Migrated repository
Go to file
2024-03-08 11:10:10 +08:00
agents-flex-core refactor: refactor Llm and Prompt module 2024-03-08 11:10:10 +08:00
agents-flex-document-parser build: v1.0.0-alpha.2 released 2024-03-07 15:58:40 +08:00
agents-flex-llm refactor: refactor Llm and Prompt module 2024-03-07 18:35:59 +08:00
agents-flex-samples build: v1.0.0-alpha.2 released 2024-03-07 15:58:40 +08:00
agents-flex-store build: v1.0.0-alpha.2 released 2024-03-07 15:58:40 +08:00
agents-flex-test build: v1.0.0-alpha.2 released 2024-03-07 15:58:40 +08:00
docs doc: update docs 2024-03-07 17:26:11 +08:00
.editorconfig init 2024-01-12 16:24:14 +08:00
.gitignore doc: update docs 2024-01-23 11:52:50 +08:00
changes.md init 2024-01-12 16:24:14 +08:00
LICENSE init 2024-01-12 16:24:14 +08:00
pom.xml build: v1.0.0-alpha.2 released 2024-03-07 15:58:40 +08:00
readme_zh.md doc: update docs 2024-03-07 17:26:11 +08:00
readme.md doc: update docs 2024-03-07 17:28:35 +08:00

English | 简体中文

Agents-Flex is a LLM Application Framework like LangChain base on Java.


Features

  • LLM Visit
  • Prompt、Prompt Template Loader
  • Function Calling Definer, Invoker、Running
  • Memory
  • Embedding
  • Vector Storage
  • Resource Loaders
  • Document
    • Splitter
    • Loader
    • Parser
      • PoiParser
      • PdfBoxParser
  • LLMs Chain
  • Agents Chain

Simple Chat

use 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);
}

use Qwen 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);
}

use 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);
}

Chat With Histories

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

        userInput = scanner.nextLine();
    }
}

Function Calling

  • step 1: define the function native
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;
    }
}

  • step 2: invoke the function from 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.invoke();

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

Communication

Modules