Sultan
/
Flowise
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'main' into feature/ChatHistory2

This commit is contained in:
chungyau97 2023-09-19 14:08:04 +08:00
parent f7178074ad 79545d0e9b
commit 922ba896ec
22 changed files with 415 additions and 305 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
CONTRIBUTING-ZH.md
View File

@ -118,25 +118,26 @@ Flowise 在一个单一的单体存储库中有 3 个不同的模块。
Flowise 支持不同的环境变量来配置您的实例。您可以在 `packages/server` 文件夹中的 `.env` 文件中指定以下变量。阅读[更多信息](https://docs.flowiseai.com/environment-variables)
| 变量名 | 描述 | 类型 | 默认值 |
| -------------------------- | ------------------------------------------------------ | ----------------------------------------------- | ----------------------------------- |
| PORT | Flowise 运行的 HTTP 端口 | 数字 | 3000 |
| FLOWISE_USERNAME | 登录用户名 | 字符串 | |
| FLOWISE_PASSWORD | 登录密码 | 字符串 | |
| DEBUG | 打印组件的日志 | 布尔值 | |
| LOG_PATH | 存储日志文件的位置 | 字符串 | `your-path/Flowise/logs` |
| LOG_LEVEL | 日志的不同级别 | 枚举字符串: `error`, `info`, `verbose`, `debug` | `info` |
| APIKEY_PATH | 存储 API 密钥的位置 | 字符串 | `your-path/Flowise/packages/server` |
| TOOL_FUNCTION_BUILTIN_DEP | 用于工具函数的 NodeJS 内置模块 | 字符串 | |
| TOOL_FUNCTION_EXTERNAL_DEP | 用于工具函数的外部模块 | 字符串 | |
| OVERRIDE_DATABASE | 是否使用默认值覆盖当前数据库 | 枚举字符串: `true`, `false` | `true` |
| DATABASE_TYPE | 存储 flowise 数据的数据库类型 | 枚举字符串: `sqlite`, `mysql`, `postgres` | `sqlite` |
| DATABASE_PATH | 数据库保存的位置（当 DATABASE_TYPE 是 sqlite 时） | 字符串 | `your-home-dir/.flowise` |
| DATABASE_HOST | 主机 URL 或 IP 地址（当 DATABASE_TYPE 不是 sqlite 时） | 字符串 | |
| DATABASE_PORT | 数据库端口（当 DATABASE_TYPE 不是 sqlite 时） | 字符串 | |
| DATABASE_USERNAME | 数据库用户名（当 DATABASE_TYPE 不是 sqlite 时） | 字符串 | |
| DATABASE_PASSWORD | 数据库密码（当 DATABASE_TYPE 不是 sqlite 时） | 字符串 | |
| DATABASE_NAME | 数据库名称（当 DATABASE_TYPE 不是 sqlite 时） | 字符串 | |
| 变量名 | 描述 | 类型 | 默认值 |
| --------------------------- | ------------------------------------------------------ | ----------------------------------------------- | ----------------------------------- |
| PORT | Flowise 运行的 HTTP 端口 | 数字 | 3000 |
| FLOWISE_USERNAME | 登录用户名 | 字符串 | |
| FLOWISE_PASSWORD | 登录密码 | 字符串 | |
| DEBUG | 打印组件的日志 | 布尔值 | |
| LOG_PATH | 存储日志文件的位置 | 字符串 | `your-path/Flowise/logs` |
| LOG_LEVEL | 日志的不同级别 | 枚举字符串: `error`, `info`, `verbose`, `debug` | `info` |
| APIKEY_PATH | 存储 API 密钥的位置 | 字符串 | `your-path/Flowise/packages/server` |
| TOOL_FUNCTION_BUILTIN_DEP | 用于工具函数的 NodeJS 内置模块 | 字符串 | |
| TOOL_FUNCTION_EXTERNAL_DEP | 用于工具函数的外部模块 | 字符串 | |
| DATABASE_TYPE | 存储 flowise 数据的数据库类型 | 枚举字符串: `sqlite`, `mysql`, `postgres` | `sqlite` |
| DATABASE_PATH | 数据库保存的位置（当 DATABASE_TYPE 是 sqlite 时） | 字符串 | `your-home-dir/.flowise` |
| DATABASE_HOST | 主机 URL 或 IP 地址（当 DATABASE_TYPE 不是 sqlite 时） | 字符串 | |
| DATABASE_PORT | 数据库端口（当 DATABASE_TYPE 不是 sqlite 时） | 字符串 | |
| DATABASE_USERNAME | 数据库用户名（当 DATABASE_TYPE 不是 sqlite 时） | 字符串 | |
| DATABASE_PASSWORD | 数据库密码（当 DATABASE_TYPE 不是 sqlite 时） | 字符串 | |
| DATABASE_NAME | 数据库名称（当 DATABASE_TYPE 不是 sqlite 时） | 字符串 | |
| SECRETKEY_PATH | 保存加密密钥（用于加密/解密凭据）的位置 | 字符串 | `your-path/Flowise/packages/server` |
| FLOWISE_SECRETKEY_OVERWRITE | 加密密钥用于替代存储在 SECRETKEY_PATH 中的密钥 | 字符串 |
您也可以在使用 `npx` 时指定环境变量。例如：

