15308555518/ FastGPT
1
0
Fork 0
mirror of https://github.com/labring/FastGPT.git synced 2025-12-25 20:02:47 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

V4.11.0 features (#5270) 

* feat: workflow catch error (#5220)

* feat: error catch

* feat: workflow catch error

* perf: add catch error to node

* feat: system tool error catch

* catch error

* fix: ts

* update doc

* perf: training queue code (#5232)

* doc

* perf: training queue code

* Feat: 优化错误提示与重试逻辑 (#5192)

* feat: 批量重试异常数据 & 报错信息国际化

  - 新增“全部重试”按钮，支持批量重试所有训练异常数据
  - 报错信息支持国际化，常见错误自动映射为 i18n key
  - 相关文档和 i18n 资源已同步更新

* feat: enhance error message and retry mechanism

* feat: enhance error message and retry mechanism

* feat: add retry_failed i18n key

* feat: enhance error message and retry mechanism

* feat: enhance error message and retry mechanism

* feat: enhance error message and retry mechanism : 5

* feat: enhance error message and retry mechanism : 6

* feat: enhance error message and retry mechanism : 7

* feat: enhance error message and retry mechanism : 8

* perf: catch chat error

* perf: copy hook (#5246)

* perf: copy hook

* doc

* doc

* add app evaluation (#5083)

* add app evaluation

* fix

* usage

* variables

* editing condition

* var ui

* isplus filter

* migrate code

* remove utils

* name

* update type

* build

* fix

* fix

* fix

* delete comment

* fix

* perf: eval code

* eval code

* eval code

* feat: ttfb time in model log

* Refactor chat page (#5253)

* feat: update side bar layout; add login and logout logic at chat page

* refactor: encapsulate login logic and reuse it in `LoginModal` and `Login` page

* chore: improve some logics and comments

* chore: improve some logics

* chore: remove redundant side effect; add translations

---------

Co-authored-by: Archer <545436317@qq.com>

* perf: chat page code

* doc

* perf: provider redirect

* chore: ui improvement (#5266)

* Fix: SSE

* Fix: SSE

* eval pagination (#5264)

* eval scroll pagination

* change eval list to manual pagination

* number

* fix build

* fix

* version doc (#5267)

* version doc

* version doc

* doc

* feat: eval model select

* config eval model

* perf: eval detail modal ui

* doc

* doc

* fix: chat store reload

* doc

---------

Co-authored-by: colnii <1286949794@qq.com>
Co-authored-by: heheer <heheer@sealos.io>
Co-authored-by: 酒川户 <76519998+chuanhu9@users.noreply.github.com>
This commit is contained in:
Archer 2025-07-22 09:42:50 +08:00 committed by GitHub
parent de208d6c3f
commit 13b7e0a192
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
212 changed files with 5840 additions and 3400 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
.cursor/design/core/app/workflow/error_catch.mdc Normal file
View File

@ -0,0 +1,28 @@
---
description:
globs:
alwaysApply: false
---
这是一个工作流节点报错捕获的设计文档。
# 背景
现在工作流运行节点若其中有一个报错，则整个工作流中断，无法继续运行，只有红色英文toast，不太友好。对于对工作流可控性要求高的用户，愿意通过编排为报错兜底。现有编排较麻烦。
这类似于代码里的 try catch 机制，用户可以获得 catch 的错误，而不是直接抛错并结束工作流。
# 实现效果
1. 部分节点可以拥有报错捕获选项，也就是 node 里 catchError 不为 undefined 的节点，catchError=true 代表启用报错捕获，catchError=false 代表不启用报错捕获。
2. 支持报错捕获节点，在输出栏右侧会有一个“错误捕获”的开关。
3. node 的 output 属性种，有一个`errorField`的字段，标识该输出是开启报错捕获时候，才会拥有的输出。
4. 开启报错捕获的节点，在运行错误时，不会阻塞后续节点运行，而是输出报错信息，并继续向下执行。
5. 开启报错捕获的节点，会多出一个“错误输出”的分支连线，错误时候会走错误的分支提示。
# 实现方案
1. FlowNodeCommonType 属性上增加一个`catchError`的可选 boolean 值。如果需要报错捕获的节点，则设置 true/false，标识启用报错捕获，并且设置默认是否启用报错捕获。
2. FlowNodeOutputTypeEnume增加一个 error 枚举值，表示该字段是错误时候才展示的输出。
3. IOTitle 组件里接收 catchError 字段，如果为 true，则在右侧展示“错误捕获”的开关。
4. 所有现有的 RenderOutput 的组件，都需要改造。传入的 flowOutputList 都不包含 hidden 和 error类型的。
5. 单独在`FastGPT/projects/app/src/pageComponents/app/detail/WorkflowComponents/Flow/nodes/render/RenderOutput`下新建一个`CatchError`的组件，用于专门渲染错误类型输出，同时有一个 SourceHandler。

35
README.md
View File

@ -47,40 +47,41 @@ https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409b
## 💡 RoadMap
`1` 应用编排能力
- [x] 对话工作流、插件工作流
- [x] 工具调用
- [x] Code sandbox
- [x] 循环调用
- [x] 用户选择
- [x] 表单输入
- [x] 对话工作流、插件工作流，包含基础的 RPA 节点。
- [x] Agent 调用
- [x] 用户交互节点
- [x] 双向 MCP
- [ ] 上下文管理
- [ ] AI 生成工作流
`2` 知识库能力
`2` 应用调试能力
- [x] 知识库单点搜索测试
- [x] 对话时反馈引用并可修改与删除
- [x] 完整调用链路日志
- [ ] 应用评测
- [ ] 高级编排 DeBug 调试模式
- [ ] 应用节点日志
`3` 知识库能力
- [x] 多库复用，混用
- [x] chunk 记录修改和删除
- [x] 支持手动输入，直接分段，QA 拆分导入
- [x] 支持 txt，md，html，pdf，docx，pptx，csv，xlsx (有需要更多可 PR file loader)，支持 url 读取、CSV 批量导入
- [x] 混合检索 & 重排
- [x] API 知识库
- [ ] 自定义文件读取服务
- [ ] 自定义分块服务
`3` 应用调试能力
- [x] 知识库单点搜索测试
- [x] 对话时反馈引用并可修改与删除
- [x] 完整上下文呈现
- [x] 完整模块中间值呈现
- [ ] 高级编排 DeBug 模式
- [ ] RAG 模块热插拔
`4` OpenAPI 接口
- [x] completions 接口 (chat 模式对齐 GPT 接口)
- [x] 知识库 CRUD
- [x] 对话 CRUD
- [ ] 完整 API Documents
`5` 运营能力
- [x] 免登录分享窗口
- [x] Iframe 一键嵌入
- [x] 聊天窗口嵌入支持自定义 Icon，默认打开，拖拽等功能
- [x] 统一查阅对话记录，并对数据进行标注
- [ ] 应用运营日志
`6` 其他
- [x] 可视化模型配置。

56
docSite/content/zh-cn/docs/development/upgrading/4110.md Normal file
View File

@ -0,0 +1,56 @@
---
title: 'V4.11.0(进行中)'
description: 'FastGPT V4.11.0 更新说明'
icon: 'upgrade'
draft: false
toc: true
weight: 783
---
<!-- ## 升级说明
### 1. 修改环境变量
FastGPT 商业版用户，可以增加评估相关环境变量，并在更新后，在管理端点击一次保存。
```
EVAL_CONCURRENCY=3 # 评估单节点并发数
EVAL_LINE_LIMIT=1000 # 评估文件最大行数
```
### 2. 更新镜像：
- 更新 FastGPT 镜像tag: v4.11.0
- 更新 FastGPT 商业版镜像tag: v4.11.0
- 更新 fastgpt-plugin 镜像 tag: v0.1.4
- mcp_server 无需更新
- Sandbox 无需更新
- AIProxy 无需更新 -->
## 项目调整
1. 移除所有**开源功能**的限制，包括：应用数量和知识库数量上限。
2. 调整 RoadMap，增加`上下文管理`,`AI 生成工作流`,`高级编排 DeBug 调试模式`等计划。
## 🚀 新增内容
1. 商业版增加**应用评测(Beta 版)**，可对应用进行有监督评分。
2. 工作流部分节点支持报错捕获分支。
3. 对话页独立 tab 页面UX。
4. 支持 Signoz traces 和 logs 系统追踪。
5. 新增 Gemini2.5, grok4, kimi 模型配置。
6. 模型调用日志增加首字响应时长和请求 IP。
## ⚙️ 优化
1. 优化代码，避免递归造成的内存堆积。
2. 知识库训练：支持全部重试当前集合异常数据。
3. 工作流 valueTypeFormat，避免数据类型不一致。
## 🐛 修复
1. 问题分类和内容提取节点，默认模型无法通过前端校验，导致工作流无法运行和保存发布。
## 🔨 工具更新
1. Markdown 文本转 Docx 和 Xlsx 文件。

7
docSite/content/zh-cn/docs/shopping_cart/intro.md
View File

@ -20,19 +20,18 @@ FastGPT 商业版是基于 FastGPT 开源版的增强版本，增加了一些独
| 文档知识库 | ✅ | ✅ | ✅ |
| 外部使用 | ✅ | ✅ | ✅ |
| API 知识库 | ✅ | ✅ | ✅ |
| 最大应用数量 | 500 | 无限制 | 由付费套餐决定 |
| 最大知识库数量（单个知识库内容无限制） | 30 | 无限制 | 由付费套餐决定 |
| 自定义版权信息 | ❌ | ✅ | 设计中 |
| 多租户与支付 | ❌ | ✅ | ✅ |
| 团队空间 & 权限 | ❌ | ✅ | ✅ |
| 应用发布安全配置 | ❌ | ✅ | ✅ |
| 内容审核 | ❌ | ✅ | ✅ |
| 应用评测 | ❌ | ✅ | ✅ |
| web站点同步 | ❌ | ✅ | ✅ |
| 增强训练模式 | ❌ | ✅ | ✅ |
| 图片知识库 | ❌ | ✅ | ✅ |
| 知识库索引增强 | ❌ | ✅ | ✅ |
| 第三方应用快速接入（飞书、公众号） | ❌ | ✅ | ✅ |
| 管理后台 | ❌ | ✅ | 不需要 |
| SSO 登录（可自定义，也可使用内置：Github、公众号、钉钉、谷歌等） | ❌ | ✅ | 不需要 |
| 图片知识库 | ❌ | 设计中 | 设计中 |
| 对话日志运营分析 | ❌ | 设计中 | 设计中 |
| 完整商业授权 | ❌ | ✅ | ✅ |
{{< /table >}}

35
env.d.ts vendored
View File

@ -1,43 +1,8 @@
declare global {
namespace NodeJS {
interface ProcessEnv {
LOG_DEPTH: string;
DEFAULT_ROOT_PSW: string;
DB_MAX_LINK: string;
FILE_TOKEN_KEY: string;
AES256_SECRET_KEY: string;
ROOT_KEY: string;
OPENAI_BASE_URL: string;
CHAT_API_KEY: string;
AIPROXY_API_ENDPOINT: string;
AIPROXY_API_TOKEN: string;
MULTIPLE_DATA_TO_BASE64: string;
MONGODB_URI: string;
MONGODB_LOG_URI?: string;
PG_URL: string;
OCEANBASE_URL: string;
MILVUS_ADDRESS: string;
MILVUS_TOKEN: string;
SANDBOX_URL: string;
PRO_URL: string;
FE_DOMAIN: string;
FILE_DOMAIN: string;
NEXT_PUBLIC_BASE_URL: string;
LOG_LEVEL?: string;
STORE_LOG_LEVEL?: string;
USE_IP_LIMIT?: string;
WORKFLOW_MAX_RUN_TIMES?: string;
WORKFLOW_MAX_LOOP_TIMES?: string;
CHECK_INTERNAL_IP?: string;
CHAT_LOG_URL?: string;
CHAT_LOG_INTERVAL?: string;
CHAT_LOG_SOURCE_ID_PREFIX?: string;
ALLOWED_ORIGINS?: string;
SHOW_COUPON?: string;
CONFIG_JSON_PATH?: string;
PASSWORD_LOGIN_LOCK_SECONDS?: string;
PASSWORD_EXPIRED_MONTH?: string;
MAX_LOGIN_SESSION?: string;
}
}
}

5
packages/global/common/error/code/user.ts
View File

@ -6,7 +6,6 @@ export enum UserErrEnum {
userExist = 'userExist',
unAuthRole = 'unAuthRole',
account_psw_error = 'account_psw_error',
balanceNotEnough = 'balanceNotEnough',
unAuthSso = 'unAuthSso'
}
const errList = [
@ -22,10 +21,6 @@ const errList = [
statusText: UserErrEnum.account_psw_error,
message: i18nT('common:code_error.account_error')
},
{
statusText: UserErrEnum.balanceNotEnough,
message: i18nT('common:code_error.user_error.balance_not_enough')
},
{
statusText: UserErrEnum.unAuthSso,
message: i18nT('user:sso_auth_failed')

6
packages/global/common/error/utils.ts
View File

@ -1,4 +1,5 @@
import { replaceSensitiveText } from '../string/tools';
import { ERROR_RESPONSE } from './errorCode';
export const getErrText = (err: any, def = ''): any => {
const msg: string =
@ -12,6 +13,11 @@ export const getErrText = (err: any, def = ''): any => {
err?.msg ||
err?.error ||
def;
if (ERROR_RESPONSE[msg]) {
return ERROR_RESPONSE[msg].message;
}
// msg && console.log('error =>', msg);
return replaceSensitiveText(msg);
};

3
packages/global/common/system/types/index.d.ts vendored
View File

@ -51,6 +51,7 @@ export type FastGPTFeConfigsType = {
bind_notification_method?: ['email' | 'phone'];
googleClientVerKey?: string;
mcpServerProxyEndpoint?: string;
chineseRedirectUrl?: string;
show_emptyChat?: boolean;
show_appStore?: boolean;
@ -82,7 +83,6 @@ export type FastGPTFeConfigsType = {
customSharePageDomain?: string;
systemTitle?: string;
systemDescription?: string;
scripts?: { [key: string]: string }[];
favicon?: string;
@ -109,6 +109,7 @@ export type FastGPTFeConfigsType = {
uploadFileMaxAmount?: number;
uploadFileMaxSize?: number;
evalFileMaxLines?: number;
// Compute by systemEnv.customPdfParse
showCustomPdfParse?: boolean;

16
packages/global/common/system/utils.ts
View File

@ -5,15 +5,17 @@ export const delay = (ms: number) =>
}, ms);
});
export const retryFn = async <T>(fn: () => Promise<T>, retryTimes = 3): Promise<T> => {
try {
return fn();
} catch (error) {
if (retryTimes > 0) {
export const retryFn = async <T>(fn: () => Promise<T>, attempts = 3): Promise<T> => {
while (true) {
try {
return fn();
} catch (error) {
if (attempts <= 0) {
return Promise.reject(error);
}
await delay(500);
return retryFn(fn, retryTimes - 1);
attempts--;
}
return Promise.reject(error);
}
};

1
packages/global/core/ai/model.d.ts vendored
View File

@ -47,6 +47,7 @@ export type LLMModelItemType = PriceType &
usedInClassify?: boolean; // classify
usedInExtractFields?: boolean; // extract fields
usedInToolCall?: boolean; // tool call
useInEvaluation?: boolean; // evaluation
functionCall: boolean;
toolChoice: boolean;

20
packages/global/core/app/evaluation/api.d.ts vendored Normal file
View File

@ -0,0 +1,20 @@
import type { PaginationProps } from '@fastgpt/web/common/fetch/type';
export type listEvaluationsBody = PaginationProps<{
searchKey?: string;
}>;
export type listEvalItemsBody = PaginationProps<{
evalId: string;
}>;
export type retryEvalItemBody = {
evalItemId: string;
};
export type updateEvalItemBody = {
evalItemId: string;
question: string;
expectedResponse: string;
variables: Record<string, string>;
};

22
packages/global/core/app/evaluation/constants.ts Normal file
View File

@ -0,0 +1,22 @@
import { i18nT } from '../../../../web/i18n/utils';
export const evaluationFileErrors = i18nT('dashboard_evaluation:eval_file_check_error');
export enum EvaluationStatusEnum {
queuing = 0,
evaluating = 1,
completed = 2
}
export const EvaluationStatusMap = {
[EvaluationStatusEnum.queuing]: {
name: i18nT('dashboard_evaluation:queuing')
},
[EvaluationStatusEnum.evaluating]: {
name: i18nT('dashboard_evaluation:evaluating')
},
[EvaluationStatusEnum.completed]: {
name: i18nT('dashboard_evaluation:completed')
}
};
export const EvaluationStatusValues = Object.keys(EvaluationStatusMap).map(Number);

51
packages/global/core/app/evaluation/type.d.ts vendored Normal file
View File

@ -0,0 +1,51 @@
import type { EvaluationStatusEnum } from './constants';
export type EvaluationSchemaType = {
_id: string;
teamId: string;
tmbId: string;
evalModel: string;
appId: string;
usageId: string;
name: string;
createTime: Date;
finishTime?: Date;
score?: number;
errorMessage?: string;
};
export type EvalItemSchemaType = {
evalId: string;
question: string;
expectedResponse: string;
globalVariables?: Record<string, any>;
history?: string;
response?: string;
responseTime?: Date;
finishTime?: Date;
status: EvaluationStatusEnum;
retry: number;
errorMessage?: string;
accuracy?: number;
relevance?: number;
semanticAccuracy?: number;
score?: number;
};
export type evaluationType = Pick<
EvaluationSchemaType,
'name' | 'appId' | 'createTime' | 'finishTime' | 'evalModel' | 'errorMessage' | 'score'
> & {
_id: string;
executorAvatar: string;
executorName: string;
appAvatar: string;
appName: string;
completedCount: number;
errorCount: number;
totalCount: number;
};
export type listEvalItemsItem = EvalItemSchemaType & {
evalItemId: string;
};

10
packages/global/core/app/evaluation/utils.ts Normal file
View File

@ -0,0 +1,10 @@
import type { VariableItemType } from '../type';
export const getEvaluationFileHeader = (appVariables?: VariableItemType[]) => {
if (!appVariables || appVariables.length === 0) return '*q,*a,history';
const variablesStr = appVariables
.map((item) => (item.required ? `*${item.key}` : item.key))
.join(',');
return `${variablesStr},*q,*a,history`;
};

4
packages/global/core/app/mcpTools/utils.ts
View File

@ -32,11 +32,11 @@ export const getMCPToolSetRuntimeNode = ({
nodeId: getNanoid(16),
flowNodeType: FlowNodeTypeEnum.toolSet,
avatar,
intro: 'MCP Tools',
intro: '',
inputs: [
{
key: NodeInputKeyEnum.toolSetData,
label: 'Tool Set Data',
label: '',
valueType: WorkflowIOValueTypeEnum.object,
renderTypeList: [FlowNodeInputTypeEnum.hidden],
value: {

3
packages/global/core/app/plugin/type.d.ts vendored
View File

@ -34,6 +34,9 @@ export type SystemPluginTemplateItemType = WorkflowTemplateType & {
versionList?: {
value: string;
description?: string;
inputs: FlowNodeInputItemType[];
outputs: FlowNodeOutputItemType[];
}[];
// Admin workflow tool

1
packages/global/core/app/type.d.ts vendored
View File

@ -66,6 +66,7 @@ export type AppListItemType = {
inheritPermission?: boolean;
private?: boolean;
sourceMember: SourceMemberType;
hasInteractiveNode?: boolean;
};
export type AppDetailType = AppSchema & {

10
packages/global/core/workflow/constants.ts
View File

@ -269,11 +269,11 @@ export enum NodeOutputKeyEnum {
reasoningText = 'reasoningText', // node reasoning. the value will be show but not save to history
success = 'success',
failed = 'failed',
error = 'error',
text = 'system_text',
addOutputParam = 'system_addOutputParam',
rawResponse = 'system_rawResponse',
systemError = 'system_error',
errorText = 'system_error_text',
// start
userFiles = 'userFiles',
@ -312,7 +312,13 @@ export enum NodeOutputKeyEnum {
loopStartIndex = 'loopStartIndex',
// form input
formInputResult = 'formInputResult'
formInputResult = 'formInputResult',
// File
fileTitle = 'fileTitle',
// @deprecated
error = 'error'
}
export enum VariableInputEnum {

1
packages/global/core/workflow/node/constant.ts
View File

@ -99,6 +99,7 @@ export const FlowNodeInputMap: Record<
export enum FlowNodeOutputTypeEnum {
hidden = 'hidden',
error = 'error',
source = 'source',
static = 'static',
dynamic = 'dynamic'

23
packages/global/core/workflow/runtime/type.d.ts vendored
View File

@ -9,7 +9,7 @@ import type { FlowNodeInputItemType, FlowNodeOutputItemType } from '../type/io.d
import type { NodeToolConfigType, StoreNodeItemType } from '../type/node';
import type { DispatchNodeResponseKeyEnum } from './constants';
import type { StoreEdgeItemType } from '../type/edge';
import type { NodeInputKeyEnum } from '../constants';
import type { NodeInputKeyEnum, NodeOutputKeyEnum } from '../constants';
import type { ClassifyQuestionAgentItemType } from '../template/system/classifyQuestion/type';
import type { NextApiResponse } from 'next';
import { UserModelSchema } from '../../../support/user/type';
@ -24,7 +24,10 @@ import type { AiChatQuoteRoleType } from '../template/system/aiChat/type';
import type { OpenaiAccountType } from '../../../support/user/team/type';
import { LafAccountType } from '../../../support/user/team/type';
import type { CompletionFinishReason } from '../../ai/type';
import type { WorkflowInteractiveResponseType } from '../template/system/interactive/type';
import type {
InteractiveNodeResponseType,
WorkflowInteractiveResponseType
} from '../template/system/interactive/type';
import type { SearchDataResponseItemType } from '../../dataset/type';
export type ExternalProviderType = {
openaiAccount?: OpenaiAccountType;
@ -104,6 +107,9 @@ export type RuntimeNodeItemType = {
// Tool
toolConfig?: StoreNodeItemType['toolConfig'];
// catch error
catchError?: boolean;
};
export type RuntimeEdgeItemType = StoreEdgeItemType & {
@ -116,7 +122,12 @@ export type DispatchNodeResponseType = {
runningTime?: number;
query?: string;
textOutput?: string;
// Client will toast
error?: Record<string, any> | string;
// Just show
errorText?: string;
customInputs?: Record<string, any>;
customOutputs?: Record<string, any>;
nodeInputs?: Record<string, any>;
@ -235,7 +246,7 @@ export type DispatchNodeResponseType = {
extensionTokens?: number;
};
export type DispatchNodeResultType<T = {}> = {
export type DispatchNodeResultType<T = {}, ERR = { [NodeOutputKeyEnum.errorText]?: string }> = {
[DispatchNodeResponseKeyEnum.skipHandleId]?: string[]; // skip some edge handle id
[DispatchNodeResponseKeyEnum.nodeResponse]?: DispatchNodeResponseType; // The node response detail
[DispatchNodeResponseKeyEnum.nodeDispatchUsages]?: ChatNodeUsageType[]; // Node total usage
@ -246,7 +257,11 @@ export type DispatchNodeResultType<T = {}> = {
[DispatchNodeResponseKeyEnum.runTimes]?: number;
[DispatchNodeResponseKeyEnum.newVariables]?: Record<string, any>;
[DispatchNodeResponseKeyEnum.memories]?: Record<string, any>;
} & T;
[DispatchNodeResponseKeyEnum.interactive]?: InteractiveNodeResponseType;
data?: T;
error?: ERR;
};
/* Single node props */
export type AIChatNodeProps = {

