
+
     const { answerText } = await (async () => {
       if (res && isStreamResponse) {
         // sse response

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

@@ -65,17 +65,7 @@ export async function dispatchDatasetSearch(
   }
 
   if (!userChatInput) {
-    return {
-      quoteQA: [],
-      [DispatchNodeResponseKeyEnum.nodeResponse]: {
-        totalPoints: 0,
-        query: '',
-        limit,
-        searchMode
-      },
-      nodeDispatchUsages: [],
-      [DispatchNodeResponseKeyEnum.toolResponses]: []
-    };
+    return Promise.reject(i18nT('common:core.chat.error.User input empty'));
   }
 
   // query extension

packages/web/common/file/utils.ts

@@ -61,14 +61,7 @@ export const readFileRawText = ({
 
         reject(getErrText(err, 'Load file error'));
       };
-      detectFileEncoding(file).then((encoding) => {
-        console.log(encoding);
-
-        reader.readAsText(
-          file,
-          ['iso-8859-1', 'windows-1252'].includes(encoding) ? 'gb2312' : 'utf-8'
-        );
-      });
+      reader.readAsText(file);
     } catch (error) {
       reject('The browser does not support file content reading');
     }
@@ -78,24 +71,6 @@ export const readFileRawText = ({
 export const readCsvRawText = async ({ file }: { file: File }) => {
   const rawText = await readFileRawText({ file });
   const csvArr = Papa.parse(rawText).data as string[][];
+
   return csvArr;
 };
-
-async function detectFileEncoding(file: File): Promise<string> {
-  const buffer = await loadFile2Buffer({ file });
-  const encoding = (() => {
-    const encodings = ['utf-8', 'iso-8859-1', 'windows-1252'];
-    for (let encoding of encodings) {
-      try {
-        const decoder = new TextDecoder(encoding, { fatal: true });
-        decoder.decode(buffer);
-        return encoding; // 如果解码成功，返回当前编码
-      } catch (e) {
-        // continue to try next encoding
-      }
-    }
-    return null; // 如果没有编码匹配，返回null
-  })();
-
-  return encoding || 'utf-8';
-}

packages/web/components/common/MySelect/MultipleRowSelect.tsx

@@ -245,7 +245,13 @@ export const MultipleRowArraySelect = ({
                   onClick={() => handleSelect(item)}
                   {...(isSelected ? { color: 'primary.600' } : {})}
                 >
-                  {showCheckbox && <Checkbox isChecked={isChecked} mr={1} />}
+                  {showCheckbox && (
+                    <Checkbox
+                      isChecked={isChecked}
+                      icon={<MyIcon name={'common/check'} w={'12px'} />}
+                      mr={1}
+                    />
+                  )}
                   <Box>{item.label}</Box>
                 </Flex>
               );

packages/web/components/common/Textarea/CodeEditor/Editor.tsx

@@ -14,6 +14,7 @@ type EditorVariablePickerType = {
 };
 
 export type Props = Omit<BoxProps, 'resize' | 'onChange'> & {
+  height?: number;
   resize?: boolean;
   defaultValue?: string;
   value?: string;
@@ -110,7 +111,7 @@ const MyEditor = ({
       borderWidth={'1px'}
       borderRadius={'md'}
       borderColor={'myGray.200'}
-      py={1}
+      py={2}
       height={height}
       position={'relative'}
       pl={2}
@@ -131,8 +132,8 @@ const MyEditor = ({
       {resize && (
         <Box
           position={'absolute'}
-          right={'-2.5'}
-          bottom={'-3.5'}
+          right={'-1'}
+          bottom={'-1'}
           zIndex={10}
           cursor={'ns-resize'}
           px={'4px'}