41
CONTRIBUTING.md
View File

@ -120,27 +120,26 @@ Flowise has 3 different modules in a single mono repository.
Flowise support different environment variables to configure your instance. You can specify the following variables in the `.env` file inside `packages/server` folder. Read [more](https://docs.flowiseai.com/environment-variables)
| Variable | Description | Type | Default |
| -------------------------- | ---------------------------------------------------------------------------- | ------------------------------------------------ | ----------------------------------- |
| PORT | The HTTP port Flowise runs on | Number | 3000 |
| FLOWISE_USERNAME | Username to login | String | |
| FLOWISE_PASSWORD | Password to login | String | |
| DEBUG | Print logs from components | Boolean | |
| LOG_PATH | Location where log files are stored | String | `your-path/Flowise/logs` |
| LOG_LEVEL | Different levels of logs | Enum String: `error`, `info`, `verbose`, `debug` | `info` |
| APIKEY_PATH | Location where api keys are saved | String | `your-path/Flowise/packages/server` |
| TOOL_FUNCTION_BUILTIN_DEP | NodeJS built-in modules to be used for Tool Function | String | |
| TOOL_FUNCTION_EXTERNAL_DEP | External modules to be used for Tool Function | String | |
| OVERRIDE_DATABASE | Override current database with default | Enum String: `true`, `false` | `true` |
| DATABASE_TYPE | Type of database to store the flowise data | Enum String: `sqlite`, `mysql`, `postgres` | `sqlite` |
| DATABASE_PATH | Location where database is saved (When DATABASE_TYPE is sqlite) | String | `your-home-dir/.flowise` |
| DATABASE_HOST | Host URL or IP address (When DATABASE_TYPE is not sqlite) | String | |
| DATABASE_PORT | Database port (When DATABASE_TYPE is not sqlite) | String | |
| DATABASE_USER | Database username (When DATABASE_TYPE is not sqlite) | String | |
| DATABASE_PASSWORD | Database password (When DATABASE_TYPE is not sqlite) | String | |
| DATABASE_NAME | Database name (When DATABASE_TYPE is not sqlite) | String | |
| PASSPHRASE | Passphrase used to create encryption key | String | `MYPASSPHRASE` |
| SECRETKEY_PATH | Location where encryption key (used to encrypt/decrypt credentials) is saved | String | `your-path/Flowise/packages/server` |
| Variable | Description | Type | Default |
| --------------------------- | ---------------------------------------------------------------------------- | ------------------------------------------------ | ----------------------------------- | --- |
| PORT | The HTTP port Flowise runs on | Number | 3000 |
| FLOWISE_USERNAME | Username to login | String | |
| FLOWISE_PASSWORD | Password to login | String | |
| DEBUG | Print logs from components | Boolean | |
| LOG_PATH | Location where log files are stored | String | `your-path/Flowise/logs` |
| LOG_LEVEL | Different levels of logs | Enum String: `error`, `info`, `verbose`, `debug` | `info` |
| APIKEY_PATH | Location where api keys are saved | String | `your-path/Flowise/packages/server` |
| TOOL_FUNCTION_BUILTIN_DEP | NodeJS built-in modules to be used for Tool Function | String | |
| TOOL_FUNCTION_EXTERNAL_DEP | External modules to be used for Tool Function | String | | |
| DATABASE_TYPE | Type of database to store the flowise data | Enum String: `sqlite`, `mysql`, `postgres` | `sqlite` |
| DATABASE_PATH | Location where database is saved (When DATABASE_TYPE is sqlite) | String | `your-home-dir/.flowise` |
| DATABASE_HOST | Host URL or IP address (When DATABASE_TYPE is not sqlite) | String | |
| DATABASE_PORT | Database port (When DATABASE_TYPE is not sqlite) | String | |
| DATABASE_USER | Database username (When DATABASE_TYPE is not sqlite) | String | |
| DATABASE_PASSWORD | Database password (When DATABASE_TYPE is not sqlite) | String | |
| DATABASE_NAME | Database name (When DATABASE_TYPE is not sqlite) | String | |
| SECRETKEY_PATH | Location where encryption key (used to encrypt/decrypt credentials) is saved | String | `your-path/Flowise/packages/server` |
| FLOWISE_SECRETKEY_OVERWRITE | Encryption key to be used instead of the key stored in SECRETKEY_PATH | String |
You can also specify the env variables when using `npx`. For example:

3
docker/.env.example
View File

@ -1,5 +1,4 @@
PORT=3000
PASSPHRASE=MYPASSPHRASE # Passphrase used to create encryption key
DATABASE_PATH=/root/.flowise
APIKEY_PATH=/root/.flowise
SECRETKEY_PATH=/root/.flowise
@ -13,10 +12,10 @@ LOG_PATH=/root/.flowise/logs
# DATABASE_NAME="flowise"
# DATABASE_USER=""
# DATABASE_PASSWORD=""
# OVERRIDE_DATABASE=true
# FLOWISE_USERNAME=user
# FLOWISE_PASSWORD=1234
# FLOWISE_SECRETKEY_OVERWRITE=myencryptionkey
# DEBUG=true
# LOG_LEVEL=debug (error | warn | info | verbose | debug)
# TOOL_FUNCTION_BUILTIN_DEP=crypto,fs

2
docker/docker-compose.yml
View File

@ -6,13 +6,13 @@ services:
restart: always
environment:
- PORT=${PORT}
- PASSPHRASE=${PASSPHRASE}
- FLOWISE_USERNAME=${FLOWISE_USERNAME}
- FLOWISE_PASSWORD=${FLOWISE_PASSWORD}
- DEBUG=${DEBUG}
- DATABASE_PATH=${DATABASE_PATH}
- APIKEY_PATH=${APIKEY_PATH}
- SECRETKEY_PATH=${SECRETKEY_PATH}
- FLOWISE_SECRETKEY_OVERWRITE=${FLOWISE_SECRETKEY_OVERWRITE}
- LOG_LEVEL=${LOG_LEVEL}
- LOG_PATH=${LOG_PATH}
ports:

2
package.json
View File

@ -1,6 +1,6 @@
{
"name": "flowise",
"version": "1.3.4",
"version": "1.3.5",
"private": true,
"homepage": "https://flowiseai.com",
"workspaces": [

2
packages/components/nodes/agents/BabyAGI/BabyAGI.ts
View File

@ -1,7 +1,7 @@
import { INode, INodeData, INodeParams } from '../../../src/Interface'
import { BabyAGI } from './core'
import { BaseChatModel } from 'langchain/chat_models/base'
import { VectorStore } from 'langchain/vectorstores'
import { VectorStore } from 'langchain/vectorstores/base'
class BabyAGI_Agents implements INode {
label: string