3
packages/global/core/workflow/runtime/utils.ts
View File

@ -251,7 +251,8 @@ export const storeNodes2RuntimeNodes = (
outputs: node.outputs,
pluginId: node.pluginId,
version: node.version,
toolConfig: node.toolConfig
toolConfig: node.toolConfig,
catchError: node.catchError
};
}) || []
);

9
packages/global/core/workflow/template/output.ts
View File

@ -2,6 +2,7 @@ import type { FlowNodeOutputItemType } from '../type/io.d';
import { NodeOutputKeyEnum } from '../constants';
import { FlowNodeOutputTypeEnum } from '../node/constant';
import { WorkflowIOValueTypeEnum } from '../constants';
import { i18nT } from '../../../../web/i18n/utils';
export const Output_Template_AddOutput: FlowNodeOutputItemType = {
id: NodeOutputKeyEnum.addOutputParam,
@ -15,3 +16,11 @@ export const Output_Template_AddOutput: FlowNodeOutputItemType = {
showDefaultValue: false
}
};
export const Output_Template_Error_Message: FlowNodeOutputItemType = {
id: NodeOutputKeyEnum.errorText,
key: NodeOutputKeyEnum.errorText,
type: FlowNodeOutputTypeEnum.error,
valueType: WorkflowIOValueTypeEnum.string,
label: i18nT('workflow:error_text')
};

5
packages/global/core/workflow/template/system/agent.ts
View File

@ -20,6 +20,7 @@ import { chatNodeSystemPromptTip, systemPromptTip } from '../tip';
import { LLMModelTypeEnum } from '../../../ai/constants';
import { i18nT } from '../../../../../web/i18n/utils';
import { Input_Template_File_Link } from '../input';
import { Output_Template_Error_Message } from '../output';
export const AgentNode: FlowNodeTemplateType = {
id: FlowNodeTypeEnum.agent,
@ -31,6 +32,7 @@ export const AgentNode: FlowNodeTemplateType = {
name: i18nT('workflow:template.agent'),
intro: i18nT('workflow:template.agent_intro'),
showStatus: true,
catchError: false,
courseUrl: '/docs/guide/dashboard/workflow/tool/',
version: '4.9.2',
inputs: [
@ -107,6 +109,7 @@ export const AgentNode: FlowNodeTemplateType = {
description: i18nT('common:core.module.output.description.Ai response content'),
valueType: WorkflowIOValueTypeEnum.string,
type: FlowNodeOutputTypeEnum.static
}
},
Output_Template_Error_Message
]
};

5
packages/global/core/workflow/template/system/aiChat/index.ts
View File

@ -20,6 +20,7 @@ import {
Input_Template_File_Link
} from '../../input';
import { i18nT } from '../../../../../../web/i18n/utils';
import { Output_Template_Error_Message } from '../../output';
export const AiChatQuoteRole = {
key: NodeInputKeyEnum.aiChatQuoteRole,
@ -54,6 +55,7 @@ export const AiChatModule: FlowNodeTemplateType = {
isTool: true,
courseUrl: '/docs/guide/dashboard/workflow/ai_chat/',
version: '4.9.7',
catchError: false,
inputs: [
Input_Template_SettingAiModel,
// --- settings modal
@ -158,6 +160,7 @@ export const AiChatModule: FlowNodeTemplateType = {
const modelItem = llmModelList.find((item) => item.model === model);
return modelItem?.reasoning !== true;
}
}
},
Output_Template_Error_Message
]
};

5
packages/global/core/workflow/template/system/contextExtract/index.ts
View File

@ -13,6 +13,7 @@ import {
import { Input_Template_SelectAIModel, Input_Template_History } from '../../input';
import { LLMModelTypeEnum } from '../../../../ai/constants';
import { i18nT } from '../../../../../../web/i18n/utils';
import { Output_Template_Error_Message } from '../../output';
export const ContextExtractModule: FlowNodeTemplateType = {
id: FlowNodeTypeEnum.contentExtract,
@ -25,6 +26,7 @@ export const ContextExtractModule: FlowNodeTemplateType = {
intro: i18nT('workflow:intro_text_content_extraction'),
showStatus: true,
isTool: true,
catchError: false,
courseUrl: '/docs/guide/dashboard/workflow/content_extract/',
version: '4.9.2',
inputs: [
@ -76,6 +78,7 @@ export const ContextExtractModule: FlowNodeTemplateType = {
description: i18nT('workflow:complete_extraction_result_description'),
valueType: WorkflowIOValueTypeEnum.string,
type: FlowNodeOutputTypeEnum.static
}
},
Output_Template_Error_Message
]
};

5
packages/global/core/workflow/template/system/datasetSearch.ts
View File

@ -15,6 +15,7 @@ import {
import { Input_Template_UserChatInput } from '../input';
import { DatasetSearchModeEnum } from '../../../dataset/constants';
import { i18nT } from '../../../../../web/i18n/utils';
import { Output_Template_Error_Message } from '../output';
export const Dataset_SEARCH_DESC = i18nT('workflow:template.dataset_search_intro');
@ -29,6 +30,7 @@ export const DatasetSearchModule: FlowNodeTemplateType = {
intro: Dataset_SEARCH_DESC,
showStatus: true,
isTool: true,
catchError: false,
courseUrl: '/docs/guide/dashboard/workflow/dataset_search/',
version: '4.9.2',
inputs: [
@ -143,6 +145,7 @@ export const DatasetSearchModule: FlowNodeTemplateType = {
type: FlowNodeOutputTypeEnum.static,
valueType: WorkflowIOValueTypeEnum.datasetQuote,
valueDesc: datasetQuoteValueDesc
}
},
Output_Template_Error_Message
]
};

16
packages/global/core/workflow/template/system/http468.ts
View File

@ -26,6 +26,7 @@ export const HttpNode468: FlowNodeTemplateType = {
intro: i18nT('workflow:intro_http_request'),
showStatus: true,
isTool: true,
catchError: false,
courseUrl: '/docs/guide/dashboard/workflow/http/',
inputs: [
{
@ -123,14 +124,6 @@ export const HttpNode468: FlowNodeTemplateType = {
label: i18nT('workflow:http_extract_output'),
description: i18nT('workflow:http_extract_output_description')
},
{
id: NodeOutputKeyEnum.error,
key: NodeOutputKeyEnum.error,
label: i18nT('workflow:request_error'),
description: i18nT('workflow:http_request_error_info'),
valueType: WorkflowIOValueTypeEnum.object,
type: FlowNodeOutputTypeEnum.static
},
{
id: NodeOutputKeyEnum.httpRawResponse,
key: NodeOutputKeyEnum.httpRawResponse,
@ -139,6 +132,13 @@ export const HttpNode468: FlowNodeTemplateType = {
description: i18nT('workflow:http_raw_response_description'),
valueType: WorkflowIOValueTypeEnum.any,
type: FlowNodeOutputTypeEnum.static
},
{
id: NodeOutputKeyEnum.error,
key: NodeOutputKeyEnum.error,
label: i18nT('workflow:error_text'),
valueType: WorkflowIOValueTypeEnum.string,
type: FlowNodeOutputTypeEnum.error
}
]
};

8
packages/global/core/workflow/template/system/laf.ts
View File

@ -11,7 +11,7 @@ import {
FlowNodeTemplateTypeEnum
} from '../../constants';
import { Input_Template_DynamicInput } from '../input';
import { Output_Template_AddOutput } from '../output';
import { Output_Template_AddOutput, Output_Template_Error_Message } from '../output';
import { i18nT } from '../../../../../web/i18n/utils';
export const nodeLafCustomInputConfig = {
@ -31,6 +31,7 @@ export const LafModule: FlowNodeTemplateType = {
intro: i18nT('workflow:intro_laf_function_call'),
showStatus: true,
isTool: true,
catchError: false,
courseUrl: '/docs/guide/dashboard/workflow/laf/',
inputs: [
{
@ -57,8 +58,7 @@ export const LafModule: FlowNodeTemplateType = {
valueType: WorkflowIOValueTypeEnum.any,
type: FlowNodeOutputTypeEnum.static
},
{
...Output_Template_AddOutput
}
Output_Template_AddOutput,
Output_Template_Error_Message
]
};

4
packages/global/core/workflow/template/system/readFiles/index.tsx
View File

@ -11,6 +11,7 @@ import {
FlowNodeTypeEnum
} from '../../../node/constant';
import { type FlowNodeTemplateType } from '../../../type/node';
import { Output_Template_Error_Message } from '../../output';
export const ReadFilesNode: FlowNodeTemplateType = {
id: FlowNodeTypeEnum.readFiles,
@ -43,6 +44,7 @@ export const ReadFilesNode: FlowNodeTemplateType = {
description: i18nT('app:workflow.read_files_result_desc'),
valueType: WorkflowIOValueTypeEnum.string,
type: FlowNodeOutputTypeEnum.static
}
},
Output_Template_Error_Message
]
};

16
packages/global/core/workflow/template/system/sandbox/index.ts
View File

@ -25,6 +25,7 @@ export const CodeNode: FlowNodeTemplateType = {
name: i18nT('workflow:code_execution'),
intro: i18nT('workflow:execute_a_simple_script_code_usually_for_complex_data_processing'),
showStatus: true,
catchError: false,
courseUrl: '/docs/guide/dashboard/workflow/sandbox/',
inputs: [
{
@ -89,14 +90,6 @@ export const CodeNode: FlowNodeTemplateType = {
valueType: WorkflowIOValueTypeEnum.object,
type: FlowNodeOutputTypeEnum.static
},
{
id: NodeOutputKeyEnum.error,
key: NodeOutputKeyEnum.error,
label: i18nT('workflow:execution_error'),
description: i18nT('workflow:error_info_returns_empty_on_success'),
valueType: WorkflowIOValueTypeEnum.object,
type: FlowNodeOutputTypeEnum.static
},
{
id: 'qLUQfhG0ILRX',
type: FlowNodeOutputTypeEnum.dynamic,
@ -110,6 +103,13 @@ export const CodeNode: FlowNodeTemplateType = {
key: 'data2',
valueType: WorkflowIOValueTypeEnum.string,
label: 'data2'
},
{
id: NodeOutputKeyEnum.error,
key: NodeOutputKeyEnum.error,
label: i18nT('workflow:error_text'),
valueType: WorkflowIOValueTypeEnum.string,
type: FlowNodeOutputTypeEnum.error
}
]
};

1
packages/global/core/workflow/type/node.d.ts vendored
View File

@ -48,6 +48,7 @@ export type FlowNodeCommonType = {
isLatestVersion?: boolean; // Just ui show
// data
catchError?: boolean;
inputs: FlowNodeInputItemType[];
outputs: FlowNodeOutputItemType[];

24
packages/global/core/workflow/utils.ts
View File

@ -52,7 +52,11 @@ import { ChatRoleEnum } from '../../core/chat/constants';
import { runtimePrompt2ChatsValue } from '../../core/chat/adapt';
import { getPluginRunContent } from '../../core/app/plugin/utils';
export const getHandleId = (nodeId: string, type: 'source' | 'target', key: string) => {
export const getHandleId = (
nodeId: string,
type: 'source' | 'source_catch' | 'target',
key: string
) => {
return `${nodeId}-${type}-${key}`;
};
@ -219,16 +223,14 @@ export const pluginData2FlowNodeIO = ({
]
: [],
outputs: pluginOutput
? [
...pluginOutput.inputs.map((item) => ({
id: item.key,
type: FlowNodeOutputTypeEnum.static,
key: item.key,
valueType: item.valueType,
label: item.label || item.key,
description: item.description
}))
]
? pluginOutput.inputs.map((item) => ({
id: item.key,
type: FlowNodeOutputTypeEnum.static,
key: item.key,
valueType: item.valueType,
label: item.label || item.key,
description: item.description
}))
: []
};
};

3
packages/global/support/user/audit/constants.ts
View File

@ -54,6 +54,9 @@ export enum AuditEventEnum {
UPDATE_APP_PUBLISH_CHANNEL = 'UPDATE_APP_PUBLISH_CHANNEL',
DELETE_APP_PUBLISH_CHANNEL = 'DELETE_APP_PUBLISH_CHANNEL',
EXPORT_APP_CHAT_LOG = 'EXPORT_APP_CHAT_LOG',
CREATE_EVALUATION = 'CREATE_EVALUATION',
EXPORT_EVALUATION = 'EXPORT_EVALUATION',
DELETE_EVALUATION = 'DELETE_EVALUATION',
//Dataset
CREATE_DATASET = 'CREATE_DATASET',
UPDATE_DATASET = 'UPDATE_DATASET',

6
packages/global/support/wallet/usage/constants.ts
View File

@ -12,7 +12,8 @@ export enum UsageSourceEnum {
dingtalk = 'dingtalk',
official_account = 'official_account',
pdfParse = 'pdfParse',
mcp = 'mcp'
mcp = 'mcp',
evaluation = 'evaluation'
}
export const UsageSourceMap = {
@ -51,5 +52,8 @@ export const UsageSourceMap = {
},
[UsageSourceEnum.mcp]: {
label: i18nT('account_usage:mcp')
},
[UsageSourceEnum.evaluation]: {
label: i18nT('account_usage:evaluation')
}
};

2
packages/global/support/wallet/usage/type.d.ts vendored
View File

@ -8,6 +8,7 @@ export type UsageListItemCountType = {
charsLength?: number;
duration?: number;
pages?: number;
count?: number; // Times
// deprecated
tokens?: number;
@ -17,6 +18,7 @@ export type UsageListItemType = UsageListItemCountType & {
moduleName: string;
amount: number;
model?: string;
count?: number;
};
export type UsageSchemaType = CreateUsageProps & {

1
packages/service/common/bullmq/index.ts
View File

@ -20,6 +20,7 @@ const defaultWorkerOpts: Omit<ConnectionOptions, 'connection'> = {
export enum QueueNames {
datasetSync = 'datasetSync',
evaluation = 'evaluation',
// abondoned
websiteSync = 'websiteSync'
}

4
packages/service/common/otel/trace/register.ts
View File

@ -1,13 +1,9 @@
import { registerOTel, OTLPHttpJsonTraceExporter } from '@vercel/otel';
// Add otel logging
// import { diag, DiagConsoleLogger, DiagLogLevel } from '@opentelemetry/api';
import { SignozBaseURL, SignozServiceName } from '../const';
import { addLog } from '../../system/log';
// diag.setLogger(new DiagConsoleLogger(), DiagLogLevel.INFO);
export function connectSignoz() {
if (!SignozBaseURL) {
addLog.warn('Signoz is not configured');
return;
}
addLog.info(`Connecting signoz, ${SignozBaseURL}, ${SignozServiceName}`);

30
packages/service/core/ai/config/provider/ChatGLM.json
View File

@ -15,11 +15,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -38,11 +33,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -61,11 +51,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -84,11 +69,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -106,11 +86,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -128,11 +103,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"

35
packages/service/core/ai/config/provider/Claude.json
View File

@ -14,11 +14,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -36,11 +31,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -58,11 +48,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -80,11 +65,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -102,11 +82,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -124,11 +99,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -146,11 +116,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"

10
packages/service/core/ai/config/provider/DeepSeek.json
View File

@ -15,11 +15,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"type": "llm"
},
{
@ -34,11 +29,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

75
packages/service/core/ai/config/provider/Doubao.json
View File

@ -14,11 +14,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -36,11 +31,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -58,11 +48,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -80,11 +65,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -102,11 +82,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -124,11 +99,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -146,11 +116,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -168,11 +133,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -190,11 +150,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -210,11 +165,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -232,11 +182,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -254,11 +199,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -276,11 +216,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -298,11 +233,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -320,11 +250,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

20
packages/service/core/ai/config/provider/Ernie.json
View File

@ -12,11 +12,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -34,11 +29,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -56,11 +46,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -78,11 +63,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

82
packages/service/core/ai/config/provider/Gemini.json
View File

@ -1,6 +1,38 @@
{
"provider": "Gemini",
"list": [
{
"model": "gemini-2.5-pro",
"name": "gemini-2.5-pro",
"maxContext": 1000000,
"maxResponse": 63000,
"quoteMaxToken": 1000000,
"maxTemperature": 1,
"vision": true,
"toolChoice": true,
"defaultSystemChatPrompt": "",
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
"showTopP": true,
"showStopSign": true
},
{
"model": "gemini-2.5-flash",
"name": "gemini-2.5-flash",
"maxContext": 1000000,
"maxResponse": 63000,
"quoteMaxToken": 1000000,
"maxTemperature": 1,
"vision": true,
"toolChoice": true,
"defaultSystemChatPrompt": "",
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
"showTopP": true,
"showStopSign": true
},
{
"model": "gemini-2.5-pro-exp-03-25",
"name": "gemini-2.5-pro-exp-03-25",
@ -12,11 +44,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -34,11 +61,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -56,11 +78,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -78,11 +95,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -100,11 +112,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -122,11 +129,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -144,11 +146,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -166,11 +163,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -188,11 +180,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -210,11 +197,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

52
packages/service/core/ai/config/provider/Grok.json
View File

@ -1,6 +1,38 @@
{
"provider": "Grok",
"list": [
{
"model": "grok-4",
"name": "grok-4",
"maxContext": 256000,
"maxResponse": 8000,
"quoteMaxToken": 128000,
"maxTemperature": 1,
"showTopP": true,
"showStopSign": true,
"vision": true,
"toolChoice": true,
"defaultSystemChatPrompt": "",
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
},
{
"model": "grok-4-0709",
"name": "grok-4-0709",
"maxContext": 256000,
"maxResponse": 8000,
"quoteMaxToken": 128000,
"maxTemperature": 1,
"showTopP": true,
"showStopSign": true,
"vision": true,
"toolChoice": true,
"defaultSystemChatPrompt": "",
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
},
{
"model": "grok-3-mini",
"name": "grok-3-mini",
@ -14,11 +46,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -36,11 +63,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -58,11 +80,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -80,11 +97,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"

10
packages/service/core/ai/config/provider/Groq.json
View File

@ -12,11 +12,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"type": "llm",
"showTopP": true,
@ -33,11 +28,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"type": "llm",
"showTopP": true,

35
packages/service/core/ai/config/provider/Hunyuan.json
View File

@ -12,11 +12,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -34,11 +29,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -56,11 +46,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -78,11 +63,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -100,11 +80,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -122,11 +97,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -144,11 +114,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

10
packages/service/core/ai/config/provider/Intern.json
View File

@ -12,11 +12,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -34,11 +29,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

10
packages/service/core/ai/config/provider/MiniMax.json
View File

@ -12,11 +12,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -34,11 +29,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

20
packages/service/core/ai/config/provider/MistralAI.json
View File

@ -12,11 +12,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -34,11 +29,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -56,11 +46,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -78,11 +63,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

98
packages/service/core/ai/config/provider/Moonshot.json
View File

@ -1,6 +1,74 @@
{
"provider": "Moonshot",
"list": [
{
"model": "kimi-k2-0711-preview",
"name": "kimi-k2-0711-preview",
"maxContext": 128000,
"maxResponse": 32000,
"quoteMaxToken": 128000,
"maxTemperature": 1,
"vision": false,
"toolChoice": true,
"defaultSystemChatPrompt": "",
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
"showTopP": true,
"showStopSign": true,
"responseFormatList": ["text", "json_object"]
},
{
"model": "kimi-latest-8k",
"name": "kimi-latest-8k",
"maxContext": 8000,
"maxResponse": 4000,
"quoteMaxToken": 6000,
"maxTemperature": 1,
"vision": false,
"toolChoice": true,
"defaultSystemChatPrompt": "",
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
"showTopP": true,
"showStopSign": true,
"responseFormatList": ["text", "json_object"]
},
{
"model": "kimi-latest-32k",
"name": "kimi-latest-32k",
"maxContext": 32000,
"maxResponse": 16000,
"quoteMaxToken": 32000,
"maxTemperature": 1,
"vision": false,
"toolChoice": true,
"defaultSystemChatPrompt": "",
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
"showTopP": true,
"showStopSign": true,
"responseFormatList": ["text", "json_object"]
},
{
"model": "kimi-latest-128k",
"name": "kimi-latest-128k",
"maxContext": 128000,
"maxResponse": 32000,
"quoteMaxToken": 128000,
"maxTemperature": 1,
"vision": false,
"toolChoice": true,
"defaultSystemChatPrompt": "",
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
"showTopP": true,
"showStopSign": true,
"responseFormatList": ["text", "json_object"]
},
{
"model": "moonshot-v1-8k",
"name": "moonshot-v1-8k",
@ -12,11 +80,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -35,11 +98,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -58,11 +116,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -81,11 +134,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -104,11 +152,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -127,11 +170,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

61
packages/service/core/ai/config/provider/OpenAI.json
View File

@ -15,10 +15,6 @@
"toolChoice": true,
"functionCall": true,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -37,10 +33,6 @@
"toolChoice": true,
"functionCall": true,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -59,10 +51,6 @@
"toolChoice": true,
"functionCall": true,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -81,10 +69,6 @@
"toolChoice": true,
"functionCall": true,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -103,11 +87,6 @@
"toolChoice": true,
"functionCall": true,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm"
@ -123,11 +102,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {
"max_tokens": "max_completion_tokens"
@ -147,11 +121,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {
"max_tokens": "max_completion_tokens"
@ -171,11 +140,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {
"max_tokens": "max_completion_tokens"
@ -195,11 +159,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {
"max_tokens": "max_completion_tokens"
@ -219,11 +178,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {
"max_tokens": "max_completion_tokens"
@ -243,11 +197,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {
"stream": false
},
@ -271,11 +220,6 @@
"toolChoice": true,
"functionCall": true,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"type": "llm"
},
{
@ -291,11 +235,6 @@
"toolChoice": true,
"functionCall": true,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"type": "llm"
},
{