packages/web/components/common/Textarea/CodeEditor/index.tsx

@@ -19,11 +19,9 @@ const CodeEditor = (props: Props) => {
         iconSrc="modal/edit"
         title={t('common:code_editor')}
         w={'full'}
-        h={'85vh'}
-        isCentered
       >
-        <ModalBody flex={'1 0 0'} overflow={'auto'}>
-          <MyEditor {...props} bg={'myGray.50'} height={'100%'} />
+        <ModalBody>
+          <MyEditor {...props} bg={'myGray.50'} defaultHeight={600} />
         </ModalBody>
         <ModalFooter>
           <Button mr={2} onClick={onClose} px={6}>

packages/web/hooks/useI18n.ts

@@ -12,27 +12,25 @@ const LANG_KEY = 'NEXT_LOCALE';
 
 export const useI18nLng = () => {
   const { i18n } = useTranslation();
-  const languageMap: Record<string, string> = {
-    zh: 'zh',
-    'zh-CN': 'zh',
-    'zh-Hans': 'zh',
-    en: 'en',
-    'en-US': 'en'
-  };
 
   const onChangeLng = (lng: string) => {
-    const lang = languageMap[lng] || 'en';
-
-    setCookie(LANG_KEY, lang, {
-      expires: 30
+    setCookie(LANG_KEY, lng, {
+      expires: 30,
+      sameSite: 'None',
+      secure: true
     });
-    i18n?.changeLanguage(lang);
+    i18n?.changeLanguage(lng);
   };
 
   const setUserDefaultLng = () => {
     if (!navigator || !localStorage) return;
     if (getCookie(LANG_KEY)) return onChangeLng(getCookie(LANG_KEY) as string);
 
+    const languageMap: Record<string, string> = {
+      zh: 'zh',
+      'zh-CN': 'zh'
+    };
+
     const lang = languageMap[navigator.language] || 'en';
 
     // currentLng not in userLang

packages/web/hooks/useWidthVariable.ts

@@ -11,14 +11,11 @@ export const useWidthVariable = <T = any>({
 }) => {
   const value = useMemo(() => {
     // 根据 width 计算，找到第一个大于 width 的值
-    const reversedWidthList = [...widthList].reverse();
-    const reversedList = [...list].reverse();
-    const index = reversedWidthList.findIndex((item) => width > item);
-
+    const index = widthList.findLastIndex((item) => width > item);
     if (index === -1) {
-      return reversedList[0];
+      return list[0];
     }
-    return reversedList[index];
+    return list[index];
   }, [list, width, widthList]);
 
   return value;

projects/app/src/components/core/app/DatasetParamsModal.tsx

@@ -206,7 +206,12 @@ const DatasetParamsModal = ({
                   </Box>
                 </Box>
                 <Box position={'relative'} w={'18px'} h={'18px'}>
-                  <Checkbox colorScheme="primary" isChecked={getValues('usingReRank')} size="lg" />
+                  <Checkbox
+                    colorScheme="primary"
+                    isChecked={getValues('usingReRank')}
+                    size="lg"
+                    icon={<MyIcon name={'common/check'} w={'12px'} />}
+                  />
                   <Box position={'absolute'} top={0} right={0} bottom={0} left={0} zIndex={1}></Box>
                 </Box>
               </Flex>

projects/app/src/components/core/chat/ChatContainer/ChatBox/components/ResponseTags.tsx

@@ -30,7 +30,6 @@ const ResponseTags = ({
   const { t } = useTranslation();
   const quoteListRef = React.useRef<HTMLDivElement>(null);
   const dataId = historyItem.dataId;
-
   const {
     totalQuoteList: quoteList = [],
     llmModuleAccount = 0,