2
packages/components/nodes/chains/VectorDBQAChain/VectorDBQAChain.ts
View File

@ -2,7 +2,7 @@ import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Inter
import { getBaseClasses } from '../../../src/utils'
import { VectorDBQAChain } from 'langchain/chains'
import { BaseLanguageModel } from 'langchain/base_language'
import { VectorStore } from 'langchain/vectorstores'
import { VectorStore } from 'langchain/vectorstores/base'
import { ConsoleCallbackHandler, CustomChainHandler, additionalCallbacks } from '../../../src/handler'
class VectorDBQAChain_Chains implements INode {

24
packages/components/nodes/vectorstores/Milvus/Milvus_Existing.ts
View File

@ -21,7 +21,7 @@ class Milvus_Existing_VectorStores implements INode {
constructor() {
this.label = 'Milvus Load Existing collection'
this.name = 'milvusExistingCollection'
this.version = 1.0
this.version = 2.0
this.type = 'Milvus'
this.icon = 'milvus.svg'
this.category = 'Vector Stores'
@ -50,6 +50,25 @@ class Milvus_Existing_VectorStores implements INode {
label: 'Milvus Collection Name',
name: 'milvusCollection',
type: 'string'
},
{
label: 'Milvus Filter',
name: 'milvusFilter',
type: 'string',
optional: true,
description:
'Filter data with a simple string query. Refer Milvus <a target="_blank" href="https://milvus.io/blog/2022-08-08-How-to-use-string-data-to-empower-your-similarity-search-applications.md#Hybrid-search">docs</a> for more details.',
placeholder: 'doc=="a"',
additionalParams: true
},
{
label: 'Top K',
name: 'topK',
description: 'Number of top results to fetch. Default to 4',
placeholder: '4',
type: 'number',
additionalParams: true,
optional: true
}
]
this.outputs = [
@ -70,6 +89,7 @@ class Milvus_Existing_VectorStores implements INode {
// server setup
const address = nodeData.inputs?.milvusServerUrl as string
const collectionName = nodeData.inputs?.milvusCollection as string
const milvusFilter = nodeData.inputs?.milvusFilter as string
// embeddings
const embeddings = nodeData.inputs?.embeddings as Embeddings
@ -109,7 +129,7 @@ class Milvus_Existing_VectorStores implements INode {
throw new Error(`Collection not found: ${vectorStore.collectionName}, please create collection before search.`)
}
const filterStr = filter ?? ''
const filterStr = milvusFilter ?? filter ?? ''
await vectorStore.grabCollectionFields()

2
packages/components/nodes/vectorstores/Vectara_Existing/Vectara_Existing.ts → packages/components/nodes/vectorstores/Vectara/Vectara_Existing.ts
View File

@ -92,7 +92,7 @@ class VectaraExisting_VectorStores implements INode {
const credentialData = await getCredentialData(nodeData.credential ?? '', options)
const apiKey = getCredentialParam('apiKey', credentialData, nodeData)
const customerId = getCredentialParam('customerID', credentialData, nodeData)
const corpusId = getCredentialParam('corpusID', credentialData, nodeData)
const corpusId = getCredentialParam('corpusID', credentialData, nodeData).split(',')
const vectaraMetadataFilter = nodeData.inputs?.filter as string
const sentencesBefore = nodeData.inputs?.sentencesBefore as number

176
packages/components/nodes/vectorstores/Vectara/Vectara_Upload.ts Normal file
View File