92
packages/service/core/ai/config/provider/Qwen.json
View File

@ -12,11 +12,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -35,11 +30,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -57,11 +47,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -80,11 +65,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"type": "llm",
"showTopP": true,
"showStopSign": true
@ -100,11 +80,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -124,11 +99,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {
"stream": true
},
@ -150,11 +120,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {
"stream": true
},
@ -176,11 +141,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {
"stream": true
},
@ -202,11 +162,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {
"stream": true
},
@ -228,11 +183,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {
"stream": true
},
@ -254,11 +204,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {
"stream": true
},
@ -280,11 +225,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {
"stream": true
},
@ -306,11 +246,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {
"stream": true
},
@ -336,7 +271,6 @@
"usedInClassify": false,
"usedInExtractFields": false,
"usedInQueryExtension": false,
"usedInToolCall": true,
"defaultConfig": {
"stream": true
},
@ -361,7 +295,6 @@
"usedInClassify": false,
"usedInExtractFields": false,
"usedInQueryExtension": false,
"usedInToolCall": true,
"defaultConfig": {
"stream": true
},
@ -381,11 +314,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -403,11 +331,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -426,11 +349,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -449,11 +367,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -472,11 +385,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

10
packages/service/core/ai/config/provider/Siliconflow.json
View File

@ -12,11 +12,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -55,11 +50,6 @@
"toolChoice": true,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

30
packages/service/core/ai/config/provider/SparkDesk.json
View File

@ -9,11 +9,6 @@
"quoteMaxToken": 32000,
"maxTemperature": 1,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -29,11 +24,6 @@
"quoteMaxToken": 8000,
"maxTemperature": 1,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -49,11 +39,6 @@
"quoteMaxToken": 128000,
"maxTemperature": 1,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -69,11 +54,6 @@
"quoteMaxToken": 8000,
"maxTemperature": 1,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -92,11 +72,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -114,11 +89,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

55
packages/service/core/ai/config/provider/StepFun.json
View File

@ -9,11 +9,6 @@
"quoteMaxToken": 6000,
"maxTemperature": 2,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -29,11 +24,6 @@
"quoteMaxToken": 8000,
"maxTemperature": 2,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -49,11 +39,6 @@
"quoteMaxToken": 32000,
"maxTemperature": 2,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -69,11 +54,6 @@
"quoteMaxToken": 128000,
"maxTemperature": 2,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -89,11 +69,6 @@
"quoteMaxToken": 256000,
"maxTemperature": 2,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -109,11 +84,6 @@
"maxResponse": 8000,
"maxTemperature": 2,
"vision": true,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -129,11 +99,6 @@
"quoteMaxToken": 8000,
"maxTemperature": 2,
"vision": true,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -149,11 +114,6 @@
"maxResponse": 8000,
"maxTemperature": 2,
"vision": true,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -169,11 +129,6 @@
"quoteMaxToken": 6000,
"maxTemperature": 2,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -189,11 +144,6 @@
"quoteMaxToken": 4000,
"maxTemperature": 2,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
@ -209,11 +159,6 @@
"quoteMaxToken": 4000,
"maxTemperature": 2,
"vision": false,
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInToolCall": true,
"usedInQueryExtension": true,
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",

10
packages/service/core/ai/config/provider/Yi.json
View File

@ -12,11 +12,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",
@ -34,11 +29,6 @@
"toolChoice": false,
"functionCall": false,
"defaultSystemChatPrompt": "",
"datasetProcess": true,
"usedInClassify": true,
"usedInExtractFields": true,
"usedInQueryExtension": true,
"usedInToolCall": true,
"defaultConfig": {},
"fieldMap": {},
"type": "llm",

9
packages/service/core/ai/config/utils.ts
View File

@ -43,6 +43,15 @@ export const loadSystemModels = async (init = false) => {
const pushModel = (model: SystemModelItemType) => {
global.systemModelList.push(model);
// Add default value
if (model.type === ModelTypeEnum.llm) {
model.datasetProcess = model.datasetProcess ?? true;
model.usedInClassify = model.usedInClassify ?? true;
model.usedInExtractFields = model.usedInExtractFields ?? true;
model.usedInToolCall = model.usedInToolCall ?? true;
model.useInEvaluation = model.useInEvaluation ?? true;
}
if (model.isActive) {
global.systemActiveModelList.push(model);

10
packages/service/core/ai/model.ts
View File

@ -14,15 +14,15 @@ export const getDatasetModel = (model?: string) => {
?.find((item) => item.model === model || item.name === model) ?? getDefaultLLMModel()
);
};
export const getVlmModel = (model?: string) => {
return Array.from(global.llmModelMap.values())
?.filter((item) => item.vision)
?.find((item) => item.model === model || item.name === model);
};
export const getVlmModelList = () => {
return Array.from(global.llmModelMap.values())?.filter((item) => item.vision) || [];
};
export const getDefaultVLMModel = () => global?.systemDefaultModel.datasetImageLLM;
export const getVlmModel = (model?: string) => {
const list = getVlmModelList();
return list.find((item) => item.model === model || item.name === model) || list[0];
};
export const getDefaultEmbeddingModel = () => global?.systemDefaultModel.embedding!;
export const getEmbeddingModel = (model?: string) => {

56
packages/service/core/app/evaluation/evalItemSchema.ts Normal file
View File

@ -0,0 +1,56 @@
import { connectionMongo, getMongoModel } from '../../../common/mongo';
import { EvaluationCollectionName } from './evalSchema';
import {
EvaluationStatusEnum,
EvaluationStatusValues
} from '@fastgpt/global/core/app/evaluation/constants';
import type { EvalItemSchemaType } from '@fastgpt/global/core/app/evaluation/type';
const { Schema } = connectionMongo;
export const EvalItemCollectionName = 'eval_items';
const EvalItemSchema = new Schema({
evalId: {
type: Schema.Types.ObjectId,
ref: EvaluationCollectionName,
required: true
},
question: {
type: String,
required: true
},
expectedResponse: {
type: String,
required: true
},
history: String,
globalVariables: Object,
response: String,
responseTime: Date,
status: {
type: Number,
default: EvaluationStatusEnum.queuing,
enum: EvaluationStatusValues
},
retry: {
type: Number,
default: 3
},
finishTime: Date,
accuracy: Number,
relevance: Number,
semanticAccuracy: Number,
score: Number, // average score
errorMessage: String
});
EvalItemSchema.index({ evalId: 1, status: 1 });
export const MongoEvalItem = getMongoModel<EvalItemSchemaType>(
EvalItemCollectionName,
EvalItemSchema
);

57
packages/service/core/app/evaluation/evalSchema.ts Normal file
View File

@ -0,0 +1,57 @@
import {
TeamCollectionName,
TeamMemberCollectionName
} from '@fastgpt/global/support/user/team/constant';
import { connectionMongo, getMongoModel } from '../../../common/mongo';
import { AppCollectionName } from '../schema';
import type { EvaluationSchemaType } from '@fastgpt/global/core/app/evaluation/type';
import { UsageCollectionName } from '../../../support/wallet/usage/schema';
const { Schema } = connectionMongo;
export const EvaluationCollectionName = 'eval';
const EvaluationSchema = new Schema({
teamId: {
type: Schema.Types.ObjectId,
ref: TeamCollectionName,
required: true
},
tmbId: {
type: Schema.Types.ObjectId,
ref: TeamMemberCollectionName,
required: true
},
appId: {
type: Schema.Types.ObjectId,
ref: AppCollectionName,
required: true
},
usageId: {
type: Schema.Types.ObjectId,
ref: UsageCollectionName,
required: true
},
evalModel: {
type: String,
required: true
},
name: {
type: String,
required: true
},
createTime: {
type: Date,
required: true,
default: () => new Date()
},
finishTime: Date,
score: Number,
errorMessage: String
});
EvaluationSchema.index({ teamId: 1 });
export const MongoEvaluation = getMongoModel<EvaluationSchemaType>(
EvaluationCollectionName,
EvaluationSchema
);

80
packages/service/core/app/evaluation/mq.ts Normal file
View File

@ -0,0 +1,80 @@
import { getQueue, getWorker, QueueNames } from '../../../common/bullmq';
import { type Processor } from 'bullmq';
import { addLog } from '../../../common/system/log';
export type EvaluationJobData = {
evalId: string;
};
export const evaluationQueue = getQueue<EvaluationJobData>(QueueNames.evaluation, {
defaultJobOptions: {
attempts: 3,
backoff: {
type: 'exponential',
delay: 1000
}
}
});
const concurrency = process.env.EVAL_CONCURRENCY ? Number(process.env.EVAL_CONCURRENCY) : 3;
export const getEvaluationWorker = (processor: Processor<EvaluationJobData>) => {
return getWorker<EvaluationJobData>(QueueNames.evaluation, processor, {
removeOnFail: {
count: 1000 // Keep last 1000 failed jobs
},
concurrency: concurrency
});
};
export const addEvaluationJob = (data: EvaluationJobData) => {
const evalId = String(data.evalId);
return evaluationQueue.add(evalId, data, { deduplication: { id: evalId } });
};
export const checkEvaluationJobActive = async (evalId: string): Promise<boolean> => {
try {
const jobId = await evaluationQueue.getDeduplicationJobId(String(evalId));
if (!jobId) return false;
const job = await evaluationQueue.getJob(jobId);
if (!job) return false;
const jobState = await job.getState();
return ['waiting', 'delayed', 'prioritized', 'active'].includes(jobState);
} catch (error) {
addLog.error('Failed to check evaluation job status', { evalId, error });
return false;
}
};
export const removeEvaluationJob = async (evalId: string): Promise<boolean> => {
const formatEvalId = String(evalId);
try {
const jobId = await evaluationQueue.getDeduplicationJobId(formatEvalId);
if (!jobId) {
addLog.warn('No job found to remove', { evalId });
return false;
}
const job = await evaluationQueue.getJob(jobId);
if (!job) {
addLog.warn('Job not found in queue', { evalId, jobId });
return false;
}
const jobState = await job.getState();
if (['waiting', 'delayed', 'prioritized'].includes(jobState)) {
await job.remove();
addLog.info('Evaluation job removed successfully', { evalId, jobId, jobState });
return true;
} else {
addLog.warn('Cannot remove active or completed job', { evalId, jobId, jobState });
return false;
}
} catch (error) {
addLog.error('Failed to remove evaluation job', { evalId, error });
return false;
}
};

45
packages/service/core/app/plugin/controller.ts
View File

@ -1,5 +1,8 @@
import { type FlowNodeTemplateType } from '@fastgpt/global/core/workflow/type/node.d';
import { FlowNodeTypeEnum } from '@fastgpt/global/core/workflow/node/constant';
import {
FlowNodeOutputTypeEnum,
FlowNodeTypeEnum
} from '@fastgpt/global/core/workflow/node/constant';
import {
appData2FlowNodeIO,
pluginData2FlowNodeIO,
@ -33,6 +36,7 @@ import type {
FlowNodeOutputItemType
} from '@fastgpt/global/core/workflow/type/io';
import { isProduction } from '@fastgpt/global/common/system/constants';
import { Output_Template_Error_Message } from '@fastgpt/global/core/workflow/template/output';
/**
plugin id rule:
@ -122,15 +126,24 @@ export const getSystemPluginByIdAndVersionId = async (
};
}
// System tool
const versionList = (plugin.versionList as SystemPluginTemplateItemType['versionList']) || [];
if (versionList.length === 0) {
return Promise.reject('Can not find plugin version list');
}
const version = versionId
? plugin.versionList?.find((item) => item.value === versionId)
: plugin.versionList?.[0];
const lastVersion = plugin.versionList?.[0];
? versionList.find((item) => item.value === versionId) ?? versionList[0]
: versionList[0];
const lastVersion = versionList[0];
return {
...plugin,
inputs: version.inputs,
outputs: version.outputs,
version: versionId ? version?.value : '',
versionLabel: version ? version?.value : '',
versionLabel: versionId ? version?.value : '',
isLatestVersion: !version || !lastVersion || version.value === lastVersion?.value
};
})();
@ -198,8 +211,8 @@ export async function getChildAppPreviewNode({
return {
flowNodeType: FlowNodeTypeEnum.tool,
nodeIOConfig: {
inputs: app.inputs!,
outputs: app.outputs!,
inputs: app.inputs || [],
outputs: app.outputs || [],
toolConfig: {
systemTool: {
toolId: app.id
@ -209,6 +222,7 @@ export async function getChildAppPreviewNode({
};
}
// Plugin workflow
if (!!app.workflow.nodes.find((node) => node.flowNodeType === FlowNodeTypeEnum.pluginInput)) {
return {
flowNodeType: FlowNodeTypeEnum.pluginModule,
@ -216,6 +230,7 @@ export async function getChildAppPreviewNode({
};
}
// Mcp
if (
!!app.workflow.nodes.find((node) => node.flowNodeType === FlowNodeTypeEnum.toolSet) &&
app.workflow.nodes.length === 1
@ -236,6 +251,7 @@ export async function getChildAppPreviewNode({
};
}
// Chat workflow
return {
flowNodeType: FlowNodeTypeEnum.appModule,
nodeIOConfig: appData2FlowNodeIO({ chatConfig: app.workflow.chatConfig })
@ -254,6 +270,7 @@ export async function getChildAppPreviewNode({
userGuide: app.userGuide,
showStatus: true,
isTool: true,
catchError: false,
version: app.version,
versionLabel: app.versionLabel,
@ -265,7 +282,10 @@ export async function getChildAppPreviewNode({
hasTokenFee: app.hasTokenFee,
hasSystemSecret: app.hasSystemSecret,
...nodeIOConfig
...nodeIOConfig,
outputs: nodeIOConfig.outputs.some((item) => item.type === FlowNodeOutputTypeEnum.error)
? nodeIOConfig.outputs
: [...nodeIOConfig.outputs, Output_Template_Error_Message]
};
}
@ -414,8 +434,9 @@ export const getSystemPlugins = async (): Promise<SystemPluginTemplateItemType[]
const formatTools = tools.map<SystemPluginTemplateItemType>((item) => {
const dbPluginConfig = systemPlugins.get(item.id);
const inputs = item.versionList[0]?.inputs as FlowNodeInputItemType[];
const outputs = item.versionList[0]?.outputs as FlowNodeOutputItemType[];
const versionList = (item.versionList as SystemPluginTemplateItemType['versionList']) || [];
const inputs = versionList[0]?.inputs;
return {
isActive: item.isActive,
@ -439,9 +460,7 @@ export const getSystemPlugins = async (): Promise<SystemPluginTemplateItemType[]
nodes: [],
edges: []
},
versionList: item.versionList,
inputs,
outputs,
versionList,
inputList: inputs?.find((input) => input.key === NodeInputKeyEnum.systemInputConfig)
?.inputList as any,

3
packages/service/core/app/plugin/systemPluginSchema.ts
View File

@ -25,8 +25,7 @@ const SystemPluginSchema = new Schema({
default: false
},
pluginOrder: {
type: Number,
default: 0
type: Number
},
customConfig: Object,
inputListVal: Object,

2
packages/service/core/app/plugin/type.d.ts vendored
View File

@ -9,7 +9,7 @@ export type SystemPluginConfigSchemaType = {
currentCost: number;
hasTokenFee: boolean;
isActive: boolean;
pluginOrder: number;
pluginOrder?: number;
customConfig?: {
name: string;

22
packages/service/core/app/utils.ts
View File

@ -79,6 +79,28 @@ export async function rewriteAppWorkflowToDetail({
node.currentCost = preview.currentCost;
node.hasTokenFee = preview.hasTokenFee;
node.hasSystemSecret = preview.hasSystemSecret;
// Latest version
if (!node.version) {
const inputsMap = new Map(node.inputs.map((item) => [item.key, item]));
const outputsMap = new Map(node.outputs.map((item) => [item.key, item]));
node.inputs = preview.inputs.map((item) => {
const input = inputsMap.get(item.key);
return {
...item,
value: input?.value,
selectedTypeIndex: input?.selectedTypeIndex
};
});
node.outputs = preview.outputs.map((item) => {
const output = outputsMap.get(item.key);
return {
...item,
value: output?.value
};
});
}
} catch (error) {
node.pluginData = {
error: getErrText(error)

2
packages/service/core/chat/saveChat.ts
View File

@ -166,7 +166,7 @@ export async function saveChat({
if (isUpdateUseTime) {
await MongoApp.findByIdAndUpdate(appId, {
updateTime: new Date()
});
}).catch();
}
} catch (error) {
addLog.error(`update chat history error`, error);

8
packages/service/core/workflow/dispatch/abandoned/runApp.ts
View File

@ -95,6 +95,10 @@ export const dispatchAppRequest = async (props: Props): Promise<Response> => {
const { text } = chatValue2RuntimePrompt(assistantResponses);
return {
data: {
answerText: text,
history: completeMessages
},
assistantResponses,
system_memories,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
@ -108,8 +112,6 @@ export const dispatchAppRequest = async (props: Props): Promise<Response> => {
moduleName: appData.name,
totalPoints: flowUsages.reduce((sum, item) => sum + (item.totalPoints || 0), 0)
}
],
answerText: text,
history: completeMessages
]
};
};

