add conversational retrieval agent

This commit is contained in:
Henry
2023-08-06 19:45:21 +01:00
parent d208eae868
commit 0ae6f53295
18 changed files with 1018 additions and 103 deletions
@@ -1,9 +1,8 @@
import { ICommonObject, IMessage, INode, INodeData, INodeParams } from '../../../src/Interface'
import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
import { initializeAgentExecutorWithOptions, AgentExecutor, InitializeAgentExecutorOptions } from 'langchain/agents'
import { Tool } from 'langchain/tools'
import { BaseChatMemory, ChatMessageHistory } from 'langchain/memory'
import { getBaseClasses } from '../../../src/utils'
import { AIMessage, HumanMessage } from 'langchain/schema'
import { BaseChatMemory } from 'langchain/memory'
import { getBaseClasses, mapChatHistory } from '../../../src/utils'
import { BaseLanguageModel } from 'langchain/base_language'
import { flatten } from 'lodash'
@@ -93,19 +92,10 @@ class ConversationalAgent_Agents implements INode {
const memory = nodeData.inputs?.memory as BaseChatMemory
if (options && options.chatHistory) {
const chatHistory = []
const histories: IMessage[] = options.chatHistory
for (const message of histories) {
if (message.type === 'apiMessage') {
chatHistory.push(new AIMessage(message.message))
} else if (message.type === 'userMessage') {
chatHistory.push(new HumanMessage(message.message))
}
}
memory.chatHistory = new ChatMessageHistory(chatHistory)
memory.chatHistory = mapChatHistory(options)
executor.memory = memory
}
const result = await executor.call({ input })
return result?.output
@@ -0,0 +1,100 @@
import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
import { initializeAgentExecutorWithOptions, AgentExecutor } from 'langchain/agents'
import { getBaseClasses, mapChatHistory } from '../../../src/utils'
import { flatten } from 'lodash'
import { BaseChatMemory } from 'langchain/memory'
import { ConsoleCallbackHandler, CustomChainHandler } from '../../../src/handler'
class ConversationalRetrievalAgent_Agents implements INode {
label: string
name: string
version: number
description: string
type: string
icon: string
category: string
baseClasses: string[]
inputs: INodeParams[]
constructor() {
this.label = 'Conversational Retrieval Agent'
this.name = 'conversationalRetrievalAgent'
this.version = 1.0
this.type = 'AgentExecutor'
this.category = 'Agents'
this.icon = 'agent.svg'
this.description = `An agent optimized for retrieval during conversation, answering questions based on past dialogue, all using OpenAI's Function Calling`
this.baseClasses = [this.type, ...getBaseClasses(AgentExecutor)]
this.inputs = [
{
label: 'Allowed Tools',
name: 'tools',
type: 'Tool',
list: true
},
{
label: 'Memory',
name: 'memory',
type: 'BaseChatMemory'
},
{
label: 'OpenAI Chat Model',
name: 'model',
type: 'ChatOpenAI'
},
{
label: 'System Message',
name: 'systemMessage',
type: 'string',
rows: 4,
optional: true,
additionalParams: true
}
]
}
async init(nodeData: INodeData): Promise<any> {
const model = nodeData.inputs?.model
const memory = nodeData.inputs?.memory as BaseChatMemory
const systemMessage = nodeData.inputs?.systemMessage as string
let tools = nodeData.inputs?.tools
tools = flatten(tools)
const executor = await initializeAgentExecutorWithOptions(tools, model, {
agentType: 'openai-functions',
verbose: process.env.DEBUG === 'true' ? true : false,
agentArgs: {
prefix: systemMessage ?? `You are a helpful AI assistant.`
},
returnIntermediateSteps: true
})
executor.memory = memory
return executor
}
async run(nodeData: INodeData, input: string, options: ICommonObject): Promise<string> {
const executor = nodeData.instance as AgentExecutor
if (options && options.chatHistory) {
if (executor.memory) {
;(executor.memory as any).memoryKey = 'chat_history'