@ -0,0 +1,176 @@
import { ICommonObject, INode, INodeData, INodeOutputsValue, INodeParams } from '../../../src/Interface'
import { getBaseClasses, getCredentialData, getCredentialParam } from '../../../src/utils'
import { VectaraStore, VectaraLibArgs, VectaraFilter, VectaraContextConfig, VectaraFile } from 'langchain/vectorstores/vectara'
class VectaraUpload_VectorStores implements INode {
label: string
name: string
version: number
description: string
type: string
icon: string
category: string
baseClasses: string[]
inputs: INodeParams[]
credential: INodeParams
outputs: INodeOutputsValue[]
constructor() {
this.label = 'Vectara Upload File'
this.name = 'vectaraUpload'
this.version = 1.0
this.type = 'Vectara'
this.icon = 'vectara.png'
this.category = 'Vector Stores'
this.description = 'Upload files to Vectara'
this.baseClasses = [this.type, 'VectorStoreRetriever', 'BaseRetriever']
this.credential = {
label: 'Connect Credential',
name: 'credential',
type: 'credential',
credentialNames: ['vectaraApi']
}
this.inputs = [
{
label: 'File',
name: 'file',
description:
'File to upload to Vectara. Supported file types: https://docs.vectara.com/docs/api-reference/indexing-apis/file-upload/file-upload-filetypes',
type: 'file'
},
{
label: 'Vectara Metadata Filter',
name: 'filter',
description:
'Filter to apply to Vectara metadata. Refer to the <a target="_blank" href="https://docs.flowiseai.com/vector-stores/vectara">documentation</a> on how to use Vectara filters with Flowise.',
type: 'string',
additionalParams: true,
optional: true
},
{
label: 'Sentences Before',
name: 'sentencesBefore',
description: 'Number of sentences to fetch before the matched sentence. Defaults to 2.',
type: 'number',
additionalParams: true,
optional: true
},
{
label: 'Sentences After',
name: 'sentencesAfter',
description: 'Number of sentences to fetch after the matched sentence. Defaults to 2.',
type: 'number',
additionalParams: true,
optional: true
},
{
label: 'Lambda',
name: 'lambda',
description:
'Improves retrieval accuracy by adjusting the balance (from 0 to 1) between neural search and keyword-based search factors.',
type: 'number',
additionalParams: true,
optional: true
},
{
label: 'Top K',
name: 'topK',
description: 'Number of top results to fetch. Defaults to 4',
placeholder: '4',
type: 'number',
additionalParams: true,
optional: true
}
]
this.outputs = [
{
label: 'Vectara Retriever',
name: 'retriever',
baseClasses: this.baseClasses
},
{
label: 'Vectara Vector Store',
name: 'vectorStore',
baseClasses: [this.type, ...getBaseClasses(VectaraStore)]
}
]
}
async init(nodeData: INodeData, _: string, options: ICommonObject): Promise<any> {
const credentialData = await getCredentialData(nodeData.credential ?? '', options)
const apiKey = getCredentialParam('apiKey', credentialData, nodeData)
const customerId = getCredentialParam('customerID', credentialData, nodeData)
const corpusId = getCredentialParam('corpusID', credentialData, nodeData).split(',')
const fileBase64 = nodeData.inputs?.file
const vectaraMetadataFilter = nodeData.inputs?.filter as string
const sentencesBefore = nodeData.inputs?.sentencesBefore as number
const sentencesAfter = nodeData.inputs?.sentencesAfter as number
const lambda = nodeData.inputs?.lambda as number
const output = nodeData.outputs?.output as string
const topK = nodeData.inputs?.topK as string
const k = topK ? parseInt(topK, 10) : 4
const vectaraArgs: VectaraLibArgs = {
apiKey: apiKey,
customerId: customerId,
corpusId: corpusId
}
const vectaraFilter: VectaraFilter = {}
if (vectaraMetadataFilter) vectaraFilter.filter = vectaraMetadataFilter
if (lambda) vectaraFilter.lambda = lambda
const vectaraContextConfig: VectaraContextConfig = {}
if (sentencesBefore) vectaraContextConfig.sentencesBefore = sentencesBefore
if (sentencesAfter) vectaraContextConfig.sentencesAfter = sentencesAfter
vectaraFilter.contextConfig = vectaraContextConfig
let files: string[] = []
if (fileBase64.startsWith('[') && fileBase64.endsWith(']')) {
files = JSON.parse(fileBase64)
} else {
files = [fileBase64]
}
const vectaraFiles: VectaraFile[] = []
for (const file of files) {
const splitDataURI = file.split(',')
splitDataURI.pop()
const bf = Buffer.from(splitDataURI.pop() || '', 'base64')
const blob = new Blob([bf])
vectaraFiles.push({ blob: blob, fileName: getFileName(file) })
}
const vectorStore = new VectaraStore(vectaraArgs)
await vectorStore.addFiles(vectaraFiles)
if (output === 'retriever') {
const retriever = vectorStore.asRetriever(k, vectaraFilter)
return retriever
} else if (output === 'vectorStore') {
;(vectorStore as any).k = k
return vectorStore
}
return vectorStore
}
}
const getFileName = (fileBase64: string) => {
let fileNames = []
if (fileBase64.startsWith('[') && fileBase64.endsWith(']')) {
const files = JSON.parse(fileBase64)
for (const file of files) {
const splitDataURI = file.split(',')
const filename = splitDataURI[splitDataURI.length - 1].split(':')[1]
fileNames.push(filename)
}
return fileNames.join(', ')
} else {
const splitDataURI = fileBase64.split(',')
const filename = splitDataURI[splitDataURI.length - 1].split(':')[1]
return filename
}
}
module.exports = { nodeClass: VectaraUpload_VectorStores }

2
packages/components/nodes/vectorstores/Vectara_Upsert/Vectara_Upsert.ts → packages/components/nodes/vectorstores/Vectara/Vectara_Upsert.ts
View File

@ -101,7 +101,7 @@ class VectaraUpsert_VectorStores implements INode {
const credentialData = await getCredentialData(nodeData.credential ?? '', options)
const apiKey = getCredentialParam('apiKey', credentialData, nodeData)
const customerId = getCredentialParam('customerID', credentialData, nodeData)
const corpusId = getCredentialParam('corpusID', credentialData, nodeData)
const corpusId = getCredentialParam('corpusID', credentialData, nodeData).split(',')
const docs = nodeData.inputs?.document as Document[]
const embeddings = {} as Embeddings

0
packages/components/nodes/vectorstores/Vectara_Existing/vectara.png → packages/components/nodes/vectorstores/Vectara/vectara.png
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 66 KiB

After

Width:  |  Height:  |  Size: 66 KiB

BIN
packages/components/nodes/vectorstores/Vectara_Upsert/vectara.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 66 KiB

4
packages/components/package.json
View File

@ -1,6 +1,6 @@
{
"name": "flowise-components",
"version": "1.3.4",
"version": "1.3.5",
"description": "Flowiseai Components",
"main": "dist/src/index",
"types": "dist/src/index.d.ts",
@ -42,7 +42,7 @@
"google-auth-library": "^9.0.0",
"graphql": "^16.6.0",
"html-to-text": "^9.0.5",
"langchain": "^0.0.145",
"langchain": "^0.0.147",
"langfuse-langchain": "^1.0.14-alpha.0",
"langsmith": "^0.0.32",
"linkifyjs": "^4.1.1",

3
packages/components/src/utils.ts
View File

@ -396,6 +396,9 @@ const getEncryptionKeyPath = (): string => {
* @returns {Promise<string>}
*/
const getEncryptionKey = async (): Promise<string> => {
if (process.env.FLOWISE_SECRETKEY_OVERWRITE !== undefined && process.env.FLOWISE_SECRETKEY_OVERWRITE !== '') {
return process.env.FLOWISE_SECRETKEY_OVERWRITE
}
try {
return await fs.promises.readFile(getEncryptionKeyPath(), 'utf8')
} catch (error) {

