Agents-Flex هو إطار تطبيق LLM مثل قاعدة LangChain على Java.

سمات

زيارة LLM
موجه، قالب موجه
محدد استدعاء الوظيفة، المستدعي، التشغيل
ذاكرة
التضمين
متجر المتجهات
محمل الموارد
وثيقة
- الخائن
- محمل
- محلل
  - PoiParser
  - PDFBoxParser
عامل
- وكيل LLM
سلسلة
- SequentialChain
- ParallelChain
- LoopChain
- ChainNode
  - AgentNode
  - EndNode
  - RouterNode
    - GroovyRouterNode
    - QLEExpressRouterNode
    - LLMRouterNode

دردشة بسيطة

استخدم OpenAi LLM:

 @ Test
public void testChat () {
    OpenAiLlmConfig config = new OpenAiLlmConfig ();
    config . setApiKey ( "sk-rts5NF6n*******" );

    Llm llm = new OpenAiLlm ( config );
    String response = llm . chat ( "what is your name?" );

    System . out . println ( response );
}

استخدم كوين LLM:

 @ Test
public void testChat () {
    QwenLlmConfig config = new QwenLlmConfig ();
    config . setApiKey ( "sk-28a6be3236****" );
    config . setModel ( "qwen-turbo" );

    Llm llm = new QwenLlm ( config );
    String response = llm . chat ( "what is your name?" );

    System . out . println ( response );
}

استخدم SparkAi LLM:

 @ Test
public void testChat () {
    SparkLlmConfig config = new SparkLlmConfig ();
    config . setAppId ( "****" );
    config . setApiKey ( "****" );
    config . setApiSecret ( "****" );

    Llm llm = new SparkLlm ( config );
    String response = llm . chat ( "what is your name?" );

    System . out . println ( response );
}

الدردشة مع التاريخ

 public static void main ( String [] args ) {
    SparkLlmConfig config = new SparkLlmConfig ();
    config . setAppId ( "****" );
    config . setApiKey ( "****" );
    config . setApiSecret ( "****" );

    Llm llm = new SparkLlm ( config );

    HistoriesPrompt prompt = new HistoriesPrompt ();

    System . out . println ( "ask for something..." );
    Scanner scanner = new Scanner ( System . in );
    String userInput = scanner . nextLine ();

    while ( userInput != null ) {

        prompt . addMessage ( new HumanMessage ( userInput ));

        llm . chatStream ( prompt , ( context , response ) -> {
            System . out . println ( ">>>> " + response . getMessage (). getContent ());
        });

        userInput = scanner . nextLine ();
    }
}

استدعاء الوظيفة

الخطوة 1: تحديد الوظيفة الأصلية

 public class WeatherUtil {

    @ FunctionDef ( name = "get_the_weather_info" , description = "get the weather info" )
    public static String getWeatherInfo (
        @ FunctionParam ( name = "city" , description = "the city name" ) String name
    ) {
        //we should invoke the third part api for weather info here
        return "Today it will be dull and overcast in " + name ;
    }
}

الخطوة 2: استدعاء الوظيفة من LLM

 public static void main ( String [] args ) {
    OpenAiLlmConfig config = new OpenAiLlmConfig ();
    config . setApiKey ( "sk-rts5NF6n*******" );

    OpenAiLlm llm = new OpenAiLlm ( config );

    FunctionPrompt prompt = new FunctionPrompt ( "How is the weather in Beijing today?" , WeatherUtil . class );
    FunctionResultResponse response = llm . chat ( prompt );

    Object result = response . getFunctionResult ();

    System . out . println ( result );
    //Today it will be dull and overcast in Beijing
}