projects/app/src/components/support/permission/MemberManager/AddMemberModal.tsx

@@ -117,12 +117,11 @@ function AddMemberModal({ onClose, mode = 'member' }: AddModalPropsType) {
             <Flex flexDirection="column" mt="2" overflow={'auto'} maxH="400px">
               {filterGroups.map((group) => {
                 const onChange = () => {
-                  setSelectedGroupIdList((state) => {
-                    if (state.includes(group._id)) {
-                      return state.filter((v) => v !== group._id);
-                    }
-                    return [...state, group._id];
-                  });
+                  if (selectedGroupIdList.includes(group._id)) {
+                    setSelectedGroupIdList(selectedGroupIdList.filter((v) => v !== group._id));
+                  } else {
+                    setSelectedGroupIdList([...selectedGroupIdList, group._id]);
+                  }
                 };
                 const collaborator = collaboratorList.find((v) => v.groupId === group._id);
                 return (
@@ -142,7 +141,10 @@ function AddMemberModal({ onClose, mode = 'member' }: AddModalPropsType) {
                     }}
                     onClick={onChange}
                   >
-                    <Checkbox isChecked={selectedGroupIdList.includes(group._id)} />
+                    <Checkbox
+                      isChecked={selectedGroupIdList.includes(group._id)}
+                      icon={<MyIcon name={'common/check'} w={'12px'} />}
+                    />
                     <MyAvatar src={group.avatar} w="1.5rem" borderRadius={'50%'} />
                     <Box ml="2" w="full">
                       {group.name === DefaultGroupName ? userInfo?.team.teamName : group.name}
@@ -155,12 +157,11 @@ function AddMemberModal({ onClose, mode = 'member' }: AddModalPropsType) {
               })}
               {filterMembers.map((member) => {
                 const onChange = () => {
-                  setSelectedMembers((state) => {
-                    if (state.includes(member.tmbId)) {
-                      return state.filter((v) => v !== member.tmbId);
-                    }
-                    return [...state, member.tmbId];
-                  });
+                  if (selectedMemberIdList.includes(member.tmbId)) {
+                    setSelectedMembers(selectedMemberIdList.filter((v) => v !== member.tmbId));
+                  } else {
+                    setSelectedMembers([...selectedMemberIdList, member.tmbId]);
+                  }
                 };
                 const collaborator = collaboratorList.find((v) => v.tmbId === member.tmbId);
                 return (
@@ -204,12 +205,11 @@ function AddMemberModal({ onClose, mode = 'member' }: AddModalPropsType) {
             <Flex flexDirection="column" mt="2" overflow={'auto'} maxH="400px">
               {selectedGroupIdList.map((groupId) => {
                 const onChange = () => {
-                  setSelectedGroupIdList((state) => {
-                    if (state.includes(groupId)) {
-                      return state.filter((v) => v !== groupId);
-                    }
-                    return [...state, groupId];
-                  });
+                  if (selectedGroupIdList.includes(groupId)) {
+                    setSelectedGroupIdList(selectedGroupIdList.filter((v) => v !== groupId));
+                  } else {
+                    setSelectedGroupIdList([...selectedGroupIdList, groupId]);
+                  }
                 };
                 const group = groups.find((v) => String(v._id) === groupId);
                 return (

projects/app/src/global/core/chat/utils.ts

@@ -6,15 +6,11 @@ import { FlowNodeTypeEnum } from '@fastgpt/global/core/workflow/node/constant';
 const isLLMNode = (item: ChatHistoryItemResType) =>
   item.moduleType === FlowNodeTypeEnum.chatNode || item.moduleType === FlowNodeTypeEnum.tools;
 
-export function transformPreviewHistories(
-  histories: ChatItemType[],
-  responseDetail: boolean
-): ChatItemType[] {
+export function transformPreviewHistories(histories: ChatItemType[]): ChatItemType[] {
   return histories.map((item) => {
     return {
       ...addStatisticalDataToHistoryItem(item),
-      responseData: undefined,
-      ...(responseDetail ? {} : { totalQuoteList: undefined })
+      responseData: undefined
     };
   });
 }
@@ -22,7 +18,6 @@ export function transformPreviewHistories(
 export function addStatisticalDataToHistoryItem(historyItem: ChatItemType) {
   if (historyItem.obj !== ChatRoleEnum.AI) return historyItem;
   if (historyItem.totalQuoteList !== undefined) return historyItem;
-  if (!historyItem.responseData) return historyItem;
 