3
packages/server/.env.example
View File

@ -1,5 +1,4 @@
PORT=3000
PASSPHRASE=MYPASSPHRASE # Passphrase used to create encryption key
# DATABASE_PATH=/your_database_path/.flowise
# APIKEY_PATH=/your_api_key_path/.flowise
# SECRETKEY_PATH=/your_api_key_path/.flowise
@ -13,10 +12,10 @@ PASSPHRASE=MYPASSPHRASE # Passphrase used to create encryption key
# DATABASE_NAME="flowise"
# DATABASE_USER=""
# DATABASE_PASSWORD=""
# OVERRIDE_DATABASE=true
# FLOWISE_USERNAME=user
# FLOWISE_PASSWORD=1234
# FLOWISE_SECRETKEY_OVERWRITE=myencryptionkey
# DEBUG=true
# LOG_LEVEL=debug (error | warn | info | verbose | debug)
# TOOL_FUNCTION_BUILTIN_DEP=crypto,fs

20
packages/server/README-ZH.md
View File

@ -35,26 +35,6 @@ FLOWISE_PASSWORD=1234
Flowise 支持不同的环境变量来配置您的实例。您可以在`packages/server`文件夹中的`.env`文件中指定以下变量。阅读[更多](https://docs.flowiseai.com/environment-variables)
| 变量 | 描述 | 类型 | 默认值 |
| -------------------------- | ------------------------------------------------------ | ----------------------------------------------- | ----------------------------------- |
| PORT | Flowise 运行的 HTTP 端口 | 数字 | 3000 |
| FLOWISE_USERNAME | 登录的用户名 | 字符串 | |
| FLOWISE_PASSWORD | 登录的密码 | 字符串 | |
| DEBUG | 打印组件的日志 | 布尔值 | |
| LOG_PATH | 存储日志文件的位置 | 字符串 | `your-path/Flowise/logs` |
| LOG_LEVEL | 日志的不同级别 | 枚举字符串：`error`、`info`、`verbose`、`debug` | `info` |
| APIKEY_PATH | 存储 API 密钥的位置 | 字符串 | `your-path/Flowise/packages/server` |
| TOOL_FUNCTION_BUILTIN_DEP | 用于工具函数的 NodeJS 内置模块 | 字符串 | |
| TOOL_FUNCTION_EXTERNAL_DEP | 用于工具函数的外部模块 | 字符串 | |
| OVERRIDE_DATABASE | 使用默认值覆盖当前数据库 | 枚举字符串：`true`、`false` | `true` |
| DATABASE_TYPE | 存储 flowise 数据的数据库类型 | 枚举字符串：`sqlite`、`mysql`、`postgres` | `sqlite` |
| DATABASE_PATH | 数据库的保存位置（当 DATABASE_TYPE 为 sqlite 时） | 字符串 | `your-home-dir/.flowise` |
| DATABASE_HOST | 主机 URL 或 IP 地址（当 DATABASE_TYPE 不为 sqlite 时） | 字符串 | |
| DATABASE_PORT | 数据库端口（当 DATABASE_TYPE 不为 sqlite 时） | 字符串 | |
| DATABASE_USERNAME | 数据库用户名（当 DATABASE_TYPE 不为 sqlite 时） | 字符串 | |
| DATABASE_PASSWORD | 数据库密码（当 DATABASE_TYPE 不为 sqlite 时） | 字符串 | |
| DATABASE_NAME | 数据库名称（当 DATABASE_TYPE 不为 sqlite 时） | 字符串 | |
您还可以在使用`npx`时指定环境变量。例如：
```

371
packages/server/marketplaces/chatflows/Vectara LLM Chain Upload.json
View File

@ -1,11 +1,125 @@
{
"description": "A simple LLM chain that uses Vectara to enable conversations with uploaded documents",
"description": "A simple LLM chain that uses Vectara to enable conversations with uploaded files",
"nodes": [
{
"width": 300,
"height": 524,
"id": "vectaraUpload_0",
"position": { "x": 219.0098475967174, "y": 189.74396248534583 },
"type": "customNode",
"data": {
"id": "vectaraUpload_0",
"label": "Vectara Upload File",
"version": 1,
"name": "vectaraUpload",
"type": "Vectara",
"baseClasses": ["Vectara", "VectorStoreRetriever", "BaseRetriever"],
"category": "Vector Stores",
"description": "Upload files to Vectara",
"inputParams": [
{
"label": "Connect Credential",
"name": "credential",
"type": "credential",
"credentialNames": ["vectaraApi"],
"id": "vectaraUpload_0-input-credential-credential"
},
{
"label": "File",
"name": "file",
"description": "File to upload to Vectara. Supported file types: https://docs.vectara.com/docs/api-reference/indexing-apis/file-upload/file-upload-filetypes",
"type": "file",
"id": "vectaraUpload_0-input-file-file"
},
{
"label": "Vectara Metadata Filter",
"name": "filter",
"description": "Filter to apply to Vectara metadata. Refer to the <a target=\"_blank\" href=\"https://docs.flowiseai.com/vector-stores/vectara\">documentation</a> on how to use Vectara filters with Flowise.",
"type": "string",
"additionalParams": true,
"optional": true,
"id": "vectaraUpload_0-input-filter-string"
},
{
"label": "Sentences Before",
"name": "sentencesBefore",
"description": "Number of sentences to fetch before the matched sentence. Defaults to 2.",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpload_0-input-sentencesBefore-number"
},
{
"label": "Sentences After",
"name": "sentencesAfter",
"description": "Number of sentences to fetch after the matched sentence. Defaults to 2.",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpload_0-input-sentencesAfter-number"
},
{
"label": "Lambda",
"name": "lambda",
"description": "Improves retrieval accuracy by adjusting the balance (from 0 to 1) between neural search and keyword-based search factors.",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpload_0-input-lambda-number"
},
{
"label": "Top K",
"name": "topK",
"description": "Number of top results to fetch. Defaults to 4",
"placeholder": "4",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpload_0-input-topK-number"
}
],
"inputAnchors": [],
"inputs": {
"filter": "",
"sentencesBefore": "",
"sentencesAfter": "",
"lambda": "",
"topK": ""
},
"outputAnchors": [
{
"name": "output",