;(executor.memory as any).outputKey = 'output'
;(executor.memory as any).chatHistory = mapChatHistory(options)
}
}
const loggerHandler = new ConsoleCallbackHandler(options.logger)
if (options.socketIO && options.socketIOClientId) {
const handler = new CustomChainHandler(options.socketIO, options.socketIOClientId)
const result = await executor.call({ input }, [loggerHandler, handler])
return result?.output
} else {
const result = await executor.call({ input }, [loggerHandler])
return result?.output
}
}
}
module.exports = { nodeClass: ConversationalRetrievalAgent_Agents }
@@ -0,0 +1,9 @@
<svg xmlns="http://www.w3.org/2000/svg" class="icon icon-tabler icon-tabler-robot" width="24" height="24" viewBox="0 0 24 24" stroke-width="2" stroke="currentColor" fill="none" stroke-linecap="round" stroke-linejoin="round">
<path stroke="none" d="M0 0h24v24H0z" fill="none"></path>
<path d="M7 7h10a2 2 0 0 1 2 2v1l1 1v3l-1 1v3a2 2 0 0 1 -2 2h-10a2 2 0 0 1 -2 -2v-3l-1 -1v-3l1 -1v-1a2 2 0 0 1 2 -2z"></path>
<path d="M10 16h4"></path>
<circle cx="8.5" cy="11.5" r=".5" fill="currentColor"></circle>
<circle cx="15.5" cy="11.5" r=".5" fill="currentColor"></circle>
<path d="M9 7l-1 -4"></path>
<path d="M15 7l1 -4"></path>
</svg>

After

Width:  |  Height:  |  Size: 650 B

@@ -1,10 +1,9 @@
import { ICommonObject, IMessage, INode, INodeData, INodeParams } from '../../../src/Interface'
import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
import { initializeAgentExecutorWithOptions, AgentExecutor } from 'langchain/agents'
import { getBaseClasses } from '../../../src/utils'
import { getBaseClasses, mapChatHistory } from '../../../src/utils'
import { BaseLanguageModel } from 'langchain/base_language'
import { flatten } from 'lodash'
import { BaseChatMemory, ChatMessageHistory } from 'langchain/memory'
import { AIMessage, HumanMessage } from 'langchain/schema'
import { BaseChatMemory } from 'langchain/memory'
import { ConsoleCallbackHandler, CustomChainHandler } from '../../../src/handler'
class OpenAIFunctionAgent_Agents implements INode {
@@ -82,17 +81,7 @@ class OpenAIFunctionAgent_Agents implements INode {
const memory = nodeData.inputs?.memory as BaseChatMemory
if (options && options.chatHistory) {
const chatHistory = []
const histories: IMessage[] = options.chatHistory
for (const message of histories) {
if (message.type === 'apiMessage') {
chatHistory.push(new AIMessage(message.message))
} else if (message.type === 'userMessage') {
chatHistory.push(new HumanMessage(message.message))
}
}
memory.chatHistory = new ChatMessageHistory(chatHistory)
memory.chatHistory = mapChatHistory(options)
executor.memory = memory
}
@@ -1,10 +1,9 @@
import { ICommonObject, IMessage, INode, INodeData, INodeParams } from '../../../src/Interface'
import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
import { ConversationChain } from 'langchain/chains'
import { getBaseClasses } from '../../../src/utils'
import { getBaseClasses, mapChatHistory } from '../../../src/utils'
import { ChatPromptTemplate, HumanMessagePromptTemplate, MessagesPlaceholder, SystemMessagePromptTemplate } from 'langchain/prompts'
import { BufferMemory, ChatMessageHistory } from 'langchain/memory'
import { BufferMemory } from 'langchain/memory'
import { BaseChatModel } from 'langchain/chat_models/base'
import { AIMessage, HumanMessage } from 'langchain/schema'
import { ConsoleCallbackHandler, CustomChainHandler } from '../../../src/handler'
import { flatten } from 'lodash'
import { Document } from 'langchain/document'
@@ -106,17 +105,7 @@ class ConversationChain_Chains implements INode {
const memory = nodeData.inputs?.memory as BufferMemory
if (options && options.chatHistory) {
const chatHistory = []
const histories: IMessage[] = options.chatHistory