431
packages/service/core/workflow/dispatch/ai/agent/index.ts
View File

@ -6,7 +6,7 @@ import type {
RuntimeNodeItemType
} from '@fastgpt/global/core/workflow/runtime/type';
import { getLLMModel } from '../../../../ai/model';
import { filterToolNodeIdByEdges, getHistories } from '../../utils';
import { filterToolNodeIdByEdges, getNodeErrResponse, getHistories } from '../../utils';
import { runToolWithToolChoice } from './toolChoice';
import { type DispatchToolModuleProps, type ToolNodeItemType } from './type';
import { type ChatItemType, type UserChatItemValueItemType } from '@fastgpt/global/core/chat/type';
@ -25,7 +25,6 @@ import { runToolWithPromptCall } from './promptCall';
import { replaceVariable } from '@fastgpt/global/common/string/tools';
import { getMultiplePrompt, Prompt_Tool_Call } from './constants';
import { filterToolResponseToPreview } from './utils';
import { type InteractiveNodeResponseType } from '@fastgpt/global/core/workflow/template/system/interactive/type';
import { getFileContentFromLinks, getHistoryFileLinks } from '../../tools/readFiles';
import { parseUrlToFileType } from '@fastgpt/global/common/file/tools';
import { FlowNodeTypeEnum } from '@fastgpt/global/core/workflow/node/constant';
@ -38,7 +37,6 @@ import type { JSONSchemaInputType } from '@fastgpt/global/core/app/jsonschema';
type Response = DispatchNodeResultType<{
[NodeOutputKeyEnum.answerText]: string;
[DispatchNodeResponseKeyEnum.interactive]?: InteractiveNodeResponseType;
}>;
export const dispatchRunTools = async (props: DispatchToolModuleProps): Promise<Response> => {
@ -64,244 +62,249 @@ export const dispatchRunTools = async (props: DispatchToolModuleProps): Promise<
}
} = props;
const toolModel = getLLMModel(model);
const useVision = aiChatVision && toolModel.vision;
const chatHistories = getHistories(history, histories);
try {
const toolModel = getLLMModel(model);
const useVision = aiChatVision && toolModel.vision;
const chatHistories = getHistories(history, histories);
props.params.aiChatVision = aiChatVision && toolModel.vision;
props.params.aiChatReasoning = aiChatReasoning && toolModel.reasoning;
const fileUrlInput = inputs.find((item) => item.key === NodeInputKeyEnum.fileUrlList);
if (!fileUrlInput || !fileUrlInput.value || fileUrlInput.value.length === 0) {
fileLinks = undefined;
}
console.log(fileLinks, 22);
props.params.aiChatVision = aiChatVision && toolModel.vision;
props.params.aiChatReasoning = aiChatReasoning && toolModel.reasoning;
const fileUrlInput = inputs.find((item) => item.key === NodeInputKeyEnum.fileUrlList);
if (!fileUrlInput || !fileUrlInput.value || fileUrlInput.value.length === 0) {
fileLinks = undefined;
}
const toolNodeIds = filterToolNodeIdByEdges({ nodeId, edges: runtimeEdges });
const toolNodeIds = filterToolNodeIdByEdges({ nodeId, edges: runtimeEdges });
// Gets the module to which the tool is connected
const toolNodes = toolNodeIds
.map((nodeId) => {
const tool = runtimeNodes.find((item) => item.nodeId === nodeId);
return tool;
})
.filter(Boolean)
.map<ToolNodeItemType>((tool) => {
const toolParams: FlowNodeInputItemType[] = [];
// Raw json schema(MCP tool)
let jsonSchema: JSONSchemaInputType | undefined = undefined;
tool?.inputs.forEach((input) => {
if (input.toolDescription) {
toolParams.push(input);
}
// Gets the module to which the tool is connected
const toolNodes = toolNodeIds
.map((nodeId) => {
const tool = runtimeNodes.find((item) => item.nodeId === nodeId);
return tool;
})
.filter(Boolean)
.map<ToolNodeItemType>((tool) => {
const toolParams: FlowNodeInputItemType[] = [];
// Raw json schema(MCP tool)
let jsonSchema: JSONSchemaInputType | undefined = undefined;
tool?.inputs.forEach((input) => {
if (input.toolDescription) {
toolParams.push(input);
}
if (input.key === NodeInputKeyEnum.toolData || input.key === 'toolData') {
const value = input.value as McpToolDataType;
jsonSchema = value.inputSchema;
}
if (input.key === NodeInputKeyEnum.toolData || input.key === 'toolData') {
const value = input.value as McpToolDataType;
jsonSchema = value.inputSchema;
}
});
return {
...(tool as RuntimeNodeItemType),
toolParams,
jsonSchema
};
});
return {
...(tool as RuntimeNodeItemType),
toolParams,
jsonSchema
};
// Check interactive entry
props.node.isEntry = false;
const hasReadFilesTool = toolNodes.some(
(item) => item.flowNodeType === FlowNodeTypeEnum.readFiles
);
const globalFiles = chatValue2RuntimePrompt(query).files;
const { documentQuoteText, userFiles } = await getMultiInput({
runningUserInfo,
histories: chatHistories,
requestOrigin,
maxFiles: chatConfig?.fileSelectConfig?.maxFiles || 20,
customPdfParse: chatConfig?.fileSelectConfig?.customPdfParse,
fileLinks,
inputFiles: globalFiles,
hasReadFilesTool
});
// Check interactive entry
props.node.isEntry = false;
const hasReadFilesTool = toolNodes.some(
(item) => item.flowNodeType === FlowNodeTypeEnum.readFiles
);
const globalFiles = chatValue2RuntimePrompt(query).files;
const { documentQuoteText, userFiles } = await getMultiInput({
runningUserInfo,
histories: chatHistories,
requestOrigin,
maxFiles: chatConfig?.fileSelectConfig?.maxFiles || 20,
customPdfParse: chatConfig?.fileSelectConfig?.customPdfParse,
fileLinks,
inputFiles: globalFiles,
hasReadFilesTool
});
const concatenateSystemPrompt = [
toolModel.defaultSystemChatPrompt,
systemPrompt,
documentQuoteText
? replaceVariable(getDocumentQuotePrompt(version), {
quote: documentQuoteText
})
: ''
]
.filter(Boolean)
.join('\n\n===---===---===\n\n');
const messages: ChatItemType[] = (() => {
const value: ChatItemType[] = [
...getSystemPrompt_ChatItemType(concatenateSystemPrompt),
// Add file input prompt to histories
...chatHistories.map((item) => {
if (item.obj === ChatRoleEnum.Human) {
return {
...item,
value: toolCallMessagesAdapt({
userInput: item.value,
skip: !hasReadFilesTool
})
};
}
return item;
}),
{
obj: ChatRoleEnum.Human,
value: toolCallMessagesAdapt({
skip: !hasReadFilesTool,
userInput: runtimePrompt2ChatsValue({
text: userChatInput,
files: userFiles
const concatenateSystemPrompt = [
toolModel.defaultSystemChatPrompt,
systemPrompt,
documentQuoteText
? replaceVariable(getDocumentQuotePrompt(version), {
quote: documentQuoteText
})
})
}
];
if (lastInteractive && isEntry) {
return value.slice(0, -2);
}
return value;
})();
: ''
]
.filter(Boolean)
.join('\n\n===---===---===\n\n');
// censor model and system key
if (toolModel.censor && !externalProvider.openaiAccount?.key) {
await postTextCensor({
text: `${systemPrompt}
const messages: ChatItemType[] = (() => {
const value: ChatItemType[] = [
...getSystemPrompt_ChatItemType(concatenateSystemPrompt),
// Add file input prompt to histories
...chatHistories.map((item) => {
if (item.obj === ChatRoleEnum.Human) {
return {
...item,
value: toolCallMessagesAdapt({
userInput: item.value,
skip: !hasReadFilesTool
})
};
}
return item;
}),
{
obj: ChatRoleEnum.Human,
value: toolCallMessagesAdapt({
skip: !hasReadFilesTool,
userInput: runtimePrompt2ChatsValue({
text: userChatInput,
files: userFiles
})
})
}
];
if (lastInteractive && isEntry) {
return value.slice(0, -2);
}
return value;
})();
// censor model and system key
if (toolModel.censor && !externalProvider.openaiAccount?.key) {
await postTextCensor({
text: `${systemPrompt}
${userChatInput}
`
});
}
const {
toolWorkflowInteractiveResponse,
dispatchFlowResponse, // tool flow response
toolNodeInputTokens,
toolNodeOutputTokens,
completeMessages = [], // The actual message sent to AI(just save text)
assistantResponses = [], // FastGPT system store assistant.value response
runTimes,
finish_reason
} = await (async () => {
const adaptMessages = chats2GPTMessages({
messages,
reserveId: false
// reserveTool: !!toolModel.toolChoice
});
const requestParams = {
runtimeNodes,
runtimeEdges,
toolNodes,
toolModel,
messages: adaptMessages,
interactiveEntryToolParams: lastInteractive?.toolParams
};
if (toolModel.toolChoice) {
return runToolWithToolChoice({
...props,
...requestParams,
maxRunToolTimes: 30
});
}
if (toolModel.functionCall) {
return runToolWithFunctionCall({
...props,
...requestParams
});
}
const lastMessage = adaptMessages[adaptMessages.length - 1];
if (typeof lastMessage?.content === 'string') {
lastMessage.content = replaceVariable(Prompt_Tool_Call, {
question: lastMessage.content
const {
toolWorkflowInteractiveResponse,
dispatchFlowResponse, // tool flow response
toolNodeInputTokens,
toolNodeOutputTokens,
completeMessages = [], // The actual message sent to AI(just save text)
assistantResponses = [], // FastGPT system store assistant.value response
runTimes,
finish_reason
} = await (async () => {
const adaptMessages = chats2GPTMessages({
messages,
reserveId: false
// reserveTool: !!toolModel.toolChoice
});
} else if (Array.isArray(lastMessage.content)) {
// array, replace last element
const lastText = lastMessage.content[lastMessage.content.length - 1];
if (lastText.type === 'text') {
lastText.text = replaceVariable(Prompt_Tool_Call, {
question: lastText.text
const requestParams = {
runtimeNodes,
runtimeEdges,
toolNodes,
toolModel,
messages: adaptMessages,
interactiveEntryToolParams: lastInteractive?.toolParams
};
if (toolModel.toolChoice) {
return runToolWithToolChoice({
...props,
...requestParams,
maxRunToolTimes: 30
});
}
if (toolModel.functionCall) {
return runToolWithFunctionCall({
...props,
...requestParams
});
}
const lastMessage = adaptMessages[adaptMessages.length - 1];
if (typeof lastMessage?.content === 'string') {
lastMessage.content = replaceVariable(Prompt_Tool_Call, {
question: lastMessage.content
});
} else if (Array.isArray(lastMessage.content)) {
// array, replace last element
const lastText = lastMessage.content[lastMessage.content.length - 1];
if (lastText.type === 'text') {
lastText.text = replaceVariable(Prompt_Tool_Call, {
question: lastText.text
});
} else {
return Promise.reject('Prompt call invalid input');
}
} else {
return Promise.reject('Prompt call invalid input');
}
} else {
return Promise.reject('Prompt call invalid input');
}
return runToolWithPromptCall({
...props,
...requestParams
return runToolWithPromptCall({
...props,
...requestParams
});
})();
const { totalPoints, modelName } = formatModelChars2Points({
model,
inputTokens: toolNodeInputTokens,
outputTokens: toolNodeOutputTokens,
modelType: ModelTypeEnum.llm
});
})();
const toolAIUsage = externalProvider.openaiAccount?.key ? 0 : totalPoints;
const { totalPoints, modelName } = formatModelChars2Points({
model,
inputTokens: toolNodeInputTokens,
outputTokens: toolNodeOutputTokens,
modelType: ModelTypeEnum.llm
});
const toolAIUsage = externalProvider.openaiAccount?.key ? 0 : totalPoints;
// flat child tool response
const childToolResponse = dispatchFlowResponse.map((item) => item.flowResponses).flat();
// flat child tool response
const childToolResponse = dispatchFlowResponse.map((item) => item.flowResponses).flat();
// concat tool usage
const totalPointsUsage =
toolAIUsage +
dispatchFlowResponse.reduce((sum, item) => {
const childrenTotal = item.flowUsages.reduce((sum, item) => sum + item.totalPoints, 0);
return sum + childrenTotal;
}, 0);
const flatUsages = dispatchFlowResponse.map((item) => item.flowUsages).flat();
// concat tool usage
const totalPointsUsage =
toolAIUsage +
dispatchFlowResponse.reduce((sum, item) => {
const childrenTotal = item.flowUsages.reduce((sum, item) => sum + item.totalPoints, 0);
return sum + childrenTotal;
}, 0);
const flatUsages = dispatchFlowResponse.map((item) => item.flowUsages).flat();
const previewAssistantResponses = filterToolResponseToPreview(assistantResponses);
const previewAssistantResponses = filterToolResponseToPreview(assistantResponses);
return {
[DispatchNodeResponseKeyEnum.runTimes]: runTimes,
[NodeOutputKeyEnum.answerText]: previewAssistantResponses
.filter((item) => item.text?.content)
.map((item) => item.text?.content || '')
.join(''),
[DispatchNodeResponseKeyEnum.assistantResponses]: previewAssistantResponses,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
// 展示的积分消耗
totalPoints: totalPointsUsage,
toolCallInputTokens: toolNodeInputTokens,
toolCallOutputTokens: toolNodeOutputTokens,
childTotalPoints: flatUsages.reduce((sum, item) => sum + item.totalPoints, 0),
model: modelName,
query: userChatInput,
historyPreview: getHistoryPreview(
GPTMessages2Chats(completeMessages, false),
10000,
useVision
),
toolDetail: childToolResponse,
mergeSignId: nodeId,
finishReason: finish_reason
},
[DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
// 工具调用本身的积分消耗
{
moduleName: name,
model: modelName,
totalPoints: toolAIUsage,
inputTokens: toolNodeInputTokens,
outputTokens: toolNodeOutputTokens
return {
data: {
[NodeOutputKeyEnum.answerText]: previewAssistantResponses
.filter((item) => item.text?.content)
.map((item) => item.text?.content || '')
.join('')
},
// 工具的消耗
...flatUsages
],
[DispatchNodeResponseKeyEnum.interactive]: toolWorkflowInteractiveResponse
};
[DispatchNodeResponseKeyEnum.runTimes]: runTimes,
[DispatchNodeResponseKeyEnum.assistantResponses]: previewAssistantResponses,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
// 展示的积分消耗
totalPoints: totalPointsUsage,
toolCallInputTokens: toolNodeInputTokens,
toolCallOutputTokens: toolNodeOutputTokens,
childTotalPoints: flatUsages.reduce((sum, item) => sum + item.totalPoints, 0),
model: modelName,
query: userChatInput,
historyPreview: getHistoryPreview(
GPTMessages2Chats(completeMessages, false),
10000,
useVision
),
toolDetail: childToolResponse,
mergeSignId: nodeId,
finishReason: finish_reason
},
[DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
// 工具调用本身的积分消耗
{
moduleName: name,
model: modelName,
totalPoints: toolAIUsage,
inputTokens: toolNodeInputTokens,
outputTokens: toolNodeOutputTokens
},
// 工具的消耗
...flatUsages
],
[DispatchNodeResponseKeyEnum.interactive]: toolWorkflowInteractiveResponse
};
} catch (error) {
return getNodeErrResponse({ error });
}
};
const getMultiInput = async ({

463
packages/service/core/workflow/dispatch/ai/chat.ts
View File

@ -17,10 +17,7 @@ import type {
} from '@fastgpt/global/core/ai/type.d';
import { formatModelChars2Points } from '../../../../support/wallet/usage/utils';
import type { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
import {
ChatCompletionRequestMessageRoleEnum,
getLLMDefaultUsage
} from '@fastgpt/global/core/ai/constants';
import { ChatCompletionRequestMessageRoleEnum } from '@fastgpt/global/core/ai/constants';
import type {
ChatDispatchProps,
DispatchNodeResultType
@ -47,7 +44,7 @@ import type { SearchDataResponseItemType } from '@fastgpt/global/core/dataset/ty
import type { NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
import { NodeInputKeyEnum } from '@fastgpt/global/core/workflow/constants';
import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
import { checkQuoteQAValue, getHistories } from '../utils';
import { checkQuoteQAValue, getNodeErrResponse, getHistories } from '../utils';
import { filterSearchResultsByMaxChars } from '../../utils';
import { getHistoryPreview } from '@fastgpt/global/core/chat/utils';
import { computedMaxToken, llmCompletionsBodyFormat } from '../../../ai/utils';
@ -59,6 +56,7 @@ import { parseUrlToFileType } from '@fastgpt/global/common/file/tools';
import { i18nT } from '../../../../../web/i18n/utils';
import { ModelTypeEnum } from '@fastgpt/global/core/ai/model';
import { postTextCensor } from '../../../chat/postTextCensor';
import { getErrText } from '@fastgpt/global/common/error/utils';
export type ChatProps = ModuleDispatchProps<
AIChatNodeProps & {
@ -67,11 +65,16 @@ export type ChatProps = ModuleDispatchProps<
[NodeInputKeyEnum.aiChatDatasetQuote]?: SearchDataResponseItemType[];
}
>;
export type ChatResponse = DispatchNodeResultType<{
[NodeOutputKeyEnum.answerText]: string;
[NodeOutputKeyEnum.reasoningText]?: string;
[NodeOutputKeyEnum.history]: ChatItemType[];
}>;
export type ChatResponse = DispatchNodeResultType<
{
[NodeOutputKeyEnum.answerText]: string;
[NodeOutputKeyEnum.reasoningText]?: string;
[NodeOutputKeyEnum.history]: ChatItemType[];
},
{
[NodeOutputKeyEnum.errorText]: string;
}
>;
/* request openai chat */
export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResponse> => {
@ -114,243 +117,253 @@ export const dispatchChatCompletion = async (props: ChatProps): Promise<ChatResp
const modelConstantsData = getLLMModel(model);
if (!modelConstantsData) {
return Promise.reject(`Mode ${model} is undefined, you need to select a chat model.`);
return getNodeErrResponse({
error: `Model ${model} is undefined, you need to select a chat model.`
});
}
aiChatVision = modelConstantsData.vision && aiChatVision;
aiChatReasoning = !!aiChatReasoning && !!modelConstantsData.reasoning;
// Check fileLinks is reference variable
const fileUrlInput = inputs.find((item) => item.key === NodeInputKeyEnum.fileUrlList);
if (!fileUrlInput || !fileUrlInput.value || fileUrlInput.value.length === 0) {
fileLinks = undefined;
}
try {
aiChatVision = modelConstantsData.vision && aiChatVision;
aiChatReasoning = !!aiChatReasoning && !!modelConstantsData.reasoning;
// Check fileLinks is reference variable
const fileUrlInput = inputs.find((item) => item.key === NodeInputKeyEnum.fileUrlList);
if (!fileUrlInput || !fileUrlInput.value || fileUrlInput.value.length === 0) {
fileLinks = undefined;
}
const chatHistories = getHistories(history, histories);
quoteQA = checkQuoteQAValue(quoteQA);
const chatHistories = getHistories(history, histories);
quoteQA = checkQuoteQAValue(quoteQA);
const [{ datasetQuoteText }, { documentQuoteText, userFiles }] = await Promise.all([
filterDatasetQuote({
quoteQA,
const [{ datasetQuoteText }, { documentQuoteText, userFiles }] = await Promise.all([
filterDatasetQuote({
quoteQA,
model: modelConstantsData,
quoteTemplate: quoteTemplate || getQuoteTemplate(version)
}),
getMultiInput({
histories: chatHistories,
inputFiles,
fileLinks,
stringQuoteText,
requestOrigin,
maxFiles: chatConfig?.fileSelectConfig?.maxFiles || 20,
customPdfParse: chatConfig?.fileSelectConfig?.customPdfParse,
runningUserInfo
})
]);
if (!userChatInput && !documentQuoteText && userFiles.length === 0) {
return getNodeErrResponse({ error: i18nT('chat:AI_input_is_empty') });
}
const max_tokens = computedMaxToken({
model: modelConstantsData,
quoteTemplate: quoteTemplate || getQuoteTemplate(version)
}),
getMultiInput({
histories: chatHistories,
inputFiles,
fileLinks,
stringQuoteText,
requestOrigin,
maxFiles: chatConfig?.fileSelectConfig?.maxFiles || 20,
customPdfParse: chatConfig?.fileSelectConfig?.customPdfParse,
runningUserInfo
})
]);
maxToken
});
if (!userChatInput && !documentQuoteText && userFiles.length === 0) {
return Promise.reject(i18nT('chat:AI_input_is_empty'));
}
const max_tokens = computedMaxToken({
model: modelConstantsData,
maxToken
});
const [{ filterMessages }] = await Promise.all([
getChatMessages({
model: modelConstantsData,
maxTokens: max_tokens,
histories: chatHistories,
useDatasetQuote: quoteQA !== undefined,
datasetQuoteText,
aiChatQuoteRole,
datasetQuotePrompt: quotePrompt,
version,
userChatInput,
systemPrompt,
userFiles,
documentQuoteText
}),
// Censor = true and system key, will check content
(() => {
if (modelConstantsData.censor && !externalProvider.openaiAccount?.key) {
return postTextCensor({
text: `${systemPrompt}
const [{ filterMessages }] = await Promise.all([
getChatMessages({
model: modelConstantsData,
maxTokens: max_tokens,
histories: chatHistories,
useDatasetQuote: quoteQA !== undefined,
datasetQuoteText,
aiChatQuoteRole,
datasetQuotePrompt: quotePrompt,
version,
userChatInput,
systemPrompt,
userFiles,
documentQuoteText
}),
// Censor = true and system key, will check content
(() => {
if (modelConstantsData.censor && !externalProvider.openaiAccount?.key) {
return postTextCensor({
text: `${systemPrompt}
${userChatInput}
`
});
});
}
})()
]);
const requestMessages = await loadRequestMessages({
messages: filterMessages,
useVision: aiChatVision,
origin: requestOrigin
});
const requestBody = llmCompletionsBodyFormat(
{
model: modelConstantsData.model,
stream,
messages: requestMessages,
temperature,
max_tokens,
top_p: aiChatTopP,
stop: aiChatStopSign,
response_format: {
type: aiChatResponseFormat as any,
json_schema: aiChatJsonSchema
}
},
modelConstantsData
);
// console.log(JSON.stringify(requestBody, null, 2), '===');
const { response, isStreamResponse, getEmptyResponseTip } = await createChatCompletion({
body: requestBody,
userKey: externalProvider.openaiAccount,
options: {
headers: {
Accept: 'application/json, text/plain, */*'
}
}
})()
]);
});
const requestMessages = await loadRequestMessages({
messages: filterMessages,
useVision: aiChatVision,
origin: requestOrigin
});
let { answerText, reasoningText, finish_reason, inputTokens, outputTokens } =
await (async () => {
if (isStreamResponse) {
if (!res || res.closed) {
return {
answerText: '',
reasoningText: '',
finish_reason: 'close' as const,
inputTokens: 0,
outputTokens: 0
};
}
// sse response
const { answer, reasoning, finish_reason, usage } = await streamResponse({
res,
stream: response,
aiChatReasoning,
parseThinkTag: modelConstantsData.reasoning,
isResponseAnswerText,
workflowStreamResponse,
retainDatasetCite
});
const requestBody = llmCompletionsBodyFormat(
{
model: modelConstantsData.model,
stream,
messages: requestMessages,
temperature,
max_tokens,
top_p: aiChatTopP,
stop: aiChatStopSign,
response_format: {
type: aiChatResponseFormat as any,
json_schema: aiChatJsonSchema
}
},
modelConstantsData
);
// console.log(JSON.stringify(requestBody, null, 2), '===');
const { response, isStreamResponse, getEmptyResponseTip } = await createChatCompletion({
body: requestBody,
userKey: externalProvider.openaiAccount,
options: {
headers: {
Accept: 'application/json, text/plain, */*'
}
}
});
let { answerText, reasoningText, finish_reason, inputTokens, outputTokens } = await (async () => {
if (isStreamResponse) {
if (!res || res.closed) {
return {
answerText: '',
reasoningText: '',
finish_reason: 'close' as const,
inputTokens: 0,
outputTokens: 0
};
}
// sse response
const { answer, reasoning, finish_reason, usage } = await streamResponse({
res,
stream: response,
aiChatReasoning,
parseThinkTag: modelConstantsData.reasoning,
isResponseAnswerText,
workflowStreamResponse,
retainDatasetCite
});
return {
answerText: answer,
reasoningText: reasoning,
finish_reason,
inputTokens: usage?.prompt_tokens,
outputTokens: usage?.completion_tokens
};
} else {
const finish_reason = response.choices?.[0]?.finish_reason as CompletionFinishReason;
const usage = response.usage;
const { content, reasoningContent } = (() => {
const content = response.choices?.[0]?.message?.content || '';
// @ts-ignore
const reasoningContent: string = response.choices?.[0]?.message?.reasoning_content || '';
// API already parse reasoning content
if (reasoningContent || !aiChatReasoning) {
return {
content,
reasoningContent
answerText: answer,
reasoningText: reasoning,
finish_reason,
inputTokens: usage?.prompt_tokens,
outputTokens: usage?.completion_tokens
};
} else {
const finish_reason = response.choices?.[0]?.finish_reason as CompletionFinishReason;
const usage = response.usage;
const { content, reasoningContent } = (() => {
const content = response.choices?.[0]?.message?.content || '';
const reasoningContent: string =
// @ts-ignore
response.choices?.[0]?.message?.reasoning_content || '';
// API already parse reasoning content
if (reasoningContent || !aiChatReasoning) {
return {
content,
reasoningContent
};
}
const [think, answer] = parseReasoningContent(content);
return {
content: answer,
reasoningContent: think
};
})();
const formatReasonContent = removeDatasetCiteText(reasoningContent, retainDatasetCite);
const formatContent = removeDatasetCiteText(content, retainDatasetCite);
// Some models do not support streaming
if (aiChatReasoning && reasoningContent) {
workflowStreamResponse?.({
event: SseResponseEventEnum.fastAnswer,
data: textAdaptGptResponse({
reasoning_content: formatReasonContent
})
});
}
if (isResponseAnswerText && content) {
workflowStreamResponse?.({
event: SseResponseEventEnum.fastAnswer,
data: textAdaptGptResponse({
text: formatContent
})
});
}
return {
reasoningText: formatReasonContent,
answerText: formatContent,
finish_reason,
inputTokens: usage?.prompt_tokens,
outputTokens: usage?.completion_tokens
};
}
const [think, answer] = parseReasoningContent(content);
return {
content: answer,
reasoningContent: think
};
})();
const formatReasonContent = removeDatasetCiteText(reasoningContent, retainDatasetCite);
const formatContent = removeDatasetCiteText(content, retainDatasetCite);
// Some models do not support streaming
if (aiChatReasoning && reasoningContent) {
workflowStreamResponse?.({
event: SseResponseEventEnum.fastAnswer,
data: textAdaptGptResponse({
reasoning_content: formatReasonContent
})
});
}
if (isResponseAnswerText && content) {
workflowStreamResponse?.({
event: SseResponseEventEnum.fastAnswer,
data: textAdaptGptResponse({
text: formatContent
})
});
}
return {
reasoningText: formatReasonContent,
answerText: formatContent,
finish_reason,
inputTokens: usage?.prompt_tokens,
outputTokens: usage?.completion_tokens
};
if (!answerText && !reasoningText) {
return getNodeErrResponse({ error: getEmptyResponseTip() });
}
})();
if (!answerText && !reasoningText) {
return Promise.reject(getEmptyResponseTip());
}
const AIMessages: ChatCompletionMessageParam[] = [
{
role: ChatCompletionRequestMessageRoleEnum.Assistant,
content: answerText,
reasoning_text: reasoningText // reasoning_text is only recorded for response, but not for request
}
];
const completeMessages = [...requestMessages, ...AIMessages];
const chatCompleteMessages = GPTMessages2Chats(completeMessages);
inputTokens = inputTokens || (await countGptMessagesTokens(requestMessages));
outputTokens = outputTokens || (await countGptMessagesTokens(AIMessages));
const { totalPoints, modelName } = formatModelChars2Points({
model,
inputTokens,
outputTokens,
modelType: ModelTypeEnum.llm
});
return {
answerText: answerText.trim(),
reasoningText,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
model: modelName,
inputTokens: inputTokens,
outputTokens: outputTokens,
query: `${userChatInput}`,
maxToken: max_tokens,
reasoningText,
historyPreview: getHistoryPreview(chatCompleteMessages, 10000, aiChatVision),
contextTotalLen: completeMessages.length,
finishReason: finish_reason
},
[DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
const AIMessages: ChatCompletionMessageParam[] = [
{
moduleName: name,
role: ChatCompletionRequestMessageRoleEnum.Assistant,
content: answerText,
reasoning_text: reasoningText // reasoning_text is only recorded for response, but not for request
}
];
const completeMessages = [...requestMessages, ...AIMessages];
const chatCompleteMessages = GPTMessages2Chats(completeMessages);
inputTokens = inputTokens || (await countGptMessagesTokens(requestMessages));
outputTokens = outputTokens || (await countGptMessagesTokens(AIMessages));
const { totalPoints, modelName } = formatModelChars2Points({
model,
inputTokens,
outputTokens,
modelType: ModelTypeEnum.llm
});
return {
data: {
answerText: answerText.trim(),
reasoningText,
history: chatCompleteMessages
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
model: modelName,
inputTokens: inputTokens,
outputTokens: outputTokens
}
],
[DispatchNodeResponseKeyEnum.toolResponses]: answerText,
history: chatCompleteMessages
};
outputTokens: outputTokens,
query: `${userChatInput}`,
maxToken: max_tokens,
reasoningText,
historyPreview: getHistoryPreview(chatCompleteMessages, 10000, aiChatVision),
contextTotalLen: completeMessages.length,
finishReason: finish_reason
},
[DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
{
moduleName: name,
totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
model: modelName,
inputTokens: inputTokens,
outputTokens: outputTokens
}
],
[DispatchNodeResponseKeyEnum.toolResponses]: answerText
};
} catch (error) {
return getNodeErrResponse({ error });
}
};
async function filterDatasetQuote({