   // Flat children
   const flatResData: ChatHistoryItemResType[] =

projects/app/src/pages/account/components/Info/index.tsx

@@ -45,7 +45,6 @@ import { TeamMemberRoleEnum } from '@fastgpt/global/support/user/team/constant';
 import QuestionTip from '@fastgpt/web/components/common/MyTooltip/QuestionTip';
 import { useSystem } from '@fastgpt/web/hooks/useSystem';
 import MyImage from '@fastgpt/web/components/common/Image/MyImage';
-import { getWebReqUrl } from '@fastgpt/web/common/system/utils';
 
 const StandDetailModal = dynamic(() => import('./standardDetailModal'));
 const TeamMenu = dynamic(() => import('@/components/support/user/team/TeamMenu'));
@@ -495,7 +494,7 @@ const PlanUsage = () => {
             </Box>
           </Flex>
           <Link
-            href={getWebReqUrl(EXTRA_PLAN_CARD_ROUTE)}
+            href={EXTRA_PLAN_CARD_ROUTE}
             transform={'translateX(15px)'}
             display={'flex'}
             alignItems={'center'}

projects/app/src/pages/api/core/chat/getPaginationRecords.ts

@@ -82,16 +82,11 @@ async function handler(
     limit: pageSize
   });
 
-  const responseDetail = !shareChat || shareChat.responseDetail;
-
   // Remove important information
   if (shareChat && app.type !== AppTypeEnum.plugin) {
     histories.forEach((item) => {
       if (item.obj === ChatRoleEnum.AI) {
-        item.responseData = filterPublicNodeResponseData({
-          flowResponses: item.responseData,
-          responseDetail
-        });
+        item.responseData = filterPublicNodeResponseData({ flowResponses: item.responseData });
 
         if (shareChat.showNodeStatus === false) {
           item.value = item.value.filter((v) => v.type !== ChatItemValueTypeEnum.tool);
@@ -101,7 +96,7 @@ async function handler(
   }
 
   return {
-    list: isPlugin ? histories : transformPreviewHistories(histories, responseDetail),
+    list: isPlugin ? histories : transformPreviewHistories(histories),
     total
   };
 }

projects/app/src/pages/api/core/chat/getResData.ts

@@ -11,7 +11,6 @@ import { ChatHistoryItemResType } from '@fastgpt/global/core/chat/type';
 import { OutLinkChatAuthProps } from '@fastgpt/global/support/permission/chat';
 import { authApp } from '@fastgpt/service/support/permission/app/auth';
 import { filterPublicNodeResponseData } from '@fastgpt/global/core/chat/utils';
-import { MongoOutLink } from '@fastgpt/service/support/outLink/schema';
 
 export type getResDataQuery = OutLinkChatAuthProps & {
   chatId?: string;
@@ -27,57 +26,44 @@ async function handler(
   req: ApiRequestProps<getResDataBody, getResDataQuery>,
   res: ApiResponseType<any>
 ): Promise<getResDataResponse> {
-  const { appId, chatId, dataId, shareId } = req.query;
+  const { appId, chatId, dataId } = req.query;
   if (!appId || !chatId || !dataId) {
     return {};
   }
 
   // 1. Un login api: share chat, team chat
   // 2. Login api: account chat, chat log
-  const authData = await (() => {
-    try {
-      return authChatCrud({
-        req,
-        authToken: true,
-        authApiKey: true,
-        ...req.query,
-        per: ReadPermissionVal
-      });
-    } catch (error) {
-      return authApp({
-        req,
-        authToken: true,
-        authApiKey: true,
-        appId,
-        per: ManagePermissionVal
-      });
-    }
-  })();
-
-  const [chatData] = await Promise.all([
-    MongoChatItem.findOne(
-      {
-        appId,
-        chatId,
-        dataId
-      },
-      'obj responseData'
-    ).lean(),
-    shareId ? MongoOutLink.findOne({ shareId }).lean() : Promise.resolve(null)
-  ]);
-
-  if (chatData?.obj !== ChatRoleEnum.AI) {
-    return {};
+  try {
+    await authChatCrud({
+      req,
+      authToken: true,
+      authApiKey: true,
+      ...req.query,
+      per: ReadPermissionVal
+    });
+  } catch (error) {
+    await authApp({
+      req,
+      authToken: true,
+      authApiKey: true,
+      appId,
+      per: ManagePermissionVal
+    });
   }
 