"label": "Output",
"type": "options",
"options": [
{
"id": "vectaraUpload_0-output-retriever-Vectara|VectorStoreRetriever|BaseRetriever",
"name": "retriever",
"label": "Vectara Retriever",
"type": "Vectara | VectorStoreRetriever | BaseRetriever"
},
{
"id": "vectaraUpload_0-output-vectorStore-Vectara|VectorStore",
"name": "vectorStore",
"label": "Vectara Vector Store",
"type": "Vectara | VectorStore"
}
],
"default": "retriever"
}
],
"outputs": { "output": "retriever" },
"selected": false
},
"selected": false,
"positionAbsolute": { "x": 219.0098475967174, "y": 189.74396248534583 },
"dragging": false
},
{
"width": 300,
"height": 525,
"id": "chatOpenAI_0",
"position": { "x": 514.1088940275924, "y": 199.574479681537 },
"position": { "x": 669.6533996522251, "y": 177.86181519287192 },
"type": "customNode",
"data": {
"id": "chatOpenAI_0",
@ -13,7 +127,7 @@
"version": 1,
"name": "chatOpenAI",
"type": "ChatOpenAI",
"baseClasses": ["ChatOpenAI", "BaseChatModel", "BaseLanguageModel"],
"baseClasses": ["ChatOpenAI", "BaseChatModel", "BaseLanguageModel", "Runnable"],
"category": "Chat Models",
"description": "Wrapper around OpenAI large language models that use the Chat endpoint",
"inputParams": [
@ -36,7 +150,10 @@
{ "label": "gpt-3.5-turbo", "name": "gpt-3.5-turbo" },
{ "label": "gpt-3.5-turbo-0613", "name": "gpt-3.5-turbo-0613" },
{ "label": "gpt-3.5-turbo-16k", "name": "gpt-3.5-turbo-16k" },
{ "label": "gpt-3.5-turbo-16k-0613", "name": "gpt-3.5-turbo-16k-0613" }
{
"label": "gpt-3.5-turbo-16k-0613",
"name": "gpt-3.5-turbo-16k-0613"
}
],
"default": "gpt-3.5-turbo",
"optional": true,
@ -103,6 +220,14 @@
"optional": true,
"additionalParams": true,
"id": "chatOpenAI_0-input-basepath-string"
},
{
"label": "BaseOptions",
"name": "baseOptions",
"type": "json",
"optional": true,
"additionalParams": true,
"id": "chatOpenAI_0-input-baseOptions-json"
}
],
"inputAnchors": [],
@ -114,28 +239,29 @@
"frequencyPenalty": "",
"presencePenalty": "",
"timeout": "",
"basepath": ""
"basepath": "",
"baseOptions": ""
},
"outputAnchors": [
{
"id": "chatOpenAI_0-output-chatOpenAI-ChatOpenAI|BaseChatModel|BaseLanguageModel",
"id": "chatOpenAI_0-output-chatOpenAI-ChatOpenAI|BaseChatModel|BaseLanguageModel|Runnable",
"name": "chatOpenAI",
"label": "ChatOpenAI",
"type": "ChatOpenAI | BaseChatModel | BaseLanguageModel"
"type": "ChatOpenAI | BaseChatModel | BaseLanguageModel | Runnable"
}
],
"outputs": {},
"selected": false
},
"selected": false,
"positionAbsolute": { "x": 514.1088940275924, "y": 199.574479681537 },
"positionAbsolute": { "x": 669.6533996522251, "y": 177.86181519287192 },
"dragging": false
},
{
"width": 300,
"height": 481,
"id": "conversationalRetrievalQAChain_0",
"position": { "x": 900.4793407261002, "y": 205.9476004518217 },
"position": { "x": 1135.5490908971935, "y": 201.62146241822506 },
"type": "customNode",
"data": {
"id": "conversationalRetrievalQAChain_0",
@ -143,7 +269,7 @@
"version": 1,
"name": "conversationalRetrievalQAChain",
"type": "ConversationalRetrievalQAChain",
"baseClasses": ["ConversationalRetrievalQAChain", "BaseChain"],
"baseClasses": ["ConversationalRetrievalQAChain", "BaseChain", "Runnable"],
"category": "Chains",
"description": "Document QA - built on RetrievalQAChain to provide a chat history component",
"inputParams": [
@ -214,234 +340,45 @@
],
"inputs": {
"model": "{{chatOpenAI_0.data.instance}}",
"vectorStoreRetriever": "{{vectaraUpsert_0.data.instance}}",
"vectorStoreRetriever": "{{vectaraUpload_0.data.instance}}",
"memory": "",
"returnSourceDocuments": "",
"returnSourceDocuments": true,
"systemMessagePrompt": "",
"chainOption": ""
},
"outputAnchors": [
{
"id": "conversationalRetrievalQAChain_0-output-conversationalRetrievalQAChain-ConversationalRetrievalQAChain|BaseChain",
"id": "conversationalRetrievalQAChain_0-output-conversationalRetrievalQAChain-ConversationalRetrievalQAChain|BaseChain|Runnable",
"name": "conversationalRetrievalQAChain",
"label": "ConversationalRetrievalQAChain",
"type": "ConversationalRetrievalQAChain | BaseChain"
"type": "ConversationalRetrievalQAChain | BaseChain | Runnable"
}
],
"outputs": {},
"selected": false
},
"selected": false,
"positionAbsolute": { "x": 900.4793407261002, "y": 205.9476004518217 },
"dragging": false
},
{
"width": 300,
"height": 509,
"id": "pdfFile_0",
"position": { "x": -210.44158723479913, "y": 236.6627524951051 },
"type": "customNode",
"data": {
"id": "pdfFile_0",
"label": "Pdf File",
"version": 1,
"name": "pdfFile",
"type": "Document",
"baseClasses": ["Document"],
"category": "Document Loaders",
"description": "Load data from PDF files",
"inputParams": [
{ "label": "Pdf File", "name": "pdfFile", "type": "file", "fileType": ".pdf", "id": "pdfFile_0-input-pdfFile-file" },
{
"label": "Usage",
"name": "usage",
"type": "options",