4
packages/service/core/workflow/dispatch/ai/classifyQuestion.ts
View File

@ -78,7 +78,9 @@ export const dispatchClassifyQuestion = async (props: Props): Promise<CQResponse
});
return {
[NodeOutputKeyEnum.cqResult]: result.value,
data: {
[NodeOutputKeyEnum.cqResult]: result.value
},
[DispatchNodeResponseKeyEnum.skipHandleId]: agents
.filter((item) => item.key !== result.key)
.map((item) => getHandleId(nodeId, 'source', item.key)),

145
packages/service/core/workflow/dispatch/ai/extract.ts
View File

@ -19,7 +19,7 @@ import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runti
import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/type';
import { sliceJsonStr } from '@fastgpt/global/common/string/tools';
import { type LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
import { getHistories } from '../utils';
import { getNodeErrResponse, getHistories } from '../utils';
import { getLLMModel } from '../../../ai/model';
import { formatModelChars2Points } from '../../../../support/wallet/usage/utils';
import json5 from 'json5';
@ -46,6 +46,7 @@ type Props = ModuleDispatchProps<{
type Response = DispatchNodeResultType<{
[NodeOutputKeyEnum.success]: boolean;
[NodeOutputKeyEnum.contextExtractFields]: string;
[key: string]: any;
}>;
type ActionProps = Props & { extractModel: LLMModelItemType; lastMemory?: Record<string, any> };
@ -62,7 +63,7 @@ export async function dispatchContentExtract(props: Props): Promise<Response> {
} = props;
if (!content) {
return Promise.reject('Input is empty');
return getNodeErrResponse({ error: 'Input is empty' });
}
const extractModel = getLLMModel(model);
@ -75,88 +76,94 @@ export async function dispatchContentExtract(props: Props): Promise<Response> {
any
>;
const { arg, inputTokens, outputTokens } = await (async () => {
if (extractModel.toolChoice) {
return toolChoice({
try {
const { arg, inputTokens, outputTokens } = await (async () => {
if (extractModel.toolChoice) {
return toolChoice({
...props,
histories: chatHistories,
extractModel,
lastMemory
});
}
return completions({
...props,
histories: chatHistories,
extractModel,
lastMemory
});
}
return completions({
...props,
histories: chatHistories,
extractModel,
lastMemory
});
})();
})();
// remove invalid key
for (let key in arg) {
const item = extractKeys.find((item) => item.key === key);
if (!item) {
delete arg[key];
}
if (arg[key] === '') {
delete arg[key];
}
}
// auto fill required fields
extractKeys.forEach((item) => {
if (item.required && arg[item.key] === undefined) {
arg[item.key] = item.defaultValue || '';
}
});
// auth fields
let success = !extractKeys.find((item) => !(item.key in arg));
// auth empty value
if (success) {
for (const key in arg) {
// remove invalid key
for (let key in arg) {
const item = extractKeys.find((item) => item.key === key);
if (!item) {
success = false;
break;
delete arg[key];
}
if (arg[key] === '') {
delete arg[key];
}
}
}
const { totalPoints, modelName } = formatModelChars2Points({
model: extractModel.model,
inputTokens: inputTokens,
outputTokens: outputTokens,
modelType: ModelTypeEnum.llm
});
// auto fill required fields
extractKeys.forEach((item) => {
if (item.required && arg[item.key] === undefined) {
arg[item.key] = item.defaultValue || '';
}
});
return {
[NodeOutputKeyEnum.success]: success,
[NodeOutputKeyEnum.contextExtractFields]: JSON.stringify(arg),
[DispatchNodeResponseKeyEnum.memories]: {
[memoryKey]: arg
},
...arg,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
model: modelName,
query: content,
inputTokens,
outputTokens,
extractDescription: description,
extractResult: arg,
contextTotalLen: chatHistories.length + 2
},
[DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
{
moduleName: name,
// auth fields
let success = !extractKeys.find((item) => !(item.key in arg));
// auth empty value
if (success) {
for (const key in arg) {
const item = extractKeys.find((item) => item.key === key);
if (!item) {
success = false;
break;
}
}
}
const { totalPoints, modelName } = formatModelChars2Points({
model: extractModel.model,
inputTokens: inputTokens,
outputTokens: outputTokens,
modelType: ModelTypeEnum.llm
});
return {
data: {
[NodeOutputKeyEnum.success]: success,
[NodeOutputKeyEnum.contextExtractFields]: JSON.stringify(arg),
...arg
},
[DispatchNodeResponseKeyEnum.memories]: {
[memoryKey]: arg
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
model: modelName,
query: content,
inputTokens,
outputTokens
}
]
};
outputTokens,
extractDescription: description,
extractResult: arg,
contextTotalLen: chatHistories.length + 2
},
[DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
{
moduleName: name,
totalPoints: externalProvider.openaiAccount?.key ? 0 : totalPoints,
model: modelName,
inputTokens,
outputTokens
}
]
};
} catch (error) {
return getNodeErrResponse({ error });
}
}
const getJsonSchema = ({ params: { extractKeys } }: ActionProps) => {

208
packages/service/core/workflow/dispatch/child/runApp.ts Normal file
View File

@ -0,0 +1,208 @@
import type { ChatItemType } from '@fastgpt/global/core/chat/type.d';
import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/type';
import { dispatchWorkFlow } from '../index';
import { ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
import { SseResponseEventEnum } from '@fastgpt/global/core/workflow/runtime/constants';
import {
getWorkflowEntryNodeIds,
storeEdges2RuntimeEdges,
rewriteNodeOutputByHistories,
storeNodes2RuntimeNodes,
textAdaptGptResponse
} from '@fastgpt/global/core/workflow/runtime/utils';
import type { NodeInputKeyEnum } from '@fastgpt/global/core/workflow/constants';
import { NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
import { filterSystemVariables, getNodeErrResponse, getHistories } from '../utils';
import { chatValue2RuntimePrompt, runtimePrompt2ChatsValue } from '@fastgpt/global/core/chat/adapt';
import { type DispatchNodeResultType } from '@fastgpt/global/core/workflow/runtime/type';
import { authAppByTmbId } from '../../../../support/permission/app/auth';
import { ReadPermissionVal } from '@fastgpt/global/support/permission/constant';
import { getAppVersionById } from '../../../app/version/controller';
import { parseUrlToFileType } from '@fastgpt/global/common/file/tools';
import { getUserChatInfoAndAuthTeamPoints } from '../../../../support/permission/auth/team';
type Props = ModuleDispatchProps<{
[NodeInputKeyEnum.userChatInput]: string;
[NodeInputKeyEnum.history]?: ChatItemType[] | number;
[NodeInputKeyEnum.fileUrlList]?: string[];
[NodeInputKeyEnum.forbidStream]?: boolean;
[NodeInputKeyEnum.fileUrlList]?: string[];
}>;
type Response = DispatchNodeResultType<{
[NodeOutputKeyEnum.answerText]: string;
[NodeOutputKeyEnum.history]: ChatItemType[];
}>;
export const dispatchRunAppNode = async (props: Props): Promise<Response> => {
const {
runningAppInfo,
histories,
query,
lastInteractive,
node: { pluginId: appId, version },
workflowStreamResponse,
params,
variables
} = props;
const {
system_forbid_stream = false,
userChatInput,
history,
fileUrlList,
...childrenAppVariables
} = params;
const { files } = chatValue2RuntimePrompt(query);
const userInputFiles = (() => {
if (fileUrlList) {
return fileUrlList.map((url) => parseUrlToFileType(url)).filter(Boolean);
}
// Adapt version 4.8.13 upgrade
return files;
})();
if (!userChatInput && !userInputFiles) {
return getNodeErrResponse({ error: 'Input is empty' });
}
if (!appId) {
return getNodeErrResponse({ error: 'pluginId is empty' });
}
try {
// Auth the app by tmbId(Not the user, but the workflow user)
const { app: appData } = await authAppByTmbId({
appId: appId,
tmbId: runningAppInfo.tmbId,
per: ReadPermissionVal
});
const { nodes, edges, chatConfig } = await getAppVersionById({
appId,
versionId: version,
app: appData
});
const childStreamResponse = system_forbid_stream ? false : props.stream;
// Auto line
if (childStreamResponse) {
workflowStreamResponse?.({
event: SseResponseEventEnum.answer,
data: textAdaptGptResponse({
text: '\n'
})
});
}
const chatHistories = getHistories(history, histories);
// Rewrite children app variables
const systemVariables = filterSystemVariables(variables);
const { externalProvider } = await getUserChatInfoAndAuthTeamPoints(appData.tmbId);
const childrenRunVariables = {
...systemVariables,
...childrenAppVariables,
histories: chatHistories,
appId: String(appData._id),
...(externalProvider ? externalProvider.externalWorkflowVariables : {})
};
const childrenInteractive =
lastInteractive?.type === 'childrenInteractive'
? lastInteractive.params.childrenResponse
: undefined;
const runtimeNodes = rewriteNodeOutputByHistories(
storeNodes2RuntimeNodes(
nodes,
getWorkflowEntryNodeIds(nodes, childrenInteractive || undefined)
),
childrenInteractive
);
const runtimeEdges = storeEdges2RuntimeEdges(edges, childrenInteractive);
const theQuery = childrenInteractive
? query
: runtimePrompt2ChatsValue({ files: userInputFiles, text: userChatInput });
const {
flowResponses,
flowUsages,
assistantResponses,
runTimes,
workflowInteractiveResponse,
system_memories
} = await dispatchWorkFlow({
...props,
lastInteractive: childrenInteractive,
// Rewrite stream mode
...(system_forbid_stream
? {
stream: false,
workflowStreamResponse: undefined
}
: {}),
runningAppInfo: {
id: String(appData._id),
teamId: String(appData.teamId),
tmbId: String(appData.tmbId),
isChildApp: true
},
runtimeNodes,
runtimeEdges,
histories: chatHistories,
variables: childrenRunVariables,
query: theQuery,
chatConfig
});
const completeMessages = chatHistories.concat([
{
obj: ChatRoleEnum.Human,
value: query
},
{
obj: ChatRoleEnum.AI,
value: assistantResponses
}
]);
const { text } = chatValue2RuntimePrompt(assistantResponses);
const usagePoints = flowUsages.reduce((sum, item) => sum + (item.totalPoints || 0), 0);
return {
data: {
[NodeOutputKeyEnum.answerText]: text,
[NodeOutputKeyEnum.history]: completeMessages
},
system_memories,
[DispatchNodeResponseKeyEnum.interactive]: workflowInteractiveResponse
? {
type: 'childrenInteractive',
params: {
childrenResponse: workflowInteractiveResponse
}
}
: undefined,
assistantResponses: system_forbid_stream ? [] : assistantResponses,
[DispatchNodeResponseKeyEnum.runTimes]: runTimes,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
moduleLogo: appData.avatar,
totalPoints: usagePoints,
query: userChatInput,
textOutput: text,
pluginDetail: appData.permission.hasWritePer ? flowResponses : undefined,
mergeSignId: props.node.nodeId
},
[DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
{
moduleName: appData.name,
totalPoints: usagePoints
}
],
[DispatchNodeResponseKeyEnum.toolResponses]: text
};
} catch (error) {
return getNodeErrResponse({ error });
}
};

136
packages/service/core/workflow/dispatch/plugin/runTool.ts → packages/service/core/workflow/dispatch/child/runTool.ts
View File

@ -17,23 +17,25 @@ import type { StoreSecretValueType } from '@fastgpt/global/common/secret/type';
import { getSystemPluginById } from '../../../app/plugin/controller';
import { textAdaptGptResponse } from '@fastgpt/global/core/workflow/runtime/utils';
import { pushTrack } from '../../../../common/middle/tracks/utils';
import { getNodeErrResponse } from '../utils';
type SystemInputConfigType = {
type: SystemToolInputTypeEnum;
value: StoreSecretValueType;
};
type RunToolProps = ModuleDispatchProps<
{
[NodeInputKeyEnum.toolData]?: McpToolDataType;
[NodeInputKeyEnum.systemInputConfig]?: SystemInputConfigType;
} & Record<string, any>
>;
type RunToolProps = ModuleDispatchProps<{
[NodeInputKeyEnum.toolData]?: McpToolDataType;
[NodeInputKeyEnum.systemInputConfig]?: SystemInputConfigType;
[key: string]: any;
}>;
type RunToolResponse = DispatchNodeResultType<
{
[NodeOutputKeyEnum.rawResponse]?: any;
} & Record<string, any>
[key: string]: any;
},
Record<string, any>
>;
export const dispatchRunTool = async (props: RunToolProps): Promise<RunToolResponse> => {
@ -43,7 +45,7 @@ export const dispatchRunTool = async (props: RunToolProps): Promise<RunToolRespo
runningAppInfo,
variables,
workflowStreamResponse,
node: { name, avatar, toolConfig, version }
node: { name, avatar, toolConfig, version, catchError }
} = props;
const systemToolId = toolConfig?.systemTool?.toolId;
@ -80,50 +82,69 @@ export const dispatchRunTool = async (props: RunToolProps): Promise<RunToolRespo
const formatToolId = tool.id.split('-')[1];
const result = await (async () => {
const res = await runSystemTool({
toolId: formatToolId,
inputs,
systemVar: {
user: {
id: variables.userId,
teamId: runningUserInfo.teamId,
name: runningUserInfo.tmbId
},
app: {
id: runningAppInfo.id,
name: runningAppInfo.id
},
tool: {
id: formatToolId,
version: version || tool.versionList?.[0]?.value || ''
},
time: variables.cTime
const res = await runSystemTool({
toolId: formatToolId,
inputs,
systemVar: {
user: {
id: variables.userId,
teamId: runningUserInfo.teamId,
name: runningUserInfo.tmbId
},
onMessage: ({ type, content }) => {
if (workflowStreamResponse && content) {
workflowStreamResponse({
event: type as unknown as SseResponseEventEnum,
data: textAdaptGptResponse({
text: content
})
});
}
app: {
id: runningAppInfo.id,
name: runningAppInfo.id
},
tool: {
id: formatToolId,
version: version || tool.versionList?.[0]?.value || ''
},
time: variables.cTime
},
onMessage: ({ type, content }) => {
if (workflowStreamResponse && content) {
workflowStreamResponse({
event: type as unknown as SseResponseEventEnum,
data: textAdaptGptResponse({
text: content
})
});
}
});
if (res.error) {
return Promise.reject(res.error);
}
if (!res.output) return {};
});
let result = res.output || {};
return res.output;
})();
if (res.error) {
// 适配旧版：旧版本没有catchError，部分工具会正常返回 error 字段作为响应。
if (catchError === undefined && typeof res.error === 'object') {
return {
data: res.error,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
toolRes: res.error,
moduleLogo: avatar
},
[DispatchNodeResponseKeyEnum.toolResponses]: res.error
};
}
// String error(Common error, not custom)
if (typeof res.error === 'string') {
throw new Error(res.error);
}
// Custom error field
return {
error: res.error,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
error: res.error,
moduleLogo: avatar
},
[DispatchNodeResponseKeyEnum.toolResponses]: res.error
};
}
const usagePoints = (() => {
if (
params.system_input_config?.type !== SystemToolInputTypeEnum.system ||
result[NodeOutputKeyEnum.systemError]
) {
if (params.system_input_config?.type !== SystemToolInputTypeEnum.system) {
return 0;
}
return tool.currentCost ?? 0;
@ -140,6 +161,7 @@ export const dispatchRunTool = async (props: RunToolProps): Promise<RunToolRespo
});
return {
data: result,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
toolRes: result,
moduleLogo: avatar,
@ -151,8 +173,7 @@ export const dispatchRunTool = async (props: RunToolProps): Promise<RunToolRespo
moduleName: name,
totalPoints: usagePoints
}
],
...result
]
};
} else {
// mcp tool
@ -168,12 +189,14 @@ export const dispatchRunTool = async (props: RunToolProps): Promise<RunToolRespo
const result = await mcpClient.toolCall(toolName, restParams);
return {
data: {
[NodeOutputKeyEnum.rawResponse]: result
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
toolRes: result,
moduleLogo: avatar
},
[DispatchNodeResponseKeyEnum.toolResponses]: result,
[NodeOutputKeyEnum.rawResponse]: result
[DispatchNodeResponseKeyEnum.toolResponses]: result
};
}
} catch (error) {
@ -188,12 +211,11 @@ export const dispatchRunTool = async (props: RunToolProps): Promise<RunToolRespo
});
}
return {
[DispatchNodeResponseKeyEnum.nodeResponse]: {
moduleLogo: avatar,
error: getErrText(error)
},
[DispatchNodeResponseKeyEnum.toolResponses]: getErrText(error)
};
return getNodeErrResponse({
error,
customNodeResponse: {
moduleLogo: avatar
}
});
}
};

10
packages/service/core/workflow/dispatch/dataset/concat.ts
View File

@ -35,10 +35,12 @@ export async function dispatchDatasetConcat(
);
return {
[NodeOutputKeyEnum.datasetQuoteQA]: await filterSearchResultsByMaxChars(
rrfConcatResults,
limit
),
data: {
[NodeOutputKeyEnum.datasetQuoteQA]: await filterSearchResultsByMaxChars(
rrfConcatResults,
limit
)
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
concatLength: rrfConcatResults.length
}