for (const message of histories) {
if (message.type === 'apiMessage') {
chatHistory.push(new AIMessage(message.message))
} else if (message.type === 'userMessage') {
chatHistory.push(new HumanMessage(message.message))
}
}
memory.chatHistory = new ChatMessageHistory(chatHistory)
memory.chatHistory = mapChatHistory(options)
chain.memory = memory
}
@@ -1,10 +1,9 @@
import { BaseLanguageModel } from 'langchain/base_language'
import { ICommonObject, IMessage, INode, INodeData, INodeParams } from '../../../src/Interface'
import { getBaseClasses } from '../../../src/utils'
import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
import { getBaseClasses, mapChatHistory } from '../../../src/utils'
import { ConversationalRetrievalQAChain, QAChainParams } from 'langchain/chains'
import { AIMessage, HumanMessage } from 'langchain/schema'
import { BaseRetriever } from 'langchain/schema/retriever'
import { BaseChatMemory, BufferMemory, ChatMessageHistory, BufferMemoryInput } from 'langchain/memory'
import { BufferMemory, BufferMemoryInput } from 'langchain/memory'
import { PromptTemplate } from 'langchain/prompts'
import { ConsoleCallbackHandler, CustomChainHandler } from '../../../src/handler'
import {
@@ -105,7 +104,7 @@ class ConversationalRetrievalQAChain_Chains implements INode {
const systemMessagePrompt = nodeData.inputs?.systemMessagePrompt as string
const returnSourceDocuments = nodeData.inputs?.returnSourceDocuments as boolean
const chainOption = nodeData.inputs?.chainOption as string
const memory = nodeData.inputs?.memory
const externalMemory = nodeData.inputs?.memory
const obj: any = {
verbose: process.env.DEBUG === 'true' ? true : false,
@@ -113,7 +112,9 @@ class ConversationalRetrievalQAChain_Chains implements INode {
template: CUSTOM_QUESTION_GENERATOR_CHAIN_PROMPT
}
}
if (returnSourceDocuments) obj.returnSourceDocuments = returnSourceDocuments
if (chainOption === 'map_reduce') {
obj.qaChainOptions = {
type: 'map_reduce',
@@ -142,20 +143,21 @@ class ConversationalRetrievalQAChain_Chains implements INode {
} as QAChainParams
}
if (memory) {
memory.inputKey = 'question'
memory.memoryKey = 'chat_history'
if (chainOption === 'refine') memory.outputKey = 'output_text'
else memory.outputKey = 'text'
obj.memory = memory
if (externalMemory) {
externalMemory.memoryKey = 'chat_history'
externalMemory.inputKey = 'question'
externalMemory.outputKey = 'text'
externalMemory.returnMessages = true
if (chainOption === 'refine') externalMemory.outputKey = 'output_text'
obj.memory = externalMemory
} else {
const fields: BufferMemoryInput = {
memoryKey: 'chat_history',
inputKey: 'question',
outputKey: 'text',
returnMessages: true
}
if (chainOption === 'refine') fields.outputKey = 'output_text'
else fields.outputKey = 'text'
obj.memory = new BufferMemory(fields)
}
@@ -166,7 +168,6 @@ class ConversationalRetrievalQAChain_Chains implements INode {
async run(nodeData: INodeData, input: string, options: ICommonObject): Promise<string | ICommonObject> {
const chain = nodeData.instance as ConversationalRetrievalQAChain
const returnSourceDocuments = nodeData.inputs?.returnSourceDocuments as boolean
const memory = nodeData.inputs?.memory
const chainOption = nodeData.inputs?.chainOption as string
let model = nodeData.inputs?.model
@@ -177,21 +178,8 @@ class ConversationalRetrievalQAChain_Chains implements INode {
const obj = { question: input }
// If external memory like Zep, Redis is being used, ignore below
if (!memory && chain.memory && options && options.chatHistory) {
const chatHistory = []
const histories: IMessage[] = options.chatHistory
const memory = chain.memory as BaseChatMemory
for (const message of histories) {
if (message.type === 'apiMessage') {