"options": [
{ "label": "One document per page", "name": "perPage" },
{ "label": "One document per file", "name": "perFile" }
],
"default": "perPage",
"id": "pdfFile_0-input-usage-options"
},
{
"label": "Use Legacy Build",
"name": "legacyBuild",
"type": "boolean",
"optional": true,
"additionalParams": true,
"id": "pdfFile_0-input-legacyBuild-boolean"
},
{
"label": "Metadata",
"name": "metadata",
"type": "json",
"optional": true,
"additionalParams": true,
"id": "pdfFile_0-input-metadata-json"
}
],
"inputAnchors": [
{
"label": "Text Splitter",
"name": "textSplitter",
"type": "TextSplitter",
"optional": true,
"id": "pdfFile_0-input-textSplitter-TextSplitter"
}
],
"inputs": { "textSplitter": "", "usage": "perPage", "legacyBuild": "", "metadata": "" },
"outputAnchors": [
{ "id": "pdfFile_0-output-pdfFile-Document", "name": "pdfFile", "label": "Document", "type": "Document" }
],
"outputs": {},
"selected": false
},
"selected": false,
"positionAbsolute": { "x": -210.44158723479913, "y": 236.6627524951051 },
"dragging": false
},
{
"width": 300,
"height": 408,
"id": "vectaraUpsert_0",
"position": { "x": 172.06946164914868, "y": 373.11406233089934 },
"type": "customNode",
"data": {
"id": "vectaraUpsert_0",
"label": "Vectara Upsert Document",
"version": 1,
"name": "vectaraUpsert",
"type": "Vectara",
"baseClasses": ["Vectara", "VectorStoreRetriever", "BaseRetriever"],
"category": "Vector Stores",
"description": "Upsert documents to Vectara",
"inputParams": [
{
"label": "Connect Credential",
"name": "credential",
"type": "credential",
"credentialNames": ["vectaraApi"],
"id": "vectaraUpsert_0-input-credential-credential"
},
{
"label": "Vectara Metadata Filter",
"name": "filter",
"description": "Filter to apply to Vectara metadata. Refer to the <a target=\"_blank\" href=\"https://docs.flowiseai.com/vector-stores/vectara\">documentation</a> on how to use Vectara filters with Flowise.",
"type": "string",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-filter-string"
},
{
"label": "Sentences Before",
"name": "sentencesBefore",
"description": "Number of sentences to fetch before the matched sentence. Defaults to 2.",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-sentencesBefore-number"
},
{
"label": "Sentences After",
"name": "sentencesAfter",
"description": "Number of sentences to fetch after the matched sentence. Defaults to 2.",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-sentencesAfter-number"
},
{
"label": "Lambda",
"name": "lambda",
"description": "Improves retrieval accuracy by adjusting the balance (from 0 to 1) between neural search and keyword-based search factors.",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-lambda-number"
},
{
"label": "Top K",
"name": "topK",
"description": "Number of top results to fetch. Defaults to 4",
"placeholder": "4",
"type": "number",
"additionalParams": true,
"optional": true,
"id": "vectaraUpsert_0-input-topK-number"
}
],
"inputAnchors": [
{
"label": "Document",
"name": "document",
"type": "Document",
"list": true,
"id": "vectaraUpsert_0-input-document-Document"
}
],
"inputs": {
"document": ["{{pdfFile_0.data.instance}}"],
"filter": "",
"sentencesBefore": "",
"sentencesAfter": "",
"lambda": "",
"topK": ""
},
"outputAnchors": [
{
"name": "output",
"label": "Output",
"type": "options",
"options": [
{
"id": "vectaraUpsert_0-output-retriever-Vectara|VectorStoreRetriever|BaseRetriever",
"name": "retriever",
"label": "Vectara Retriever",
"type": "Vectara | VectorStoreRetriever | BaseRetriever"
},
{
"id": "vectaraUpsert_0-output-vectorStore-Vectara|VectorStore",
"name": "vectorStore",
"label": "Vectara Vector Store",
"type": "Vectara | VectorStore"
}
],
"default": "retriever"
}
],
"outputs": { "output": "retriever" },
"selected": false
},
"positionAbsolute": { "x": 172.06946164914868, "y": 373.11406233089934 },
"selected": false
"dragging": false,
"positionAbsolute": { "x": 1135.5490908971935, "y": 201.62146241822506 }
}
],
"edges": [
{
"source": "chatOpenAI_0",
"sourceHandle": "chatOpenAI_0-output-chatOpenAI-ChatOpenAI|BaseChatModel|BaseLanguageModel",
"target": "conversationalRetrievalQAChain_0",
"targetHandle": "conversationalRetrievalQAChain_0-input-model-BaseLanguageModel",
"type": "buttonedge",
"id": "chatOpenAI_0-chatOpenAI_0-output-chatOpenAI-ChatOpenAI|BaseChatModel|BaseLanguageModel-conversationalRetrievalQAChain_0-conversationalRetrievalQAChain_0-input-model-BaseLanguageModel",
"data": { "label": "" }
},
{
"source": "pdfFile_0",
"sourceHandle": "pdfFile_0-output-pdfFile-Document",
"target": "vectaraUpsert_0",
"targetHandle": "vectaraUpsert_0-input-document-Document",
"type": "buttonedge",
"id": "pdfFile_0-pdfFile_0-output-pdfFile-Document-vectaraUpsert_0-vectaraUpsert_0-input-document-Document",
"data": { "label": "" }
},
{