344
packages/service/core/workflow/dispatch/dataset/search.ts
View File

@ -17,6 +17,7 @@ import { i18nT } from '../../../../../web/i18n/utils';
import { filterDatasetsByTmbId } from '../../../dataset/utils';
import { ModelTypeEnum } from '@fastgpt/global/core/ai/model';
import { getDatasetSearchToolResponsePrompt } from '../../../../../global/core/ai/prompt/dataset';
import { getNodeErrResponse } from '../utils';
type DatasetSearchProps = ModuleDispatchProps<{
[NodeInputKeyEnum.datasetSelectList]: SelectedDatasetType;
@ -83,11 +84,13 @@ export async function dispatchDatasetSearch(
}
if (datasets.length === 0) {
return Promise.reject(i18nT('common:core.chat.error.Select dataset empty'));
return getNodeErrResponse({ error: i18nT('common:core.chat.error.Select dataset empty') });
}
const emptyResult = {
quoteQA: [],
const emptyResult: DatasetSearchResponse = {
data: {
quoteQA: []
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
totalPoints: 0,
query: '',
@ -102,177 +105,184 @@ export async function dispatchDatasetSearch(
return emptyResult;
}
const datasetIds = authTmbId
? await filterDatasetsByTmbId({
datasetIds: datasets.map((item) => item.datasetId),
tmbId
})
: await Promise.resolve(datasets.map((item) => item.datasetId));
try {
const datasetIds = authTmbId
? await filterDatasetsByTmbId({
datasetIds: datasets.map((item) => item.datasetId),
tmbId
})
: await Promise.resolve(datasets.map((item) => item.datasetId));
if (datasetIds.length === 0) {
return emptyResult;
}
if (datasetIds.length === 0) {
return emptyResult;
}
// get vector
const vectorModel = getEmbeddingModel(
(await MongoDataset.findById(datasets[0].datasetId, 'vectorModel').lean())?.vectorModel
);
// Get Rerank Model
const rerankModelData = getRerankModel(rerankModel);
// get vector
const vectorModel = getEmbeddingModel(
(await MongoDataset.findById(datasets[0].datasetId, 'vectorModel').lean())?.vectorModel
);
// Get Rerank Model
const rerankModelData = getRerankModel(rerankModel);
// start search
const searchData = {
histories,
teamId,
reRankQuery: userChatInput,
queries: [userChatInput],
model: vectorModel.model,
similarity,
limit,
datasetIds,
searchMode,
embeddingWeight,
usingReRank,
rerankModel: rerankModelData,
rerankWeight,
collectionFilterMatch
};
const {
searchRes,
embeddingTokens,
reRankInputTokens,
usingSimilarityFilter,
usingReRank: searchUsingReRank,
queryExtensionResult,
deepSearchResult
} = datasetDeepSearch
? await deepRagSearch({
...searchData,
datasetDeepSearchModel,
datasetDeepSearchMaxTimes,
datasetDeepSearchBg
})
: await defaultSearchDatasetData({
...searchData,
datasetSearchUsingExtensionQuery,
datasetSearchExtensionModel,
datasetSearchExtensionBg
});
// count bill results
const nodeDispatchUsages: ChatNodeUsageType[] = [];
// vector
const { totalPoints: embeddingTotalPoints, modelName: embeddingModelName } =
formatModelChars2Points({
// start search
const searchData = {
histories,
teamId,
reRankQuery: userChatInput,
queries: [userChatInput],
model: vectorModel.model,
inputTokens: embeddingTokens,
modelType: ModelTypeEnum.embedding
});
nodeDispatchUsages.push({
totalPoints: embeddingTotalPoints,
moduleName: node.name,
model: embeddingModelName,
inputTokens: embeddingTokens
});
// Rerank
const { totalPoints: reRankTotalPoints, modelName: reRankModelName } = formatModelChars2Points({
model: rerankModelData?.model,
inputTokens: reRankInputTokens,
modelType: ModelTypeEnum.rerank
});
if (usingReRank) {
similarity,
limit,
datasetIds,
searchMode,
embeddingWeight,
usingReRank,
rerankModel: rerankModelData,
rerankWeight,
collectionFilterMatch
};
const {
searchRes,
embeddingTokens,
reRankInputTokens,
usingSimilarityFilter,
usingReRank: searchUsingReRank,
queryExtensionResult,
deepSearchResult
} = datasetDeepSearch
? await deepRagSearch({
...searchData,
datasetDeepSearchModel,
datasetDeepSearchMaxTimes,
datasetDeepSearchBg
})
: await defaultSearchDatasetData({
...searchData,
datasetSearchUsingExtensionQuery,
datasetSearchExtensionModel,
datasetSearchExtensionBg
});
// count bill results
const nodeDispatchUsages: ChatNodeUsageType[] = [];
// vector
const { totalPoints: embeddingTotalPoints, modelName: embeddingModelName } =
formatModelChars2Points({
model: vectorModel.model,
inputTokens: embeddingTokens,
modelType: ModelTypeEnum.embedding
});
nodeDispatchUsages.push({
totalPoints: reRankTotalPoints,
totalPoints: embeddingTotalPoints,
moduleName: node.name,
model: reRankModelName,
inputTokens: reRankInputTokens
model: embeddingModelName,
inputTokens: embeddingTokens
});
}
// Query extension
(() => {
if (queryExtensionResult) {
const { totalPoints, modelName } = formatModelChars2Points({
model: queryExtensionResult.model,
inputTokens: queryExtensionResult.inputTokens,
outputTokens: queryExtensionResult.outputTokens,
modelType: ModelTypeEnum.llm
});
nodeDispatchUsages.push({
totalPoints,
moduleName: i18nT('common:core.module.template.Query extension'),
model: modelName,
inputTokens: queryExtensionResult.inputTokens,
outputTokens: queryExtensionResult.outputTokens
});
return {
totalPoints
};
}
return {
totalPoints: 0
};
})();
// Deep search
(() => {
if (deepSearchResult) {
const { totalPoints, modelName } = formatModelChars2Points({
model: deepSearchResult.model,
inputTokens: deepSearchResult.inputTokens,
outputTokens: deepSearchResult.outputTokens,
modelType: ModelTypeEnum.llm
});
nodeDispatchUsages.push({
totalPoints,
moduleName: i18nT('common:deep_rag_search'),
model: modelName,
inputTokens: deepSearchResult.inputTokens,
outputTokens: deepSearchResult.outputTokens
});
return {
totalPoints
};
}
return {
totalPoints: 0
};
})();
const totalPoints = nodeDispatchUsages.reduce((acc, item) => acc + item.totalPoints, 0);
const responseData: DispatchNodeResponseType & { totalPoints: number } = {
totalPoints,
query: userChatInput,
embeddingModel: vectorModel.name,
embeddingTokens,
similarity: usingSimilarityFilter ? similarity : undefined,
limit,
searchMode,
embeddingWeight: searchMode === DatasetSearchModeEnum.mixedRecall ? embeddingWeight : undefined,
// Rerank
...(searchUsingReRank && {
rerankModel: rerankModelData?.name,
rerankWeight: rerankWeight,
reRankInputTokens
}),
searchUsingReRank,
// Results
quoteList: searchRes,
queryExtensionResult,
deepSearchResult
};
return {
quoteQA: searchRes,
[DispatchNodeResponseKeyEnum.nodeResponse]: responseData,
nodeDispatchUsages,
[DispatchNodeResponseKeyEnum.toolResponses]: {
prompt: getDatasetSearchToolResponsePrompt(),
cites: searchRes.map((item) => ({
id: item.id,
sourceName: item.sourceName,
updateTime: item.updateTime,
content: `${item.q}\n${item.a}`.trim()
}))
const { totalPoints: reRankTotalPoints, modelName: reRankModelName } = formatModelChars2Points({
model: rerankModelData?.model,
inputTokens: reRankInputTokens,
modelType: ModelTypeEnum.rerank
});
if (usingReRank) {
nodeDispatchUsages.push({
totalPoints: reRankTotalPoints,
moduleName: node.name,
model: reRankModelName,
inputTokens: reRankInputTokens
});
}
};
// Query extension
(() => {
if (queryExtensionResult) {
const { totalPoints, modelName } = formatModelChars2Points({
model: queryExtensionResult.model,
inputTokens: queryExtensionResult.inputTokens,
outputTokens: queryExtensionResult.outputTokens,
modelType: ModelTypeEnum.llm
});
nodeDispatchUsages.push({
totalPoints,
moduleName: i18nT('common:core.module.template.Query extension'),
model: modelName,
inputTokens: queryExtensionResult.inputTokens,
outputTokens: queryExtensionResult.outputTokens
});
return {
totalPoints
};
}
return {
totalPoints: 0
};
})();
// Deep search
(() => {
if (deepSearchResult) {
const { totalPoints, modelName } = formatModelChars2Points({
model: deepSearchResult.model,
inputTokens: deepSearchResult.inputTokens,
outputTokens: deepSearchResult.outputTokens,
modelType: ModelTypeEnum.llm
});
nodeDispatchUsages.push({
totalPoints,
moduleName: i18nT('common:deep_rag_search'),
model: modelName,
inputTokens: deepSearchResult.inputTokens,
outputTokens: deepSearchResult.outputTokens
});
return {
totalPoints
};
}
return {
totalPoints: 0
};
})();
const totalPoints = nodeDispatchUsages.reduce((acc, item) => acc + item.totalPoints, 0);
const responseData: DispatchNodeResponseType & { totalPoints: number } = {
totalPoints,
query: userChatInput,
embeddingModel: vectorModel.name,
embeddingTokens,
similarity: usingSimilarityFilter ? similarity : undefined,
limit,
searchMode,
embeddingWeight:
searchMode === DatasetSearchModeEnum.mixedRecall ? embeddingWeight : undefined,
// Rerank
...(searchUsingReRank && {
rerankModel: rerankModelData?.name,
rerankWeight: rerankWeight,
reRankInputTokens
}),
searchUsingReRank,
// Results
quoteList: searchRes,
queryExtensionResult,
deepSearchResult
};
return {
data: {
quoteQA: searchRes
},
[DispatchNodeResponseKeyEnum.nodeResponse]: responseData,
nodeDispatchUsages,
[DispatchNodeResponseKeyEnum.toolResponses]: {
prompt: getDatasetSearchToolResponsePrompt(),
cites: searchRes.map((item) => ({
id: item.id,
sourceName: item.sourceName,
updateTime: item.updateTime,
content: `${item.q}\n${item.a}`.trim()
}))
}
};
} catch (error) {
return getNodeErrResponse({ error });
}
}

132
packages/service/core/workflow/dispatch/index.ts
View File

@ -49,7 +49,7 @@ import { dispatchRunTools } from './ai/agent/index';
import { dispatchStopToolCall } from './ai/agent/stopTool';
import { dispatchToolParams } from './ai/agent/toolParams';
import { dispatchChatCompletion } from './ai/chat';
import { dispatchRunCode } from './code/run';
import { dispatchCodeSandbox } from './tools/codeSandbox';
import { dispatchDatasetConcat } from './dataset/concat';
import { dispatchDatasetSearch } from './dataset/search';
import { dispatchSystemConfig } from './init/systemConfig';
@ -60,10 +60,10 @@ import { dispatchLoop } from './loop/runLoop';
import { dispatchLoopEnd } from './loop/runLoopEnd';
import { dispatchLoopStart } from './loop/runLoopStart';
import { dispatchRunPlugin } from './plugin/run';
import { dispatchRunAppNode } from './plugin/runApp';
import { dispatchRunAppNode } from './child/runApp';
import { dispatchPluginInput } from './plugin/runInput';
import { dispatchPluginOutput } from './plugin/runOutput';
import { dispatchRunTool } from './plugin/runTool';
import { dispatchRunTool } from './child/runTool';
import { dispatchAnswer } from './tools/answer';
import { dispatchCustomFeedback } from './tools/customFeedback';
import { dispatchHttp468Request } from './tools/http468';
@ -74,7 +74,8 @@ import { dispatchLafRequest } from './tools/runLaf';
import { dispatchUpdateVariable } from './tools/runUpdateVar';
import { dispatchTextEditor } from './tools/textEditor';
import type { DispatchFlowResponse } from './type';
import { formatHttpError, removeSystemVariable, rewriteRuntimeWorkFlow } from './utils';
import { removeSystemVariable, rewriteRuntimeWorkFlow } from './utils';
import { getHandleId } from '@fastgpt/global/core/workflow/utils';
const callbackMap: Record<FlowNodeTypeEnum, Function> = {
[FlowNodeTypeEnum.workflowStart]: dispatchWorkflowStart,
@ -96,7 +97,7 @@ const callbackMap: Record<FlowNodeTypeEnum, Function> = {
[FlowNodeTypeEnum.lafModule]: dispatchLafRequest,
[FlowNodeTypeEnum.ifElseNode]: dispatchIfElse,
[FlowNodeTypeEnum.variableUpdate]: dispatchUpdateVariable,
[FlowNodeTypeEnum.code]: dispatchRunCode,
[FlowNodeTypeEnum.code]: dispatchCodeSandbox,
[FlowNodeTypeEnum.textEditor]: dispatchTextEditor,
[FlowNodeTypeEnum.customFeedback]: dispatchCustomFeedback,
[FlowNodeTypeEnum.readFiles]: dispatchReadFiles,
@ -123,6 +124,14 @@ type Props = ChatDispatchProps & {
runtimeNodes: RuntimeNodeItemType[];
runtimeEdges: RuntimeEdgeItemType[];
};
type NodeResponseType = DispatchNodeResultType<{
[NodeOutputKeyEnum.answerText]?: string;
[NodeOutputKeyEnum.reasoningText]?: string;
[key: string]: any;
}>;
type NodeResponseCompleteType = Omit<NodeResponseType, 'responseData'> & {
[DispatchNodeResponseKeyEnum.nodeResponse]?: ChatHistoryItemResType;
};
/* running */
export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowResponse> {
@ -229,8 +238,7 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
function pushStore(
{ inputs = [] }: RuntimeNodeItemType,
{
answerText = '',
reasoningText,
data: { answerText = '', reasoningText } = {},
responseData,
nodeDispatchUsages,
toolResponses,
@ -238,14 +246,7 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
rewriteHistories,
runTimes = 1,
system_memories: newMemories
}: Omit<
DispatchNodeResultType<{
[NodeOutputKeyEnum.answerText]?: string;
[NodeOutputKeyEnum.reasoningText]?: string;
[DispatchNodeResponseKeyEnum.nodeResponse]?: ChatHistoryItemResType;
}>,
'nodeResponse'
>
}: NodeResponseCompleteType
) {
// Add run times
workflowRunTimes += runTimes;
@ -316,22 +317,27 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
/* Pass the output of the node, to get next nodes and update edge status */
function nodeOutput(
node: RuntimeNodeItemType,
result: Record<string, any> = {}
result: NodeResponseCompleteType
): {
nextStepActiveNodes: RuntimeNodeItemType[];
nextStepSkipNodes: RuntimeNodeItemType[];
} {
pushStore(node, result);
const concatData: Record<string, any> = {
...(result.data ?? {}),
...(result.error ?? {})
};
// Assign the output value to the next node
node.outputs.forEach((outputItem) => {
if (result[outputItem.key] === undefined) return;
if (concatData[outputItem.key] === undefined) return;
/* update output value */
outputItem.value = result[outputItem.key];
outputItem.value = concatData[outputItem.key];
});
// Get next source edges and update status
const skipHandleId = (result[DispatchNodeResponseKeyEnum.skipHandleId] || []) as string[];
const skipHandleId = result[DispatchNodeResponseKeyEnum.skipHandleId] || [];
const targetEdges = filterWorkflowEdges(runtimeEdges).filter(
(item) => item.source === node.nodeId
);
@ -591,7 +597,7 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
async function nodeRunWithActive(node: RuntimeNodeItemType): Promise<{
node: RuntimeNodeItemType;
runStatus: 'run';
result: Record<string, any>;
result: NodeResponseCompleteType;
}> {
// push run status messages
if (node.showStatus && !props.isToolCall) {
@ -625,23 +631,66 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
};
// run module
const dispatchRes: Record<string, any> = await (async () => {
const dispatchRes: NodeResponseType = await (async () => {
if (callbackMap[node.flowNodeType]) {
const targetEdges = runtimeEdges.filter((item) => item.source === node.nodeId);
try {
return await callbackMap[node.flowNodeType](dispatchData);
const result = (await callbackMap[node.flowNodeType](dispatchData)) as NodeResponseType;
const errorHandleId = getHandleId(node.nodeId, 'source_catch', 'right');
if (!result.error) {
const skipHandleId =
targetEdges.find((item) => item.sourceHandle === errorHandleId)?.sourceHandle || '';
return {
...result,
[DispatchNodeResponseKeyEnum.skipHandleId]: (result[
DispatchNodeResponseKeyEnum.skipHandleId
]
? [...result[DispatchNodeResponseKeyEnum.skipHandleId], skipHandleId]
: [skipHandleId]
).filter(Boolean)
};
}
// Run error and not catch error, skip all edges
if (!node.catchError) {
return {
...result,
[DispatchNodeResponseKeyEnum.skipHandleId]: targetEdges.map(
(item) => item.sourceHandle
)
};
}
// Catch error
const skipHandleIds = targetEdges
.filter((item) => {
if (node.catchError) {
return item.sourceHandle !== errorHandleId;
}
return true;
})
.map((item) => item.sourceHandle);
return {
...result,
[DispatchNodeResponseKeyEnum.skipHandleId]: result[
DispatchNodeResponseKeyEnum.skipHandleId
]
? [...result[DispatchNodeResponseKeyEnum.skipHandleId], ...skipHandleIds].filter(
Boolean
)
: skipHandleIds
};
} catch (error) {
// Get source handles of outgoing edges
const targetEdges = runtimeEdges.filter((item) => item.source === node.nodeId);
const skipHandleIds = targetEdges.map((item) => item.sourceHandle);
toolRunResponse = getErrText(error);
// Skip all edges and return error
return {
[DispatchNodeResponseKeyEnum.nodeResponse]: {
error: formatHttpError(error)
error: getErrText(error)
},
[DispatchNodeResponseKeyEnum.skipHandleId]: skipHandleIds
[DispatchNodeResponseKeyEnum.skipHandleId]: targetEdges.map((item) => item.sourceHandle)
};
}
}
@ -649,15 +698,16 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
})();
// format response data. Add modulename and module type
const formatResponseData: ChatHistoryItemResType = (() => {
const formatResponseData: NodeResponseCompleteType['responseData'] = (() => {
if (!dispatchRes[DispatchNodeResponseKeyEnum.nodeResponse]) return undefined;
return {
...dispatchRes[DispatchNodeResponseKeyEnum.nodeResponse],
id: getNanoid(),
nodeId: node.nodeId,
moduleName: node.name,
moduleType: node.flowNodeType,
runningTime: +((Date.now() - startTime) / 1000).toFixed(2),
...dispatchRes[DispatchNodeResponseKeyEnum.nodeResponse]
runningTime: +((Date.now() - startTime) / 1000).toFixed(2)
};
})();
@ -675,11 +725,13 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
}
// Add output default value
node.outputs.forEach((item) => {
if (!item.required) return;
if (dispatchRes[item.key] !== undefined) return;
dispatchRes[item.key] = valueTypeFormat(item.defaultValue, item.valueType);
});
if (dispatchRes.data) {
node.outputs.forEach((item) => {
if (!item.required) return;
if (dispatchRes.data?.[item.key] !== undefined) return;
dispatchRes.data![item.key] = valueTypeFormat(item.defaultValue, item.valueType);
});
}
// Update new variables
if (dispatchRes[DispatchNodeResponseKeyEnum.newVariables]) {
@ -691,7 +743,7 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
// Error
if (dispatchRes?.responseData?.error) {
addLog.warn('workflow error', dispatchRes.responseData.error);
addLog.warn('workflow error', { error: dispatchRes.responseData.error });
}
return {
@ -706,7 +758,7 @@ export async function dispatchWorkFlow(data: Props): Promise<DispatchFlowRespons
async function nodeRunWithSkip(node: RuntimeNodeItemType): Promise<{
node: RuntimeNodeItemType;
runStatus: 'skip';
result: Record<string, any>;
result: NodeResponseCompleteType;
}> {
// Set target edges status to skipped
const targetEdges = runtimeEdges.filter((item) => item.source === node.nodeId);

7
packages/service/core/workflow/dispatch/init/workflowStart.tsx
View File

@ -34,8 +34,9 @@ export const dispatchWorkflowStart = (props: Record<string, any>): Response => {
return {
[DispatchNodeResponseKeyEnum.nodeResponse]: {},
[NodeInputKeyEnum.userChatInput]: text || userChatInput,
[NodeOutputKeyEnum.userFiles]: [...queryFiles, ...variablesFiles]
// [NodeInputKeyEnum.inputFiles]: files
data: {
[NodeInputKeyEnum.userChatInput]: text || userChatInput,
[NodeOutputKeyEnum.userFiles]: [...queryFiles, ...variablesFiles]
}
};
};

13
packages/service/core/workflow/dispatch/interactive/formInput.ts
View File

@ -6,10 +6,7 @@ import type {
DispatchNodeResultType,
ModuleDispatchProps
} from '@fastgpt/global/core/workflow/runtime/type';
import type {
UserInputFormItemType,
UserInputInteractive
} from '@fastgpt/global/core/workflow/template/system/interactive/type';
import type { UserInputFormItemType } from '@fastgpt/global/core/workflow/template/system/interactive/type';
import { addLog } from '../../../../common/system/log';
type Props = ModuleDispatchProps<{
@ -17,8 +14,8 @@ type Props = ModuleDispatchProps<{
[NodeInputKeyEnum.userInputForms]: UserInputFormItemType[];
}>;
type FormInputResponse = DispatchNodeResultType<{
[DispatchNodeResponseKeyEnum.interactive]?: UserInputInteractive;
[NodeOutputKeyEnum.formInputResult]?: Record<string, any>;
[key: string]: any;
}>;
/*
@ -60,9 +57,11 @@ export const dispatchFormInput = async (props: Props): Promise<FormInputResponse
})();
return {
data: {
...userInputVal,
[NodeOutputKeyEnum.formInputResult]: userInputVal
},
[DispatchNodeResponseKeyEnum.rewriteHistories]: histories.slice(0, -2), // Removes the current session record as the history of subsequent nodes
...userInputVal,
[NodeOutputKeyEnum.formInputResult]: userInputVal,
[DispatchNodeResponseKeyEnum.toolResponses]: userInputVal,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
formInputResult: userInputVal

13
packages/service/core/workflow/dispatch/interactive/userSelect.ts
View File

@ -6,10 +6,7 @@ import type {
import type { NodeInputKeyEnum } from '@fastgpt/global/core/workflow/constants';
import { NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
import { getHandleId } from '@fastgpt/global/core/workflow/utils';
import type {
UserSelectInteractive,
UserSelectOptionItemType
} from '@fastgpt/global/core/workflow/template/system/interactive/type';
import type { UserSelectOptionItemType } from '@fastgpt/global/core/workflow/template/system/interactive/type';
import { chatValue2RuntimePrompt } from '@fastgpt/global/core/chat/adapt';
type Props = ModuleDispatchProps<{
@ -17,8 +14,6 @@ type Props = ModuleDispatchProps<{
[NodeInputKeyEnum.userSelectOptions]: UserSelectOptionItemType[];
}>;
type UserSelectResponse = DispatchNodeResultType<{
[NodeOutputKeyEnum.answerText]?: string;
[DispatchNodeResponseKeyEnum.interactive]?: UserSelectInteractive;
[NodeOutputKeyEnum.selectResult]?: string;
}>;
@ -59,6 +54,9 @@ export const dispatchUserSelect = async (props: Props): Promise<UserSelectRespon
}
return {
data: {
[NodeOutputKeyEnum.selectResult]: userSelectedVal
},
[DispatchNodeResponseKeyEnum.rewriteHistories]: histories.slice(0, -2), // Removes the current session record as the history of subsequent nodes
[DispatchNodeResponseKeyEnum.skipHandleId]: userSelectOptions
.filter((item) => item.value !== userSelectedVal)
@ -66,7 +64,6 @@ export const dispatchUserSelect = async (props: Props): Promise<UserSelectRespon
[DispatchNodeResponseKeyEnum.nodeResponse]: {
userSelectResult: userSelectedVal
},
[DispatchNodeResponseKeyEnum.toolResponses]: userSelectedVal,
[NodeOutputKeyEnum.selectResult]: userSelectedVal
[DispatchNodeResponseKeyEnum.toolResponses]: userSelectedVal
};
};

10
packages/service/core/workflow/dispatch/loop/runLoop.ts
View File

@ -11,10 +11,7 @@ import {
type ChatHistoryItemResType
} from '@fastgpt/global/core/chat/type';
import { cloneDeep } from 'lodash';
import {
type LoopInteractive,
type WorkflowInteractiveResponseType
} from '@fastgpt/global/core/workflow/template/system/interactive/type';
import { type WorkflowInteractiveResponseType } from '@fastgpt/global/core/workflow/template/system/interactive/type';
import { storeEdges2RuntimeEdges } from '@fastgpt/global/core/workflow/runtime/utils';
type Props = ModuleDispatchProps<{
@ -22,7 +19,6 @@ type Props = ModuleDispatchProps<{
[NodeInputKeyEnum.childrenNodeIdList]: string[];
}>;
type Response = DispatchNodeResultType<{
[DispatchNodeResponseKeyEnum.interactive]?: LoopInteractive;
[NodeOutputKeyEnum.loopArray]: Array<any>;
}>;
@ -133,6 +129,9 @@ export const dispatchLoop = async (props: Props): Promise<Response> => {
}
return {
data: {
[NodeOutputKeyEnum.loopArray]: outputValueArr
},
[DispatchNodeResponseKeyEnum.interactive]: interactiveResponse
? {
type: 'loopInteractive',
@ -157,7 +156,6 @@ export const dispatchLoop = async (props: Props): Promise<Response> => {
moduleName: name
}
],
[NodeOutputKeyEnum.loopArray]: outputValueArr,
[DispatchNodeResponseKeyEnum.newVariables]: newVariables
};
};

8
packages/service/core/workflow/dispatch/loop/runLoopStart.ts
View File

@ -18,10 +18,12 @@ type Response = DispatchNodeResultType<{
export const dispatchLoopStart = async (props: Props): Promise<Response> => {
const { params } = props;
return {
data: {
[NodeOutputKeyEnum.loopStartInput]: params.loopStartInput,
[NodeOutputKeyEnum.loopStartIndex]: params.loopStartIndex
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
loopInputValue: params.loopStartInput
},
[NodeOutputKeyEnum.loopStartInput]: params.loopStartInput,
[NodeOutputKeyEnum.loopStartIndex]: params.loopStartIndex
}
};
};