chatHistory.push(new AIMessage(message.message))
} else if (message.type === 'userMessage') {
chatHistory.push(new HumanMessage(message.message))
}
}
memory.chatHistory = new ChatMessageHistory(chatHistory)
chain.memory = memory
if (options && options.chatHistory && chain.memory) {
;(chain.memory as any).chatHistory = mapChatHistory(options)
}
const loggerHandler = new ConsoleCallbackHandler(options.logger)
@@ -1,6 +1,6 @@
import { ICommonObject, INode, INodeData, INodeParams, getBaseClasses, getCredentialData, getCredentialParam } from '../../../src'
import { DynamoDBChatMessageHistory } from 'langchain/stores/message/dynamodb'
import { BufferMemory } from 'langchain/memory'
import { BufferMemory, BufferMemoryInput } from 'langchain/memory'
class DynamoDb_Memory implements INode {
label: string
@@ -51,7 +51,7 @@ class DynamoDb_Memory implements INode {
label: 'Session ID',
name: 'sessionId',
type: 'string',
description: 'if empty, chatId will be used automatically',
description: 'If not specified, the first CHAT_MESSAGE_ID will be used as sessionId',
default: '',
additionalParams: true,
optional: true
@@ -86,9 +86,11 @@ const initalizeDynamoDB = async (nodeData: INodeData, options: ICommonObject): P
const sessionId = nodeData.inputs?.sessionId as string
const region = nodeData.inputs?.region as string
const memoryKey = nodeData.inputs?.memoryKey as string
const chatId = options.chatId
let isSessionIdUsingChatMessageId = false
if (!sessionId && chatId) isSessionIdUsingChatMessageId = true
const credentialData = await getCredentialData(nodeData.credential ?? '', options)
const accessKeyId = getCredentialParam('accessKey', credentialData, nodeData)
const secretAccessKey = getCredentialParam('secretAccessKey', credentialData, nodeData)
@@ -106,12 +108,26 @@ const initalizeDynamoDB = async (nodeData: INodeData, options: ICommonObject): P
}
})
const memory = new BufferMemory({
const memory = new BufferMemoryExtended({
memoryKey,
chatHistory: dynamoDb,
returnMessages: true
returnMessages: true,
isSessionIdUsingChatMessageId
})
return memory
}
interface BufferMemoryExtendedInput {
isSessionIdUsingChatMessageId: boolean
}
class BufferMemoryExtended extends BufferMemory {
isSessionIdUsingChatMessageId? = false
constructor(fields: BufferMemoryInput & Partial<BufferMemoryExtendedInput>) {
super(fields)
this.isSessionIdUsingChatMessageId = fields.isSessionIdUsingChatMessageId
}
}
module.exports = { nodeClass: DynamoDb_Memory }
@@ -2,6 +2,7 @@ import { INode, INodeData, INodeParams } from '../../../src/Interface'
import { getBaseClasses, getCredentialData, getCredentialParam } from '../../../src/utils'
import { ICommonObject } from '../../../src'
import { MotorheadMemory, MotorheadMemoryInput } from 'langchain/memory'
import fetch from 'node-fetch'
class MotorMemory_Memory implements INode {
label: string
@@ -44,7 +45,7 @@ class MotorMemory_Memory implements INode {
label: 'Session Id',
name: 'sessionId',
type: 'string',
description: 'if empty, chatId will be used automatically',
description: 'If not specified, the first CHAT_MESSAGE_ID will be used as sessionId',
default: '',
additionalParams: true,
optional: true
@@ -77,14 +78,16 @@ const initalizeMotorhead = async (nodeData: INodeData, options: ICommonObject):
const memoryKey = nodeData.inputs?.memoryKey as string
const baseURL = nodeData.inputs?.baseURL as string
const sessionId = nodeData.inputs?.sessionId as string
const chatId = options?.chatId as string
let isSessionIdUsingChatMessageId = false
if (!sessionId && chatId) isSessionIdUsingChatMessageId = true
const credentialData = await getCredentialData(nodeData.credential ?? '', options)
const apiKey = getCredentialParam('apiKey', credentialData, nodeData)
const clientId = getCredentialParam('clientId', credentialData, nodeData)