-  const flowResponses = chatData.responseData ?? {};
-  return req.query.shareId
-    ? filterPublicNodeResponseData({
-        // @ts-ignore
-        responseDetail: authData.responseDetail,
-        flowResponses: chatData.responseData
-      })
-    : flowResponses;
+  const chatData = await MongoChatItem.findOne(
+    {
+      appId,
+      chatId,
+      dataId
+    },
+    'obj responseData'
+  ).lean();
+
+  if (chatData?.obj === ChatRoleEnum.AI) {
+    const data = chatData.responseData || {};
+    return req.query.shareId ? filterPublicNodeResponseData(data) : data;
+  } else return {};
 }
 
 export default NextAPI(handler);

projects/app/src/pages/api/v1/chat/completions.ts

@@ -363,7 +363,7 @@ async function handler(req: NextApiRequest, res: NextApiResponse) {
     /* select fe response field */
     const feResponseData = canWrite
       ? flowResponses
-      : filterPublicNodeResponseData({ flowResponses, responseDetail });
+      : filterPublicNodeResponseData({ flowResponses });
 
     if (stream) {
       workflowResponseWrite({
@@ -380,10 +380,12 @@ async function handler(req: NextApiRequest, res: NextApiResponse) {
       });
 
       if (detail) {
-        workflowResponseWrite({
-          event: SseResponseEventEnum.flowResponses,
-          data: feResponseData
-        });
+        if (responseDetail || isPlugin) {
+          workflowResponseWrite({
+            event: SseResponseEventEnum.flowResponses,
+            data: feResponseData
+          });
+        }
       }
 
       res.end();

projects/app/src/pages/app/detail/components/SimpleApp/EditForm.tsx

@@ -104,10 +104,7 @@ const EditForm = ({
   const formatVariables = useMemo(
     () =>
       formatEditorVariablePickerIcon([
-        ...workflowSystemVariables.filter(
-          (variable) =>
-            !['appId', 'chatId', 'responseChatItemId', 'histories'].includes(variable.key)
-        ),
+        ...workflowSystemVariables,
         ...(appForm.chatConfig.variables || [])
       ]).map((item) => ({
         ...item,

projects/app/src/pages/price/components/ExtraPlan.tsx

@@ -260,7 +260,7 @@ const ExtraPlan = () => {
               >
                 <MyNumberInput
                   name="points"
-                  register={registerExtraPoints}
+                  register={registerDatasetSize}
                   min={0}
                   max={10000}
                   size={'sm'}

projects/app/src/service/events/generateQA.ts

@@ -1,7 +1,7 @@
 import { MongoDatasetTraining } from '@fastgpt/service/core/dataset/training/schema';
 import { pushQAUsage } from '@/service/support/wallet/usage/push';
 import { TrainingModeEnum } from '@fastgpt/global/core/dataset/constants';
-import { createChatCompletion } from '@fastgpt/service/core/ai/config';
+import { getAIApi } from '@fastgpt/service/core/ai/config';
 import type { ChatCompletionMessageParam } from '@fastgpt/global/core/ai/type.d';
 import { addLog } from '@fastgpt/service/common/system/log';
 import { splitText2Chunks } from '@fastgpt/global/common/string/textSplitter';
@@ -109,8 +109,11 @@ ${replaceVariable(Prompt_AgentQA.fixedText, { text })}`;
       }
     ];
 