"source": "vectaraUpsert_0",
"sourceHandle": "vectaraUpsert_0-output-retriever-Vectara|VectorStoreRetriever|BaseRetriever",
"source": "vectaraUpload_0",
"sourceHandle": "vectaraUpload_0-output-retriever-Vectara|VectorStoreRetriever|BaseRetriever",
"target": "conversationalRetrievalQAChain_0",
"targetHandle": "conversationalRetrievalQAChain_0-input-vectorStoreRetriever-BaseRetriever",
"type": "buttonedge",
"id": "vectaraUpsert_0-vectaraUpsert_0-output-retriever-Vectara|VectorStoreRetriever|BaseRetriever-conversationalRetrievalQAChain_0-conversationalRetrievalQAChain_0-input-vectorStoreRetriever-BaseRetriever",
"id": "vectaraUpload_0-vectaraUpload_0-output-retriever-Vectara|VectorStoreRetriever|BaseRetriever-conversationalRetrievalQAChain_0-conversationalRetrievalQAChain_0-input-vectorStoreRetriever-BaseRetriever",
"data": { "label": "" }
},
{
"source": "chatOpenAI_0",
"sourceHandle": "chatOpenAI_0-output-chatOpenAI-ChatOpenAI|BaseChatModel|BaseLanguageModel|Runnable",
"target": "conversationalRetrievalQAChain_0",
"targetHandle": "conversationalRetrievalQAChain_0-input-model-BaseLanguageModel",
"type": "buttonedge",
"id": "chatOpenAI_0-chatOpenAI_0-output-chatOpenAI-ChatOpenAI|BaseChatModel|BaseLanguageModel|Runnable-conversationalRetrievalQAChain_0-conversationalRetrievalQAChain_0-input-model-BaseLanguageModel",
"data": { "label": "" }
}
]

2
packages/server/package.json
View File

@ -1,6 +1,6 @@
{
"name": "flowise",
"version": "1.3.4",
"version": "1.3.5",
"description": "Flowiseai Server",
"main": "dist/index",
"types": "dist/index.d.ts",

6
packages/server/src/commands/start.ts
View File

@ -19,15 +19,14 @@ export default class Start extends Command {
FLOWISE_USERNAME: Flags.string(),
FLOWISE_PASSWORD: Flags.string(),
PORT: Flags.string(),
PASSPHRASE: Flags.string(),
DEBUG: Flags.string(),
APIKEY_PATH: Flags.string(),
SECRETKEY_PATH: Flags.string(),
FLOWISE_SECRETKEY_OVERWRITE: Flags.string(),
LOG_PATH: Flags.string(),
LOG_LEVEL: Flags.string(),
TOOL_FUNCTION_BUILTIN_DEP: Flags.string(),
TOOL_FUNCTION_EXTERNAL_DEP: Flags.string(),
OVERRIDE_DATABASE: Flags.string(),
DATABASE_TYPE: Flags.string(),
DATABASE_PATH: Flags.string(),
DATABASE_PORT: Flags.string(),
@ -80,8 +79,8 @@ export default class Start extends Command {
if (flags.APIKEY_PATH) process.env.APIKEY_PATH = flags.APIKEY_PATH
// Credentials
if (flags.PASSPHRASE) process.env.PASSPHRASE = flags.PASSPHRASE
if (flags.SECRETKEY_PATH) process.env.SECRETKEY_PATH = flags.SECRETKEY_PATH
if (flags.FLOWISE_SECRETKEY_OVERWRITE) process.env.FLOWISE_SECRETKEY_OVERWRITE = flags.FLOWISE_SECRETKEY_OVERWRITE
// Logs
if (flags.LOG_PATH) process.env.LOG_PATH = flags.LOG_PATH
@ -92,7 +91,6 @@ export default class Start extends Command {
if (flags.TOOL_FUNCTION_EXTERNAL_DEP) process.env.TOOL_FUNCTION_EXTERNAL_DEP = flags.TOOL_FUNCTION_EXTERNAL_DEP
// Database config
if (flags.OVERRIDE_DATABASE) process.env.OVERRIDE_DATABASE = flags.OVERRIDE_DATABASE
if (flags.DATABASE_TYPE) process.env.DATABASE_TYPE = flags.DATABASE_TYPE
if (flags.DATABASE_PATH) process.env.DATABASE_PATH = flags.DATABASE_PATH
if (flags.DATABASE_PORT) process.env.DATABASE_PORT = flags.DATABASE_PORT

14
packages/server/src/utils/index.ts
View File

@ -28,7 +28,7 @@ import {
convertChatHistoryToText
} from 'flowise-components'
import { scryptSync, randomBytes, timingSafeEqual } from 'crypto'
import { lib, PBKDF2, AES, enc } from 'crypto-js'
import { AES, enc } from 'crypto-js'
import { ChatFlow } from '../database/entities/ChatFlow'
import { ChatMessage } from '../database/entities/ChatMessage'
@ -814,12 +814,7 @@ export const getEncryptionKeyPath = (): string => {
* @returns {string}
*/
export const generateEncryptKey = (): string => {
const salt = lib.WordArray.random(128 / 8)
const key256Bits = PBKDF2(process.env.PASSPHRASE || 'MYPASSPHRASE', salt, {
keySize: 256 / 32,
iterations: 1000
})
return key256Bits.toString()
return randomBytes(24).toString('base64')
}
/**
@ -827,6 +822,9 @@ export const generateEncryptKey = (): string => {
* @returns {Promise<string>}
*/
export const getEncryptionKey = async (): Promise<string> => {
if (process.env.FLOWISE_SECRETKEY_OVERWRITE !== undefined && process.env.FLOWISE_SECRETKEY_OVERWRITE !== '') {
return process.env.FLOWISE_SECRETKEY_OVERWRITE
}
try {
return await fs.promises.readFile(getEncryptionKeyPath(), 'utf8')
} catch (error) {
@ -868,7 +866,7 @@ export const decryptCredentialData = async (
return JSON.parse(decryptedData.toString(enc.Utf8))
} catch (e) {
console.error(e)
throw new Error('Credentials could not be decrypted.')
return {}
}
}

2
packages/ui/package.json
View File

@ -1,6 +1,6 @@
{
"name": "flowise-ui",
"version": "1.3.2",
"version": "1.3.3",
"license": "SEE LICENSE IN LICENSE.md",
"homepage": "https://flowiseai.com",
"author": {