let obj: MotorheadMemoryInput = {
let obj: MotorheadMemoryInput & Partial<MotorheadMemoryExtendedInput> = {
returnMessages: true,
sessionId: sessionId ? sessionId : chatId,
memoryKey
@@ -103,7 +106,44 @@ const initalizeMotorhead = async (nodeData: INodeData, options: ICommonObject):
}
}
return new MotorheadMemory(obj)
if (isSessionIdUsingChatMessageId) obj.isSessionIdUsingChatMessageId = true
const motorheadMemory = new MotorheadMemoryExtended(obj)
// Get messages from sessionId
await motorheadMemory.init()
return motorheadMemory
}
interface MotorheadMemoryExtendedInput {
isSessionIdUsingChatMessageId: boolean
}
class MotorheadMemoryExtended extends MotorheadMemory {
isSessionIdUsingChatMessageId? = false
constructor(fields: MotorheadMemoryInput & Partial<MotorheadMemoryExtendedInput>) {
super(fields)
this.isSessionIdUsingChatMessageId = fields.isSessionIdUsingChatMessageId
}
async clear(): Promise<void> {
try {
await this.caller.call(fetch, `${this.url}/sessions/${this.sessionId}/memory`, {
//@ts-ignore
signal: this.timeout ? AbortSignal.timeout(this.timeout) : undefined,
headers: this._getHeaders() as ICommonObject,
method: 'DELETE'
})
} catch (error) {
console.error('Error deleting session: ', error)
}
// Clear the superclass's chat history
await this.chatHistory.clear()
await super.clear()
}
}
module.exports = { nodeClass: MotorMemory_Memory }
@@ -1,7 +1,7 @@
import { INode, INodeData, INodeParams } from '../../../src/Interface'
import { getBaseClasses } from '../../../src/utils'
import { ICommonObject } from '../../../src'
import { BufferMemory } from 'langchain/memory'
import { BufferMemory, BufferMemoryInput } from 'langchain/memory'
import { RedisChatMessageHistory, RedisChatMessageHistoryInput } from 'langchain/stores/message/redis'
import { createClient } from 'redis'
@@ -36,7 +36,7 @@ class RedisBackedChatMemory_Memory implements INode {
label: 'Session Id',
name: 'sessionId',
type: 'string',
description: 'if empty, chatId will be used automatically',
description: 'If not specified, the first CHAT_MESSAGE_ID will be used as sessionId',
default: '',
additionalParams: true,
optional: true
@@ -78,9 +78,11 @@ const initalizeRedis = (nodeData: INodeData, options: ICommonObject): BufferMemo
const sessionId = nodeData.inputs?.sessionId as string
const sessionTTL = nodeData.inputs?.sessionTTL as number
const memoryKey = nodeData.inputs?.memoryKey as string
const chatId = options?.chatId as string
let isSessionIdUsingChatMessageId = false
if (!sessionId && chatId) isSessionIdUsingChatMessageId = true
const redisClient = createClient({ url: baseURL })
let obj: RedisChatMessageHistoryInput = {
sessionId: sessionId ? sessionId : chatId,
@@ -94,10 +96,28 @@ const initalizeRedis = (nodeData: INodeData, options: ICommonObject): BufferMemo
}
}
let redisChatMessageHistory = new RedisChatMessageHistory(obj)
let redis = new BufferMemory({ memoryKey, chatHistory: redisChatMessageHistory, returnMessages: true })
const redisChatMessageHistory = new RedisChatMessageHistory(obj)
return redis
const memory = new BufferMemoryExtended({
memoryKey,
chatHistory: redisChatMessageHistory,
returnMessages: true,
isSessionIdUsingChatMessageId
})
return memory
}
interface BufferMemoryExtendedInput {
isSessionIdUsingChatMessageId: boolean
}
class BufferMemoryExtended extends BufferMemory {
isSessionIdUsingChatMessageId? = false
constructor(fields: BufferMemoryInput & Partial<BufferMemoryExtendedInput>) {
super(fields)
this.isSessionIdUsingChatMessageId = fields.isSessionIdUsingChatMessageId
}
}
module.exports = { nodeClass: RedisBackedChatMemory_Memory }
@@ -50,7 +50,7 @@ class ZepMemory_Memory implements INode {
label: 'Session Id',
name: 'sessionId',
type: 'string',