271
packages/service/core/workflow/dispatch/plugin/run.ts
View File

@ -13,19 +13,29 @@ import { type DispatchNodeResultType } from '@fastgpt/global/core/workflow/runti
import { authPluginByTmbId } from '../../../../support/permission/app/auth';
import { ReadPermissionVal } from '@fastgpt/global/support/permission/constant';
import { computedPluginUsage } from '../../../app/plugin/utils';
import { filterSystemVariables } from '../utils';
import { filterSystemVariables, getNodeErrResponse } from '../utils';
import { getPluginRunUserQuery } from '@fastgpt/global/core/workflow/utils';
import type { NodeInputKeyEnum } from '@fastgpt/global/core/workflow/constants';
import type { NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
import { getChildAppRuntimeById, splitCombinePluginId } from '../../../app/plugin/controller';
import { dispatchWorkFlow } from '../index';
import { getUserChatInfoAndAuthTeamPoints } from '../../../../support/permission/auth/team';
import { dispatchRunTool } from './runTool';
import { dispatchRunTool } from '../child/runTool';
import type { PluginRuntimeType } from '@fastgpt/global/core/app/plugin/type';
type RunPluginProps = ModuleDispatchProps<{
[NodeInputKeyEnum.forbidStream]?: boolean;
[key: string]: any;
}>;
type RunPluginResponse = DispatchNodeResultType<{}>;
type RunPluginResponse = DispatchNodeResultType<
{
[key: string]: any;
},
{
[NodeOutputKeyEnum.errorText]?: string;
}
>;
export const dispatchRunPlugin = async (props: RunPluginProps): Promise<RunPluginResponse> => {
const {
node: { pluginId, version },
@ -34,142 +44,145 @@ export const dispatchRunPlugin = async (props: RunPluginProps): Promise<RunPlugi
params: { system_forbid_stream = false, ...data } // Plugin input
} = props;
if (!pluginId) {
return Promise.reject('pluginId can not find');
return getNodeErrResponse({ error: 'pluginId can not find' });
}
// Adapt <= 4.10 system tool
const { source, pluginId: formatPluginId } = splitCombinePluginId(pluginId);
if (source === PluginSourceEnum.systemTool) {
return dispatchRunTool({
...props,
node: {
...props.node,
toolConfig: {
systemTool: {
toolId: formatPluginId
let plugin: PluginRuntimeType | undefined;
try {
// Adapt <= 4.10 system tool
const { source, pluginId: formatPluginId } = splitCombinePluginId(pluginId);
if (source === PluginSourceEnum.systemTool) {
return await dispatchRunTool({
...props,
node: {
...props.node,
toolConfig: {
systemTool: {
toolId: formatPluginId
}
}
}
}
});
}
/*
1. Team app
2. Admin selected system tool
*/
const { files } = chatValue2RuntimePrompt(query);
// auth plugin
const pluginData = await authPluginByTmbId({
appId: pluginId,
tmbId: runningAppInfo.tmbId,
per: ReadPermissionVal
});
}
/*
1. Team app
2. Admin selected system tool
*/
const { files } = chatValue2RuntimePrompt(query);
plugin = await getChildAppRuntimeById(pluginId, version);
// auth plugin
const pluginData = await authPluginByTmbId({
appId: pluginId,
tmbId: runningAppInfo.tmbId,
per: ReadPermissionVal
});
const plugin = await getChildAppRuntimeById(pluginId, version);
const outputFilterMap =
plugin.nodes
.find((node) => node.flowNodeType === FlowNodeTypeEnum.pluginOutput)
?.inputs.reduce<Record<string, boolean>>((acc, cur) => {
acc[cur.key] = cur.isToolOutput === false ? false : true;
return acc;
}, {}) ?? {};
const runtimeNodes = storeNodes2RuntimeNodes(
plugin.nodes,
getWorkflowEntryNodeIds(plugin.nodes)
).map((node) => {
// Update plugin input value
if (node.flowNodeType === FlowNodeTypeEnum.pluginInput) {
const outputFilterMap =
plugin.nodes
.find((node) => node.flowNodeType === FlowNodeTypeEnum.pluginOutput)
?.inputs.reduce<Record<string, boolean>>((acc, cur) => {
acc[cur.key] = cur.isToolOutput === false ? false : true;
return acc;
}, {}) ?? {};
const runtimeNodes = storeNodes2RuntimeNodes(
plugin.nodes,
getWorkflowEntryNodeIds(plugin.nodes)
).map((node) => {
// Update plugin input value
if (node.flowNodeType === FlowNodeTypeEnum.pluginInput) {
return {
...node,
showStatus: false,
inputs: node.inputs.map((input) => ({
...input,
value: data[input.key] ?? input.value
}))
};
}
return {
...node,
showStatus: false,
inputs: node.inputs.map((input) => ({
...input,
value: data[input.key] ?? input.value
}))
showStatus: false
};
}
return {
...node,
showStatus: false
};
});
const { externalProvider } = await getUserChatInfoAndAuthTeamPoints(runningAppInfo.tmbId);
const runtimeVariables = {
...filterSystemVariables(props.variables),
appId: String(plugin.id),
...(externalProvider ? externalProvider.externalWorkflowVariables : {})
};
const { flowResponses, flowUsages, assistantResponses, runTimes, system_memories } =
await dispatchWorkFlow({
...props,
// Rewrite stream mode
...(system_forbid_stream
? {
stream: false,
workflowStreamResponse: undefined
}
: {}),
runningAppInfo: {
id: String(plugin.id),
// 如果系统插件有 teamId 和 tmbId，则使用系统插件的 teamId 和 tmbId（管理员指定了插件作为系统插件）
teamId: plugin.teamId || runningAppInfo.teamId,
tmbId: plugin.tmbId || runningAppInfo.tmbId,
isChildApp: true
},
variables: runtimeVariables,
query: getPluginRunUserQuery({
pluginInputs: getPluginInputsFromStoreNodes(plugin.nodes),
variables: runtimeVariables,
files
}).value,
chatConfig: {},
runtimeNodes,
runtimeEdges: storeEdges2RuntimeEdges(plugin.edges)
});
const output = flowResponses.find((item) => item.moduleType === FlowNodeTypeEnum.pluginOutput);
if (output) {
output.moduleLogo = plugin.avatar;
}
const usagePoints = await computedPluginUsage({
plugin,
childrenUsage: flowUsages,
error: !!output?.pluginOutput?.error
});
return {
// 嵌套运行时，如果 childApp stream=false，实际上不会有任何内容输出给用户，所以不需要存储
assistantResponses: system_forbid_stream ? [] : assistantResponses,
system_memories,
// responseData, // debug
[DispatchNodeResponseKeyEnum.runTimes]: runTimes,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
moduleLogo: plugin.avatar,
totalPoints: usagePoints,
pluginOutput: output?.pluginOutput,
pluginDetail: pluginData?.permission?.hasWritePer // Not system plugin
? flowResponses.filter((item) => {
const filterArr = [FlowNodeTypeEnum.pluginOutput];
return !filterArr.includes(item.moduleType as any);
})
: undefined
},
[DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
{
moduleName: plugin.name,
totalPoints: usagePoints
}
],
[DispatchNodeResponseKeyEnum.toolResponses]: output?.pluginOutput
? Object.keys(output.pluginOutput)
.filter((key) => outputFilterMap[key])
.reduce<Record<string, any>>((acc, key) => {
acc[key] = output.pluginOutput![key];
return acc;
}, {})
: null,
...(output ? output.pluginOutput : {})
};
const { externalProvider } = await getUserChatInfoAndAuthTeamPoints(runningAppInfo.tmbId);
const runtimeVariables = {
...filterSystemVariables(props.variables),
appId: String(plugin.id),
...(externalProvider ? externalProvider.externalWorkflowVariables : {})
};
const { flowResponses, flowUsages, assistantResponses, runTimes, system_memories } =
await dispatchWorkFlow({
...props,
// Rewrite stream mode
...(system_forbid_stream
? {
stream: false,
workflowStreamResponse: undefined
}
: {}),
runningAppInfo: {
id: String(plugin.id),
// 如果系统插件有 teamId 和 tmbId，则使用系统插件的 teamId 和 tmbId（管理员指定了插件作为系统插件）
teamId: plugin.teamId || runningAppInfo.teamId,
tmbId: plugin.tmbId || runningAppInfo.tmbId,
isChildApp: true
},
variables: runtimeVariables,
query: getPluginRunUserQuery({
pluginInputs: getPluginInputsFromStoreNodes(plugin.nodes),
variables: runtimeVariables,
files
}).value,
chatConfig: {},
runtimeNodes,
runtimeEdges: storeEdges2RuntimeEdges(plugin.edges)
});
const output = flowResponses.find((item) => item.moduleType === FlowNodeTypeEnum.pluginOutput);
const usagePoints = await computedPluginUsage({
plugin,
childrenUsage: flowUsages,
error: !!output?.pluginOutput?.error
});
return {
data: output ? output.pluginOutput : {},
// 嵌套运行时，如果 childApp stream=false，实际上不会有任何内容输出给用户，所以不需要存储
assistantResponses: system_forbid_stream ? [] : assistantResponses,
system_memories,
// responseData, // debug
[DispatchNodeResponseKeyEnum.runTimes]: runTimes,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
moduleLogo: plugin.avatar,
totalPoints: usagePoints,
pluginOutput: output?.pluginOutput,
pluginDetail: pluginData?.permission?.hasWritePer // Not system plugin
? flowResponses.filter((item) => {
const filterArr = [FlowNodeTypeEnum.pluginOutput];
return !filterArr.includes(item.moduleType as any);
})
: undefined
},
[DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
{
moduleName: plugin.name,
totalPoints: usagePoints
}
],
[DispatchNodeResponseKeyEnum.toolResponses]: output?.pluginOutput
? Object.keys(output.pluginOutput)
.filter((key) => outputFilterMap[key])
.reduce<Record<string, any>>((acc, key) => {
acc[key] = output.pluginOutput![key];
return acc;
}, {})
: null
};
} catch (error) {
return getNodeErrResponse({ error, customNodeResponse: { moduleLogo: plugin?.avatar } });
}
};

203
packages/service/core/workflow/dispatch/plugin/runApp.ts
View File

@ -1,203 +0,0 @@
import type { ChatItemType } from '@fastgpt/global/core/chat/type.d';
import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/type';
import { dispatchWorkFlow } from '../index';
import { ChatRoleEnum } from '@fastgpt/global/core/chat/constants';
import { SseResponseEventEnum } from '@fastgpt/global/core/workflow/runtime/constants';
import {
getWorkflowEntryNodeIds,
storeEdges2RuntimeEdges,
rewriteNodeOutputByHistories,
storeNodes2RuntimeNodes,
textAdaptGptResponse
} from '@fastgpt/global/core/workflow/runtime/utils';
import type { NodeInputKeyEnum, NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
import { filterSystemVariables, getHistories } from '../utils';
import { chatValue2RuntimePrompt, runtimePrompt2ChatsValue } from '@fastgpt/global/core/chat/adapt';
import { type DispatchNodeResultType } from '@fastgpt/global/core/workflow/runtime/type';
import { authAppByTmbId } from '../../../../support/permission/app/auth';
import { ReadPermissionVal } from '@fastgpt/global/support/permission/constant';
import { getAppVersionById } from '../../../app/version/controller';
import { parseUrlToFileType } from '@fastgpt/global/common/file/tools';
import { type ChildrenInteractive } from '@fastgpt/global/core/workflow/template/system/interactive/type';
import { getUserChatInfoAndAuthTeamPoints } from '../../../../support/permission/auth/team';
type Props = ModuleDispatchProps<{
[NodeInputKeyEnum.userChatInput]: string;
[NodeInputKeyEnum.history]?: ChatItemType[] | number;
[NodeInputKeyEnum.fileUrlList]?: string[];
[NodeInputKeyEnum.forbidStream]?: boolean;
[NodeInputKeyEnum.fileUrlList]?: string[];
}>;
type Response = DispatchNodeResultType<{
[DispatchNodeResponseKeyEnum.interactive]?: ChildrenInteractive;
[NodeOutputKeyEnum.answerText]: string;
[NodeOutputKeyEnum.history]: ChatItemType[];
}>;
export const dispatchRunAppNode = async (props: Props): Promise<Response> => {
const {
runningAppInfo,
histories,
query,
lastInteractive,
node: { pluginId: appId, version },
workflowStreamResponse,
params,
variables
} = props;
const {
system_forbid_stream = false,
userChatInput,
history,
fileUrlList,
...childrenAppVariables
} = params;
const { files } = chatValue2RuntimePrompt(query);
const userInputFiles = (() => {
if (fileUrlList) {
return fileUrlList.map((url) => parseUrlToFileType(url)).filter(Boolean);
}
// Adapt version 4.8.13 upgrade
return files;
})();
if (!userChatInput && !userInputFiles) {
return Promise.reject('Input is empty');
}
if (!appId) {
return Promise.reject('pluginId is empty');
}
// Auth the app by tmbId(Not the user, but the workflow user)
const { app: appData } = await authAppByTmbId({
appId: appId,
tmbId: runningAppInfo.tmbId,
per: ReadPermissionVal
});
const { nodes, edges, chatConfig } = await getAppVersionById({
appId,
versionId: version,
app: appData
});
const childStreamResponse = system_forbid_stream ? false : props.stream;
// Auto line
if (childStreamResponse) {
workflowStreamResponse?.({
event: SseResponseEventEnum.answer,
data: textAdaptGptResponse({
text: '\n'
})
});
}
const chatHistories = getHistories(history, histories);
// Rewrite children app variables
const systemVariables = filterSystemVariables(variables);
const { externalProvider } = await getUserChatInfoAndAuthTeamPoints(appData.tmbId);
const childrenRunVariables = {
...systemVariables,
...childrenAppVariables,
histories: chatHistories,
appId: String(appData._id),
...(externalProvider ? externalProvider.externalWorkflowVariables : {})
};
const childrenInteractive =
lastInteractive?.type === 'childrenInteractive'
? lastInteractive.params.childrenResponse
: undefined;
const runtimeNodes = rewriteNodeOutputByHistories(
storeNodes2RuntimeNodes(
nodes,
getWorkflowEntryNodeIds(nodes, childrenInteractive || undefined)
),
childrenInteractive
);
const runtimeEdges = storeEdges2RuntimeEdges(edges, childrenInteractive);
const theQuery = childrenInteractive
? query
: runtimePrompt2ChatsValue({ files: userInputFiles, text: userChatInput });
const {
flowResponses,
flowUsages,
assistantResponses,
runTimes,
workflowInteractiveResponse,
system_memories
} = await dispatchWorkFlow({
...props,
lastInteractive: childrenInteractive,
// Rewrite stream mode
...(system_forbid_stream
? {
stream: false,
workflowStreamResponse: undefined
}
: {}),
runningAppInfo: {
id: String(appData._id),
teamId: String(appData.teamId),
tmbId: String(appData.tmbId),
isChildApp: true
},
runtimeNodes,
runtimeEdges,
histories: chatHistories,
variables: childrenRunVariables,
query: theQuery,
chatConfig
});
const completeMessages = chatHistories.concat([
{
obj: ChatRoleEnum.Human,
value: query
},
{
obj: ChatRoleEnum.AI,
value: assistantResponses
}
]);
const { text } = chatValue2RuntimePrompt(assistantResponses);
const usagePoints = flowUsages.reduce((sum, item) => sum + (item.totalPoints || 0), 0);
return {
system_memories,
[DispatchNodeResponseKeyEnum.interactive]: workflowInteractiveResponse
? {
type: 'childrenInteractive',
params: {
childrenResponse: workflowInteractiveResponse
}
}
: undefined,
assistantResponses: system_forbid_stream ? [] : assistantResponses,
[DispatchNodeResponseKeyEnum.runTimes]: runTimes,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
moduleLogo: appData.avatar,
totalPoints: usagePoints,
query: userChatInput,
textOutput: text,
pluginDetail: appData.permission.hasWritePer ? flowResponses : undefined,
mergeSignId: props.node.nodeId
},
[DispatchNodeResponseKeyEnum.nodeDispatchUsages]: [
{
moduleName: appData.name,
totalPoints: usagePoints
}
],
[DispatchNodeResponseKeyEnum.toolResponses]: text,
answerText: text,
history: completeMessages
};
};

29
packages/service/core/workflow/dispatch/plugin/runInput.ts
View File

@ -2,13 +2,22 @@ import { chatValue2RuntimePrompt } from '@fastgpt/global/core/chat/adapt';
import { ChatFileTypeEnum } from '@fastgpt/global/core/chat/constants';
import { NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/type';
import type {
DispatchNodeResultType,
ModuleDispatchProps
} from '@fastgpt/global/core/workflow/runtime/type';
export type PluginInputProps = ModuleDispatchProps<{
[key: string]: any;
}>;
export type PluginInputResponse = DispatchNodeResultType<{
[NodeOutputKeyEnum.userFiles]?: string[];
[key: string]: any;
}>;
export const dispatchPluginInput = (props: PluginInputProps) => {
export const dispatchPluginInput = async (
props: PluginInputProps
): Promise<PluginInputResponse> => {
const { params, query } = props;
const { files } = chatValue2RuntimePrompt(query);
@ -33,12 +42,14 @@ export const dispatchPluginInput = (props: PluginInputProps) => {
}
return {
...params,
[DispatchNodeResponseKeyEnum.nodeResponse]: {},
[NodeOutputKeyEnum.userFiles]: files
.map((item) => {
return item?.url ?? '';
})
.filter(Boolean)
data: {
...params,
[NodeOutputKeyEnum.userFiles]: files
.map((item) => {
return item?.url ?? '';
})
.filter(Boolean)
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {}
};
};

4
packages/service/core/workflow/dispatch/tools/answer.ts
View File

@ -30,7 +30,9 @@ export const dispatchAnswer = (props: Record<string, any>): AnswerResponse => {
});
return {
[NodeOutputKeyEnum.answerText]: responseText,
data: {
[NodeOutputKeyEnum.answerText]: responseText
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
textOutput: formatText
}

60
packages/service/core/workflow/dispatch/code/run.ts → packages/service/core/workflow/dispatch/tools/codeSandbox.ts
View File

@ -2,20 +2,26 @@ import type { ModuleDispatchProps } from '@fastgpt/global/core/workflow/runtime/
import { NodeInputKeyEnum, NodeOutputKeyEnum } from '@fastgpt/global/core/workflow/constants';
import { type DispatchNodeResultType } from '@fastgpt/global/core/workflow/runtime/type';
import axios from 'axios';
import { formatHttpError } from '../utils';
import { DispatchNodeResponseKeyEnum } from '@fastgpt/global/core/workflow/runtime/constants';
import { SandboxCodeTypeEnum } from '@fastgpt/global/core/workflow/template/system/sandbox/constants';
import { getErrText } from '@fastgpt/global/common/error/utils';
import { getNodeErrResponse } from '../utils';
type RunCodeType = ModuleDispatchProps<{
[NodeInputKeyEnum.codeType]: string;
[NodeInputKeyEnum.code]: string;
[NodeInputKeyEnum.addInputParam]: Record<string, any>;
}>;
type RunCodeResponse = DispatchNodeResultType<{
[NodeOutputKeyEnum.error]?: any;
[NodeOutputKeyEnum.rawResponse]?: Record<string, any>;
[key: string]: any;
}>;
type RunCodeResponse = DispatchNodeResultType<
{
[NodeOutputKeyEnum.error]?: any; // @deprecated
[NodeOutputKeyEnum.rawResponse]?: Record<string, any>;
[key: string]: any;
},
{
[NodeOutputKeyEnum.error]: string;
}
>;
function getURL(codeType: string): string {
if (codeType == SandboxCodeTypeEnum.py) {
@ -25,14 +31,21 @@ function getURL(codeType: string): string {
}
}
export const dispatchRunCode = async (props: RunCodeType): Promise<RunCodeResponse> => {
export const dispatchCodeSandbox = async (props: RunCodeType): Promise<RunCodeResponse> => {
const {
node: { catchError },
params: { codeType, code, [NodeInputKeyEnum.addInputParam]: customVariables }
} = props;
if (!process.env.SANDBOX_URL) {
return {
[NodeOutputKeyEnum.error]: 'Can not find SANDBOX_URL in env'
error: {
[NodeOutputKeyEnum.error]: 'Can not find SANDBOX_URL in env'
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
errorText: 'Can not find SANDBOX_URL in env',
customInputs: customVariables
}
};
}
@ -51,24 +64,43 @@ export const dispatchRunCode = async (props: RunCodeType): Promise<RunCodeRespon
if (runResult.success) {
return {
[NodeOutputKeyEnum.rawResponse]: runResult.data.codeReturn,
data: {
[NodeOutputKeyEnum.rawResponse]: runResult.data.codeReturn,
...runResult.data.codeReturn
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
customInputs: customVariables,
customOutputs: runResult.data.codeReturn,
codeLog: runResult.data.log
},
[DispatchNodeResponseKeyEnum.toolResponses]: runResult.data.codeReturn,
...runResult.data.codeReturn
[DispatchNodeResponseKeyEnum.toolResponses]: runResult.data.codeReturn
};
} else {
return Promise.reject('Run code failed');
throw new Error('Run code failed');
}
} catch (error) {
const text = getErrText(error);
// @adapt
if (catchError === undefined) {
return {
data: {
[NodeOutputKeyEnum.error]: { message: text }
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
customInputs: customVariables,
errorText: text
}
};
}
return {
[NodeOutputKeyEnum.error]: formatHttpError(error),
error: {
[NodeOutputKeyEnum.error]: text
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
customInputs: customVariables,
error: formatHttpError(error)
errorText: text
}
};
}

42
packages/service/core/workflow/dispatch/tools/http468.ts
View File

@ -47,10 +47,14 @@ type HttpRequestProps = ModuleDispatchProps<{
[NodeInputKeyEnum.httpTimeout]?: number;
[key: string]: any;
}>;
type HttpResponse = DispatchNodeResultType<{
[NodeOutputKeyEnum.error]?: object;
[key: string]: any;
}>;
type HttpResponse = DispatchNodeResultType<
{
[key: string]: any;
},
{
[NodeOutputKeyEnum.error]?: string;
}
>;
const UNDEFINED_SIGN = 'UNDEFINED_SIGN';
@ -349,7 +353,10 @@ export const dispatchHttp468Request = async (props: HttpRequestProps): Promise<H
}
return {
...results,
data: {
[NodeOutputKeyEnum.httpRawResponse]: rawResponse,
...results
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
totalPoints: 0,
params: Object.keys(params).length > 0 ? params : undefined,
@ -358,21 +365,36 @@ export const dispatchHttp468Request = async (props: HttpRequestProps): Promise<H
httpResult: rawResponse
},
[DispatchNodeResponseKeyEnum.toolResponses]:
Object.keys(results).length > 0 ? results : rawResponse,
[NodeOutputKeyEnum.httpRawResponse]: rawResponse
Object.keys(results).length > 0 ? results : rawResponse
};
} catch (error) {
addLog.error('Http request error', error);
// @adapt
if (node.catchError === undefined) {
return {
data: {
[NodeOutputKeyEnum.error]: getErrText(error)
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
params: Object.keys(params).length > 0 ? params : undefined,
body: Object.keys(formattedRequestBody).length > 0 ? formattedRequestBody : undefined,
headers: Object.keys(publicHeaders).length > 0 ? publicHeaders : undefined,
httpResult: { error: formatHttpError(error) }
}
};
}
return {
[NodeOutputKeyEnum.error]: formatHttpError(error),
error: {
[NodeOutputKeyEnum.error]: getErrText(error)
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
params: Object.keys(params).length > 0 ? params : undefined,
body: Object.keys(formattedRequestBody).length > 0 ? formattedRequestBody : undefined,
headers: Object.keys(publicHeaders).length > 0 ? publicHeaders : undefined,
httpResult: { error: formatHttpError(error) }
},
[NodeOutputKeyEnum.httpRawResponse]: getErrText(error)
}
};
}
};

