openai assistant swarm

OpenaiアシスタントSwarm Manager：Openaiアシスタントを軍隊に変える図書館。

| | Mintplex Labs Inc | npm

Swarm Managerとは何ですか

OpenaiのアシスタントAPIは、自律的なAIアシスタントを構築している、または一般的に「エージェント」と呼ばれる開発者にとって、信じられないほどの継続的な継続性を解き放ちます。このノードJSライブラリは、単一のAPI呼び出しを介して、カスタムエージェントとその機能のレジストリ全体のロックを解除します。 1人のエージェント「マネージャー」は、委任されたタスクからのアクションを簡単に処理できるように、スマートかつ迅速な方法で1人または他の多くのアシスタントに作業を簡単に委任できるようになりました。

どのアシスタントが弓で包まれて包まれていることを行うかを管理することの精神的なオーバーヘッドのすべて。

どのように機能しますか？

Swarm Managerは.swarm Openai Nodejs SDKの拡張機能として機能しますbeta.assistants

まず、nodejsのOpenai SDKをインストールします

yarn add openai
# or 
npm install openai

次に、 openai-assistant-swarmパッケージをインストールします

yarn add @mintplex-labs/openai-assistant-swarm
# or 
npm install @mintplex-labs/openai-assistant-swarm

ここで、通常のようにSDKを使用して拡張機能を実行し、エージェントスワームマネージャーを初期化します。

 // Enable the client for OpenAi as you normally would
const OpenAIClient = (
    new OpenAI ( {
        apiKey : process . env . OPEN_AI_KEY
    } ) ) ;

// The simply call this function on the client to extend the OpenAI SDK to now have
// OpenAIClient.beta.assistants.swarm functions available.
EnableSwarmAbilities ( OpenAIClient , {
  // all options are OPTIONAL
  debug : false , // to see console log outputs of the process and playground links for debugging.
  managerAssistantOptions : {
         name : "[AUTOMATED] ___Swarm Manager" , // Name of created/maintained agent by the library
        model : "gpt-4" , // Use gpt-4 for better reasoning and calling.
        instructions : 'Instructions you are going to give the agent manager to delegate tasks to' ; // Override the default instructions.
    } ;
} ) ;

// Initialize the swarm manager to create the swarm manager and also register it with
// your account. Swarm manager can be configured via options on `EnableSwarmAbilities`
await OpenAIClient . beta . assistants . swarm . init ( ) ;
// Now all swarm management function are available to you! 

簡単な例

3人の利用可能なアシスタント間で単一の入力を委任する完全な例...

 import OpenAI from 'openai' ;
import { EnableSwarmAbilities } from '@mintplex-labs/openai-assistant-swarm' ;
const OpenAIClient = new OpenAI ( { apiKey : process . env . OPEN_AI_KEY } ) ;
EnableSwarmAbilities ( OpenAIClient ) ;
await OpenAIClient . beta . assistants . swarm . init ( ) ;

// Optional - set up listeners here to wait for specific events to return to the user since streaming is not available yet.

// Run the main process on a single text prompt to have work delegate between all of your assistants that are available.
const response = OpenAIClient . beta . assistants . swarm . delegateWithPrompt ( 'What is the weather in New York city right now? Also what is the top stock for today?' ) ;
// For example. Given a Pirate bot, Weather Bot, and Stock Bot in your assistant registry on OpenAI.
// Run the below threads in parallel and return to you!
// |--> Will delegate to an existing Weather Bot
// |--> Will delegate to an existing Stock watcher Bot
// -> Pirate bot will not be invoked.
// -----
// The parent will respond with something like "I've arranged for two of our assistants to handle your requests. For assistance with stocks I have delegated that task  to the Stock Bot, and for the weather update in San Francisco, our Weatherbot will provide the current conditions. They will take care of your needs shortly."
//
// You will then get a response once each child responds with either a completion or a `required_action` run you can handle in your codebase easily.

console . log ( {
  parentRun : response . parentRun , // All information about the parent thread
  subRuns : response . subRuns , // array of runs created and their status for each spun-out child thread!
} ) 