description: 'if empty, chatId will be used automatically',
description: 'If not specified, the first CHAT_MESSAGE_ID will be used as sessionId',
default: '',
additionalParams: true,
optional: true
@@ -156,13 +156,15 @@ const initalizeZep = async (nodeData: INodeData, options: ICommonObject): Promis
const memoryKey = nodeData.inputs?.memoryKey as string
const inputKey = nodeData.inputs?.inputKey as string
const sessionId = nodeData.inputs?.sessionId as string
const chatId = options?.chatId as string
let isSessionIdUsingChatMessageId = false
if (!sessionId && chatId) isSessionIdUsingChatMessageId = true
const credentialData = await getCredentialData(nodeData.credential ?? '', options)
const apiKey = getCredentialParam('apiKey', credentialData, nodeData)
const obj: ZepMemoryInput = {
const obj: ZepMemoryInput & Partial<ZepMemoryExtendedInput> = {
baseURL,
sessionId: sessionId ? sessionId : chatId,
aiPrefix,
@@ -172,8 +174,39 @@ const initalizeZep = async (nodeData: INodeData, options: ICommonObject): Promis
inputKey
}
if (apiKey) obj.apiKey = apiKey
if (isSessionIdUsingChatMessageId) obj.isSessionIdUsingChatMessageId = true
return new ZepMemory(obj)
return new ZepMemoryExtended(obj)
}
interface ZepMemoryExtendedInput {
isSessionIdUsingChatMessageId: boolean
}
class ZepMemoryExtended extends ZepMemory {
isSessionIdUsingChatMessageId? = false
constructor(fields: ZepMemoryInput & Partial<ZepMemoryExtendedInput>) {
super(fields)
this.isSessionIdUsingChatMessageId = fields.isSessionIdUsingChatMessageId
}
async clear(): Promise<void> {
// Only clear when sessionId is using chatId
// If sessionId is specified, clearing and inserting again will error because the sessionId has been soft deleted
// If using chatId, it will not be a problem because the sessionId will always be the new chatId
if (this.isSessionIdUsingChatMessageId) {
try {
await this.zepClient.deleteMemory(this.sessionId)
} catch (error) {
console.error('Error deleting session: ', error)
}
// Clear the superclass's chat history
await super.clear()
}
await this.chatHistory.clear()
}
}
module.exports = { nodeClass: ZepMemory_Memory }
@@ -0,0 +1,65 @@
import { INode, INodeData, INodeParams } from '../../../src/Interface'
import { getBaseClasses } from '../../../src/utils'
import { DynamicTool } from 'langchain/tools'
import { createRetrieverTool } from 'langchain/agents/toolkits'
import { BaseRetriever } from 'langchain/schema/retriever'
class Retriever_Tools implements INode {
label: string
name: string
version: number
description: string
type: string
icon: string
category: string
baseClasses: string[]
credential: INodeParams
inputs: INodeParams[]
constructor() {
this.label = 'Retriever Tool'
this.name = 'retrieverTool'
this.version = 1.0
this.type = 'RetrieverTool'
this.icon = 'retriever-tool.png'
this.category = 'Tools'
this.description = 'Use a retriever as allowed tool for agent'
this.baseClasses = [this.type, 'DynamicTool', ...getBaseClasses(DynamicTool)]
this.inputs = [
{
label: 'Retriever Name',
name: 'name',
type: 'string',
placeholder: 'search_state_of_union'
},
{
label: 'Retriever Description',
name: 'description',
type: 'string',
description: 'When should agent uses to retrieve documents',
rows: 3,
placeholder: 'Searches and returns documents regarding the state-of-the-union.'
},
{
label: 'Retriever',
name: 'retriever',
type: 'BaseRetriever'
}
]
}
async init(nodeData: INodeData): Promise<any> {
const name = nodeData.inputs?.name as string
const description = nodeData.inputs?.description as string
const retriever = nodeData.inputs?.retriever as BaseRetriever
const tool = createRetrieverTool(retriever, {
name,
description
})
return tool
}
}
module.exports = { nodeClass: Retriever_Tools }
Binary file not shown.