6
packages/service/core/workflow/dispatch/tools/queryExternsion.ts
View File

@ -59,6 +59,9 @@ export const dispatchQueryExtension = async ({
});
return {
data: {
[NodeOutputKeyEnum.text]: JSON.stringify(filterSameQueries)
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
totalPoints,
model: modelName,
@ -75,7 +78,6 @@ export const dispatchQueryExtension = async ({
inputTokens,
outputTokens
}
],
[NodeOutputKeyEnum.text]: JSON.stringify(filterSameQueries)
]
};
};

55
packages/service/core/workflow/dispatch/tools/readFiles.ts
View File

@ -14,6 +14,7 @@ import { parseFileExtensionFromUrl } from '@fastgpt/global/common/string/tools';
import { addLog } from '../../../../common/system/log';
import { addRawTextBuffer, getRawTextBuffer } from '../../../../common/buffer/rawText/controller';
import { addMinutes } from 'date-fns';
import { getNodeErrResponse } from '../utils';
type Props = ModuleDispatchProps<{
[NodeInputKeyEnum.fileUrlList]: string[];
@ -58,31 +59,37 @@ export const dispatchReadFiles = async (props: Props): Promise<Response> => {
// Get files from histories
const filesFromHistories = version !== '489' ? [] : getHistoryFileLinks(histories);
const { text, readFilesResult } = await getFileContentFromLinks({
// Concat fileUrlList and filesFromHistories; remove not supported files
urls: [...fileUrlList, ...filesFromHistories],
requestOrigin,
maxFiles,
teamId,
tmbId,
customPdfParse
});
try {
const { text, readFilesResult } = await getFileContentFromLinks({
// Concat fileUrlList and filesFromHistories; remove not supported files
urls: [...fileUrlList, ...filesFromHistories],
requestOrigin,
maxFiles,
teamId,
tmbId,
customPdfParse
});
return {
[NodeOutputKeyEnum.text]: text,
[DispatchNodeResponseKeyEnum.nodeResponse]: {
readFiles: readFilesResult.map((item) => ({
name: item?.filename || '',
url: item?.url || ''
})),
readFilesResult: readFilesResult
.map((item) => item?.nodeResponsePreviewText ?? '')
.join('\n******\n')
},
[DispatchNodeResponseKeyEnum.toolResponses]: {
fileContent: text
}
};
return {
data: {
[NodeOutputKeyEnum.text]: text
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
readFiles: readFilesResult.map((item) => ({
name: item?.filename || '',
url: item?.url || ''
})),
readFilesResult: readFilesResult
.map((item) => item?.nodeResponsePreviewText ?? '')
.join('\n******\n')
},
[DispatchNodeResponseKeyEnum.toolResponses]: {
fileContent: text
}
};
} catch (error) {
return getNodeErrResponse({ error });
}
};
export const getHistoryFileLinks = (histories: ChatItemType[]) => {

4
packages/service/core/workflow/dispatch/tools/runIfElse.ts
View File

@ -157,7 +157,9 @@ export const dispatchIfElse = async (props: Props): Promise<Response> => {
});
return {
[NodeOutputKeyEnum.ifElseResult]: res,
data: {
[NodeOutputKeyEnum.ifElseResult]: res
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
totalPoints: 0,
ifElseResult: res

25
packages/service/core/workflow/dispatch/tools/runLaf.ts
View File

@ -6,16 +6,21 @@ import { valueTypeFormat } from '@fastgpt/global/core/workflow/runtime/utils';
import { SERVICE_LOCAL_HOST } from '../../../../common/system/tools';
import { addLog } from '../../../../common/system/log';
import { type DispatchNodeResultType } from '@fastgpt/global/core/workflow/runtime/type';
import { getErrText } from '@fastgpt/global/common/error/utils';
type LafRequestProps = ModuleDispatchProps<{
[NodeInputKeyEnum.httpReqUrl]: string;
[NodeInputKeyEnum.addInputParam]: Record<string, any>;
[key: string]: any;
}>;
type LafResponse = DispatchNodeResultType<{
[NodeOutputKeyEnum.failed]?: boolean;
[key: string]: any;
}>;
type LafResponse = DispatchNodeResultType<
{
[key: string]: any;
},
{
[NodeOutputKeyEnum.errorText]?: string;
}
>;
const UNDEFINED_SIGN = 'UNDEFINED_SIGN';
@ -78,20 +83,24 @@ export const dispatchLafRequest = async (props: LafRequestProps): Promise<LafRes
}
return {
data: {
[NodeOutputKeyEnum.httpRawResponse]: rawResponse,
...results
},
assistantResponses: [],
[DispatchNodeResponseKeyEnum.nodeResponse]: {
totalPoints: 0,
body: Object.keys(requestBody).length > 0 ? requestBody : undefined,
httpResult: rawResponse
},
[DispatchNodeResponseKeyEnum.toolResponses]: rawResponse,
[NodeOutputKeyEnum.httpRawResponse]: rawResponse,
...results
[DispatchNodeResponseKeyEnum.toolResponses]: rawResponse
};
} catch (error) {
addLog.error('Http request error', error);
return {
[NodeOutputKeyEnum.failed]: true,
error: {
[NodeOutputKeyEnum.errorText]: getErrText(error)
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
totalPoints: 0,
body: Object.keys(requestBody).length > 0 ? requestBody : undefined,

4
packages/service/core/workflow/dispatch/tools/textEditor.ts
View File

@ -40,7 +40,9 @@ export const dispatchTextEditor = (props: Record<string, any>): Response => {
});
return {
[NodeOutputKeyEnum.text]: textResult,
data: {
[NodeOutputKeyEnum.text]: textResult
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
textOutput: textResult
}

32
packages/service/core/workflow/dispatch/utils.ts
View File

@ -9,7 +9,10 @@ import {
} from '@fastgpt/global/core/workflow/runtime/type';
import { responseWrite } from '../../../common/response';
import { type NextApiResponse } from 'next';
import { SseResponseEventEnum } from '@fastgpt/global/core/workflow/runtime/constants';
import {
DispatchNodeResponseKeyEnum,
SseResponseEventEnum
} from '@fastgpt/global/core/workflow/runtime/constants';
import { getNanoid } from '@fastgpt/global/common/string/tools';
import { type SearchDataResponseItemType } from '@fastgpt/global/core/dataset/type';
import { getMCPToolRuntimeNode } from '@fastgpt/global/core/app/mcpTools/utils';
@ -206,3 +209,30 @@ export const rewriteRuntimeWorkFlow = (
}
}
};
export const getNodeErrResponse = ({
error,
customErr,
customNodeResponse
}: {
error: any;
customErr?: Record<string, any>;
customNodeResponse?: Record<string, any>;
}) => {
const errorText = getErrText(error);
return {
error: {
[NodeOutputKeyEnum.errorText]: errorText,
...(typeof customErr === 'object' ? customErr : {})
},
[DispatchNodeResponseKeyEnum.nodeResponse]: {
errorText,
...(typeof customNodeResponse === 'object' ? customNodeResponse : {})
},
[DispatchNodeResponseKeyEnum.toolResponses]: {
error: errorText,
...(typeof customErr === 'object' ? customErr : {})
}
};
};

2
packages/service/package.json
View File

@ -3,7 +3,7 @@
"version": "1.0.0",
"type": "module",
"dependencies": {
"@fastgpt-sdk/plugin": "^0.1.1",
"@fastgpt-sdk/plugin": "^0.1.2",
"@fastgpt/global": "workspace:*",
"@modelcontextprotocol/sdk": "^1.12.1",
"@node-rs/jieba": "2.0.1",

64
packages/service/support/permission/evaluation/auth.ts Normal file
View File

@ -0,0 +1,64 @@
import { parseHeaderCert } from '../controller';
import { authAppByTmbId } from '../app/auth';
import {
ManagePermissionVal,
ReadPermissionVal
} from '@fastgpt/global/support/permission/constant';
import type { EvaluationSchemaType } from '@fastgpt/global/core/app/evaluation/type';
import type { AuthModeType } from '../type';
import { MongoEvaluation } from '../../../core/app/evaluation/evalSchema';
export const authEval = async ({
evalId,
per = ReadPermissionVal,
...props
}: AuthModeType & {
evalId: string;
}): Promise<{
evaluation: EvaluationSchemaType;
tmbId: string;
teamId: string;
}> => {
const { teamId, tmbId, isRoot } = await parseHeaderCert(props);
const evaluation = await MongoEvaluation.findById(evalId, 'tmbId').lean();
if (!evaluation) {
return Promise.reject('Evaluation not found');
}
if (String(evaluation.tmbId) === tmbId) {
return {
teamId,
tmbId,
evaluation
};
}
// App read per
if (per === ReadPermissionVal) {
await authAppByTmbId({
tmbId,
appId: evaluation.appId,
per: ReadPermissionVal,
isRoot
});
return {
teamId,
tmbId,
evaluation
};
}
// Write per
await authAppByTmbId({
tmbId,
appId: evaluation.appId,
per: ManagePermissionVal,
isRoot
});
return {
teamId,
tmbId,
evaluation
};
};

4
packages/service/support/permission/teamLimit.ts
View File

@ -113,10 +113,6 @@ export const checkTeamDatasetLimit = async (teamId: string) => {
return Promise.reject(SystemErrEnum.licenseDatasetAmountLimit);
}
}
// Open source check
if (!global.feConfigs.isPlus && datasetCount >= 30) {
return Promise.reject(SystemErrEnum.communityVersionNumLimit);
}
};
export const checkTeamDatasetSyncPermission = async (teamId: string) => {

43
packages/service/support/wallet/usage/controller.ts
View File

@ -235,3 +235,46 @@ export const pushLLMTrainingUsage = async ({
return { totalPoints };
};
export const createEvaluationUsage = async ({
teamId,
tmbId,
appName,
model,
session
}: {
teamId: string;
tmbId: string;
appName: string;
model: string;
session?: ClientSession;
}) => {
const [{ _id: usageId }] = await MongoUsage.create(
[
{
teamId,
tmbId,
appName,
source: UsageSourceEnum.evaluation,
totalPoints: 0,
list: [
{
moduleName: i18nT('account_usage:generate_answer'),
amount: 0,
count: 0
},
{
moduleName: i18nT('account_usage:answer_accuracy'),
amount: 0,
inputTokens: 0,
outputTokens: 0,
model
}
]
}
],
{ session, ordered: true }
);
return { usageId };
};

10
packages/service/support/wallet/usage/type.d.ts vendored
View File

@ -1,9 +1,13 @@
export type ConcatBillQueueItemType = {
billId: string;
billId: string; // usageId
listIndex?: number;
totalPoints: number;
inputTokens: number;
outputTokens: number;
// Model usage
inputTokens?: number;
outputTokens?: number;
// Times
count?: number;
};
declare global {

53
packages/service/type/env.d.ts vendored Normal file
View File

@ -0,0 +1,53 @@
declare global {
namespace NodeJS {
interface ProcessEnv {
LOG_DEPTH: string;
DB_MAX_LINK: string;
FILE_TOKEN_KEY: string;
AES256_SECRET_KEY: string;
ROOT_KEY: string;
OPENAI_BASE_URL: string;
CHAT_API_KEY: string;
AIPROXY_API_ENDPOINT: string;
AIPROXY_API_TOKEN: string;
MULTIPLE_DATA_TO_BASE64: string;
MONGODB_URI: string;
MONGODB_LOG_URI?: string;
PG_URL: string;
OCEANBASE_URL: string;
MILVUS_ADDRESS: string;
MILVUS_TOKEN: string;
SANDBOX_URL: string;
FE_DOMAIN: string;
FILE_DOMAIN: string;
LOG_LEVEL?: string;
STORE_LOG_LEVEL?: string;
USE_IP_LIMIT?: string;
WORKFLOW_MAX_RUN_TIMES?: string;
WORKFLOW_MAX_LOOP_TIMES?: string;
CHECK_INTERNAL_IP?: string;
ALLOWED_ORIGINS?: string;
SHOW_COUPON?: string;
CONFIG_JSON_PATH?: string;
PASSWORD_LOGIN_LOCK_SECONDS?: string;
PASSWORD_EXPIRED_MONTH?: string;
MAX_LOGIN_SESSION?: string;
// 安全配置
// 密码登录锁定时间
PASSWORD_LOGIN_LOCK_SECONDS?: string;
// Signoz
SIGNOZ_BASE_URL?: string;
SIGNOZ_SERVICE_NAME?: string;
CHAT_LOG_URL?: string;
CHAT_LOG_INTERVAL?: string;
CHAT_LOG_SOURCE_ID_PREFIX?: string;
NEXT_PUBLIC_BASE_URL: string;
}
}
}
export {};

25
packages/web/components/common/Icon/constants.ts
View File

@ -20,11 +20,11 @@ export const iconPaths = {
'common/addLight': () => import('./icons/common/addLight.svg'),
'common/addUser': () => import('./icons/common/addUser.svg'),
'common/administrator': () => import('./icons/common/administrator.svg'),
'common/audit': () => import('./icons/common/audit.svg'),
'common/alipay': () => import('./icons/common/alipay.svg'),
'common/app': () => import('./icons/common/app.svg'),
'common/arrowLeft': () => import('./icons/common/arrowLeft.svg'),
'common/arrowRight': () => import('./icons/common/arrowRight.svg'),
'common/audit': () => import('./icons/common/audit.svg'),
'common/backFill': () => import('./icons/common/backFill.svg'),
'common/backLight': () => import('./icons/common/backLight.svg'),
'common/billing': () => import('./icons/common/billing.svg'),
@ -47,6 +47,7 @@ export const iconPaths = {
'common/editor/resizer': () => import('./icons/common/editor/resizer.svg'),
'common/ellipsis': () => import('./icons/common/ellipsis.svg'),
'common/enable': () => import('./icons/common/enable.svg'),
'common/error': () => import('./icons/common/error.svg'),
'common/errorFill': () => import('./icons/common/errorFill.svg'),
'common/file/move': () => import('./icons/common/file/move.svg'),
'common/fileNotFound': () => import('./icons/common/fileNotFound.svg'),
@ -111,9 +112,9 @@ export const iconPaths = {
'common/tickFill': () => import('./icons/common/tickFill.svg'),
'common/toolkit': () => import('./icons/common/toolkit.svg'),
'common/trash': () => import('./icons/common/trash.svg'),
'common/upRightArrowLight': () => import('./icons/common/upRightArrowLight.svg'),
'common/uploadFileFill': () => import('./icons/common/uploadFileFill.svg'),
'common/upperRight': () => import('./icons/common/upperRight.svg'),
'common/upRightArrowLight': () => import('./icons/common/upRightArrowLight.svg'),
'common/userInfo': () => import('./icons/common/userInfo.svg'),
'common/variable': () => import('./icons/common/variable.svg'),
'common/viewLight': () => import('./icons/common/viewLight.svg'),
@ -150,8 +151,6 @@ export const iconPaths = {
'core/app/simpleMode/tts': () => import('./icons/core/app/simpleMode/tts.svg'),
'core/app/simpleMode/variable': () => import('./icons/core/app/simpleMode/variable.svg'),
'core/app/simpleMode/whisper': () => import('./icons/core/app/simpleMode/whisper.svg'),
'core/app/templates/TranslateRobot': () =>
import('./icons/core/app/templates/TranslateRobot.svg'),
'core/app/templates/animalLife': () => import('./icons/core/app/templates/animalLife.svg'),
'core/app/templates/chinese': () => import('./icons/core/app/templates/chinese.svg'),
'core/app/templates/divination': () => import('./icons/core/app/templates/divination.svg'),
@ -161,6 +160,8 @@ export const iconPaths = {
'core/app/templates/plugin-dalle': () => import('./icons/core/app/templates/plugin-dalle.svg'),
'core/app/templates/plugin-feishu': () => import('./icons/core/app/templates/plugin-feishu.svg'),
'core/app/templates/stock': () => import('./icons/core/app/templates/stock.svg'),
'core/app/templates/TranslateRobot': () =>
import('./icons/core/app/templates/TranslateRobot.svg'),
'core/app/toolCall': () => import('./icons/core/app/toolCall.svg'),
'core/app/ttsFill': () => import('./icons/core/app/ttsFill.svg'),
'core/app/type/httpPlugin': () => import('./icons/core/app/type/httpPlugin.svg'),
@ -179,7 +180,6 @@ export const iconPaths = {
'core/app/variable/input': () => import('./icons/core/app/variable/input.svg'),
'core/app/variable/select': () => import('./icons/core/app/variable/select.svg'),
'core/app/variable/textarea': () => import('./icons/core/app/variable/textarea.svg'),
'core/chat/QGFill': () => import('./icons/core/chat/QGFill.svg'),
'core/chat/backText': () => import('./icons/core/chat/backText.svg'),
'core/chat/cancelSpeak': () => import('./icons/core/chat/cancelSpeak.svg'),
'core/chat/chatFill': () => import('./icons/core/chat/chatFill.svg'),
@ -196,6 +196,7 @@ export const iconPaths = {
'core/chat/fileSelect': () => import('./icons/core/chat/fileSelect.svg'),
'core/chat/finishSpeak': () => import('./icons/core/chat/finishSpeak.svg'),
'core/chat/imgSelect': () => import('./icons/core/chat/imgSelect.svg'),
'core/chat/QGFill': () => import('./icons/core/chat/QGFill.svg'),
'core/chat/quoteFill': () => import('./icons/core/chat/quoteFill.svg'),
'core/chat/quoteSign': () => import('./icons/core/chat/quoteSign.svg'),
'core/chat/recordFill': () => import('./icons/core/chat/recordFill.svg'),
@ -203,6 +204,7 @@ export const iconPaths = {
'core/chat/sendLight': () => import('./icons/core/chat/sendLight.svg'),
'core/chat/setTopLight': () => import('./icons/core/chat/setTopLight.svg'),
'core/chat/sideLine': () => import('./icons/core/chat/sideLine.svg'),
'core/chat/sidebar/logout': () => import('./icons/core/chat/sidebar/logout.svg'),
'core/chat/speaking': () => import('./icons/core/chat/speaking.svg'),
'core/chat/stopSpeech': () => import('./icons/core/chat/stopSpeech.svg'),
'core/chat/think': () => import('./icons/core/chat/think.svg'),
@ -283,13 +285,12 @@ export const iconPaths = {
'core/workflow/redo': () => import('./icons/core/workflow/redo.svg'),
'core/workflow/revertVersion': () => import('./icons/core/workflow/revertVersion.svg'),
'core/workflow/runError': () => import('./icons/core/workflow/runError.svg'),
'core/workflow/running': () => import('./icons/core/workflow/running.svg'),
'core/workflow/runSkip': () => import('./icons/core/workflow/runSkip.svg'),
'core/workflow/runSuccess': () => import('./icons/core/workflow/runSuccess.svg'),
'core/workflow/running': () => import('./icons/core/workflow/running.svg'),
'core/workflow/template/BI': () => import('./icons/core/workflow/template/BI.svg'),
'core/workflow/template/FileRead': () => import('./icons/core/workflow/template/FileRead.svg'),
'core/workflow/template/aiChat': () => import('./icons/core/workflow/template/aiChat.svg'),
'core/workflow/template/baseChart': () => import('./icons/core/workflow/template/baseChart.svg'),
'core/workflow/template/BI': () => import('./icons/core/workflow/template/BI.svg'),
'core/workflow/template/bing': () => import('./icons/core/workflow/template/bing.svg'),
'core/workflow/template/bocha': () => import('./icons/core/workflow/template/bocha.svg'),
'core/workflow/template/codeRun': () => import('./icons/core/workflow/template/codeRun.svg'),
@ -306,6 +307,7 @@ export const iconPaths = {
'core/workflow/template/extractJson': () =>
import('./icons/core/workflow/template/extractJson.svg'),
'core/workflow/template/fetchUrl': () => import('./icons/core/workflow/template/fetchUrl.svg'),
'core/workflow/template/FileRead': () => import('./icons/core/workflow/template/FileRead.svg'),
'core/workflow/template/formInput': () => import('./icons/core/workflow/template/formInput.svg'),
'core/workflow/template/getTime': () => import('./icons/core/workflow/template/getTime.svg'),
'core/workflow/template/google': () => import('./icons/core/workflow/template/google.svg'),
@ -335,12 +337,12 @@ export const iconPaths = {
'core/workflow/template/textConcat': () =>
import('./icons/core/workflow/template/textConcat.svg'),
'core/workflow/template/toolCall': () => import('./icons/core/workflow/template/toolCall.svg'),
'core/workflow/template/toolParams': () =>
import('./icons/core/workflow/template/toolParams.svg'),
'core/workflow/template/toolkitActive': () =>
import('./icons/core/workflow/template/toolkitActive.svg'),
'core/workflow/template/toolkitInactive': () =>
import('./icons/core/workflow/template/toolkitInactive.svg'),
'core/workflow/template/toolParams': () =>
import('./icons/core/workflow/template/toolParams.svg'),
'core/workflow/template/userSelect': () =>
import('./icons/core/workflow/template/userSelect.svg'),
'core/workflow/template/variable': () => import('./icons/core/workflow/template/variable.svg'),
@ -389,6 +391,7 @@ export const iconPaths = {
key: () => import('./icons/key.svg'),
keyPrimary: () => import('./icons/keyPrimary.svg'),
loading: () => import('./icons/loading.svg'),
mcp: () => import('./icons/mcp.svg'),
menu: () => import('./icons/menu.svg'),
minus: () => import('./icons/minus.svg'),
'modal/AddClb': () => import('./icons/modal/AddClb.svg'),
@ -400,10 +403,10 @@ export const iconPaths = {
'modal/selectSource': () => import('./icons/modal/selectSource.svg'),
'modal/setting': () => import('./icons/modal/setting.svg'),
'modal/teamPlans': () => import('./icons/modal/teamPlans.svg'),
'model/BAAI': () => import('./icons/model/BAAI.svg'),
'model/alicloud': () => import('./icons/model/alicloud.svg'),
'model/aws': () => import('./icons/model/aws.svg'),
'model/azure': () => import('./icons/model/azure.svg'),
'model/BAAI': () => import('./icons/model/BAAI.svg'),
'model/baichuan': () => import('./icons/model/baichuan.svg'),
'model/chatglm': () => import('./icons/model/chatglm.svg'),
'model/claude': () => import('./icons/model/claude.svg'),

Some files were not shown because too many files have changed in this diff Show More