利用可能なツール

プロンプトによる代表団

第一に、おそらくあなたが興味を持っている主な主なもの - サブアシスタントへの代表団。セットアップが簡単で、イベントを聴き、現在のワークフローに追加できます。

 // Set up an event listener for when the parent response is completed so you don't have to wait
// for parent + children responses to all complete.
// Useful to return the parent response early while you work on the subtask tool_calls that 
// may or not be required depending on what happened.
OpenAIClient . beta . assistants . swarm . emitter . on ( 'parent_assistant_complete' , ( args ) => {
    console . group ( 'Parent assistant response completed' ) ;
    console . log ( args . parentRun . playground ) // => https://platform.openai.com/playground.... to debug thread & run in browser.
    console . log ( args . parentRun . textResponse ) // => Yarrh! Want to be speaking to the captain do ya? Ill go fetch them ya land lubber.
    // args.parentRun => The full Run object from OpenAI so you can get the thread_id and other properties like status.
    console . log ( 'nn' )
    console . groupEnd ( ) ;
} ) ;

// Set up an event listener for when the delegated assistant responses are completed so you don't have to wait
// for parent + children responses to all complete.
// From here you can handle all sub-run tool_calls if they are required to be run.
OpenAIClient . beta . assistants . swarm . emitter . on ( 'child_assistants_complete' , ( args ) => {
    console . group ( 'Child assistant response completed' ) ;
    console . log ( args . subRuns . map ( ( run ) => run . textResponse ) ) // => Yarrh! I am the captain of this vessel. Ye be after my treasure, Yar?
    console . log ( args . subRuns . map ( ( run ) => run . playground ) ) // => https://platform.openai.com/playground.... to debug thread & run in browser.
    // args.subRuns[x].run => The full Run object from OpenAI so you can get the thread_id and other properties like status.
    console . log ( 'nn' )
    console . groupEnd ( ) ;
} ) ;

// Set up and event listener to see every step event as it is completed:
OpenAIClient . beta . assistants . swarm . emitter . on ( 'poll_event' , ( { data } ) => {
    console . group ( 'Poll event!' ) ;
    console . log ( {
        status : data . status ,
        text : data . prompt || data . textResponse ,
        runId : data ?. run ?. id ,
        link : data . playground ,
        runStatus : data ?. run ?. status ,
    } )
    console . log ( 'nn' )
    console . groupEnd ( ) ;
} ) ;

// Run the main process on a single text prompt to have work delegate between all of the possible assistants that are available.
const response = OpenAIClient . beta . assistants . swarm . delegateWithPrompt ( 'Let me speak to the head pirate of this vessel! What say ye??' ) ;
// You can also just wait for the entire flow to finish instead of setting up listeners to keep the code more synchronous
console . log ( {
  parentRun : response . parentRun ,
  subRuns : response . subRuns ,
} )

// You can also focus the given task or prompt on a subset of assistants that you know you want to handle delegated work.
// OpenAIClient.beta.assistants.swarm.delegateWithPrompt('Let me speak to the head pirate of this vessel! What say ye??', ['asst_lead_pirate']);

利用可能なすべてのアシスタントを取得します

今、あなたは、質問に答えたり、タスクを処理するために誰が周りにいるのかを確認するために、攻撃者をページングする必要があります。今、あなたは1回の電話をかけることができ、私たちはあなたのためにページネーションを処理することができます

 const allAssistants = await OpenAIClient . beta . assistants . swarm . allAssistants ( ) ;
console . log ( `Found ${ allAssistants . length } assistants for this OpenAI Account` ) ;
// will be an array of assistant objects you can filter or manage. The Swarm Manager will not appear here.

一度に多くの既知のアシスタントを取得します

APIを介して一度に1人のアシスタントを取得することに限定されます。今、あなたは一度に多くを得ることができます

 const assistantIds = [ 'asst_customer_success' , 'asst_lead_pirate_manager' , 'asst_that_was_deleted' ]
const specificAssistants = await OpenAIClient . beta . assistants . swarm . getAssistants ( assistantIds ) ;
console . log ( `Found ${ specificAssistants . length } assistants from ${ assistantIds . length } ids given.` ) ;
// Will be an array of assistant objects you can filter or manage. The Swarm Manager will not appear here.
// Invalid assistants will not appear in the end result.