After

Width:  |  Height:  |  Size: 14 KiB

+1 -1
View File
@@ -38,7 +38,7 @@
"form-data": "^4.0.0",
"graphql": "^16.6.0",
"html-to-text": "^9.0.5",
"langchain": "^0.0.117",
"langchain": "^0.0.122",
"linkifyjs": "^4.1.1",
"mammoth": "^1.5.1",
"moment": "^2.29.3",
+42 -4
View File
@@ -4,8 +4,10 @@ import * as fs from 'fs'
import * as path from 'path'
import { JSDOM } from 'jsdom'
import { DataSource } from 'typeorm'
import { ICommonObject, IDatabaseEntity, INodeData } from './Interface'
import { ICommonObject, IDatabaseEntity, IMessage, INodeData } from './Interface'
import { AES, enc } from 'crypto-js'
import { ChatMessageHistory } from 'langchain/memory'
import { AIMessage, HumanMessage } from 'langchain/schema'
export const numberOrExpressionRegex = '^(\\d+\\.?\\d*|{{.*}})$' //return true if string consists only numbers OR expression {{}}
export const notEmptyRegex = '(.|\\s)*\\S(.|\\s)*' //return true if string is not empty or blank
@@ -204,6 +206,9 @@ export const getAvailableURLs = async (url: string, limit: number) => {
/**
* Search for href through htmlBody string
* @param {string} htmlBody
* @param {string} baseURL
* @returns {string[]}
*/
function getURLsFromHTML(htmlBody: string, baseURL: string): string[] {
const dom = new JSDOM(htmlBody)
@@ -233,6 +238,8 @@ function getURLsFromHTML(htmlBody: string, baseURL: string): string[] {
/**
* Normalize URL to prevent crawling the same page
* @param {string} urlString
* @returns {string}
*/
function normalizeURL(urlString: string): string {
const urlObj = new URL(urlString)
@@ -246,6 +253,11 @@ function normalizeURL(urlString: string): string {
/**
* Recursive crawl using normalizeURL and getURLsFromHTML
* @param {string} baseURL
* @param {string} currentURL
* @param {string[]} pages
* @param {number} limit
* @returns {Promise<string[]>}
*/
async function crawl(baseURL: string, currentURL: string, pages: string[], limit: number): Promise<string[]> {
const baseURLObj = new URL(baseURL)
@@ -290,6 +302,9 @@ async function crawl(baseURL: string, currentURL: string, pages: string[], limit
/**
* Prep URL before passing into recursive carwl function
* @param {string} stringURL
* @param {number} limit
* @returns {Promise<string[]>}
*/
export async function webCrawl(stringURL: string, limit: number): Promise<string[]> {
const URLObj = new URL(stringURL)
@@ -336,10 +351,10 @@ export async function xmlScrape(currentURL: string, limit: number): Promise<stri
return urls
}
/*
/**
* Get env variables
* @param {string} url
* @returns {string[]}
* @param {string} name
* @returns {string | undefined}
*/
export const getEnvironmentVariable = (name: string): string | undefined => {
try {
@@ -470,6 +485,10 @@ export function handleEscapeCharacters(input: any, reverse: Boolean): any {
return input
}
/**
* Get user home dir
* @returns {string}
*/
export const getUserHome = (): string => {
let variableName = 'HOME'
if (process.platform === 'win32') {
@@ -482,3 +501,22 @@ export const getUserHome = (): string => {
}
return process.env[variableName] as string
}
/**
* Map incoming chat history to ChatMessageHistory
* @param {options} ICommonObject
* @returns {ChatMessageHistory}
*/
export const mapChatHistory = (options: ICommonObject): ChatMessageHistory => {
const chatHistory = []
const histories: IMessage[] = options.chatHistory
for (const message of histories) {
if (message.type === 'apiMessage') {
chatHistory.push(new AIMessage(message.message))
} else if (message.type === 'userMessage') {
chatHistory.push(new HumanMessage(message.message))
}
}
return new ChatMessageHistory(chatHistory)
}