-    const { response: chatResponse } = await createChatCompletion({
-      body: llmCompletionsBodyFormat(
+    const ai = getAIApi({
+      timeout: 600000
+    });
+    const chatResponse = await ai.chat.completions.create(
+      llmCompletionsBodyFormat(
         {
           model: modelData.model,
           temperature: 0.3,
@@ -119,7 +122,7 @@ ${replaceVariable(Prompt_AgentQA.fixedText, { text })}`;
         },
         modelData
       )
-    });
+    );
     const answer = chatResponse.choices?.[0].message?.content || '';
 
     const qaArr = formatSplitText(answer, text); // 格式化后的QA对
@@ -162,7 +165,6 @@ ${replaceVariable(Prompt_AgentQA.fixedText, { text })}`;
     reduceQueue();
     generateQA();
   } catch (err: any) {
-    addLog.error(`[QA Queue] Error`);
     reduceQueue();
 
     if (await checkInvalidChunkAndLock({ err, data, errText: 'QA模型调用失败' })) {

projects/app/src/service/events/generateVector.ts

@@ -121,7 +121,6 @@ export async function generateVector(): Promise<any> {
     reduceQueue();
     generateVector();
   } catch (err: any) {
-    addLog.error(`[Vector Queue] Error`, err);
     reduceQueue();
 
     if (await checkInvalidChunkAndLock({ err, data, errText: '向量模型调用失败' })) {

projects/app/src/service/support/permission/auth/chat.ts

@@ -42,19 +42,18 @@ export async function authChatCrud({
   chat?: ChatSchema;
   isOutLink: boolean;
   uid?: string;
-  responseDetail: boolean;
 }> {
   const isOutLink = Boolean((shareId || spaceTeamId) && outLinkUid);
-  if (!chatId) return { isOutLink, uid: outLinkUid, responseDetail: true };
+  if (!chatId) return { isOutLink, uid: outLinkUid };
 
   const chat = await MongoChat.findOne({ appId, chatId }).lean();
 
-  const { uid, responseDetail } = await (async () => {
+  const { uid } = await (async () => {
     // outLink Auth
     if (shareId && outLinkUid) {
-      const { uid, shareChat } = await authOutLink({ shareId, outLinkUid });
+      const { uid } = await authOutLink({ shareId, outLinkUid });
       if (!chat || (chat.shareId === shareId && chat.outLinkUid === uid)) {
-        return { uid, responseDetail: shareChat.responseDetail };
+        return { uid };
       }
       return Promise.reject(ChatErrEnum.unAuthChat);
     }
@@ -63,12 +62,12 @@ export async function authChatCrud({
       const { uid } = await authTeamSpaceToken({ teamId: spaceTeamId, teamToken });
       addLog.debug('Auth team token', { uid, spaceTeamId, teamToken, chatUid: chat?.outLinkUid });
       if (!chat || (String(chat.teamId) === String(spaceTeamId) && chat.outLinkUid === uid)) {
-        return { uid, responseDetail: true };
+        return { uid };
       }
       return Promise.reject(ChatErrEnum.unAuthChat);
     }
 
-    if (!chat) return { id: outLinkUid, responseDetail: true };
+    if (!chat) return { id: outLinkUid };
 
     // auth req
     const { teamId, tmbId, permission } = await authApp({
@@ -81,19 +80,18 @@ export async function authChatCrud({
 
     if (String(teamId) !== String(chat.teamId)) return Promise.reject(ChatErrEnum.unAuthChat);
 
-    if (permission.hasManagePer) return { uid: outLinkUid, responseDetail: true };
-    if (String(tmbId) === String(chat.tmbId)) return { uid: outLinkUid, responseDetail: true };
+    if (permission.hasManagePer) return { uid: outLinkUid };
+    if (String(tmbId) === String(chat.tmbId)) return { uid: outLinkUid };
 
     return Promise.reject(ChatErrEnum.unAuthChat);
   })();
 
-  if (!chat) return { isOutLink, uid, responseDetail };
+  if (!chat) return { isOutLink, uid };
 
   return {
     chat,
     isOutLink,
-    uid,
-    responseDetail
+    uid
   };
 }