agents with adk

create a virtual env no matter what to get clean stuff

python -m venv .myvenv #even can be hidden or not
source .myvenv/bin/activate

pip install -r requirements.txt


#delete venv
rm -rf venv

just fo the research agent sample
pip install poetry

# Clone this repository.
git clone https://github.com/google/adk-samples.git
cd adk-samples/python/agents/academic-research
# Install the package and dependencies.
poetry install

cd  till root then 
 adk web
 
 test
 who are you


uv run adk web --port 8501



---
---

## run java check gemini models

structure of project java:


**idx is not required **

enviroment vairables
export GOOGLE_API_KEY=API_KEY
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

then in pom.xml

API KEY generation from console also is gcloud set of commands and also enbale [vertex ai api](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) access.


**append** not add, not put at the end, dependency like this in pom.xml :

<dependencies>
  <dependency>
    <groupId>com.google.genai</groupId>
    <artifactId>google-genai</artifactId>
    <version>0.1.0</version>
  </dependency>
</dependencies>


add code and decorator to main class:
***original code:***

import com.google.genai.Client;
import com.google.genai.types.Content;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.Part;

public class GenerateContentWithText {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.0-flash";
    generateContent(modelId);
  }

  public static String generateContent(String modelId) {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests.
    try (Client client = Client.builder()
        .httpOptions(HttpOptions.builder().apiVersion("v1").build())
        .build()) {

      GenerateContentResponse response =
          client.models.generateContent(modelId, Content.fromParts(
                  Part.fromText("How does AI work?")),
              null);

      System.out.print(response.text());
      // Example response:
      // Okay, let's break down how AI works. It's a broad field, so I'll focus on the ...
      //
      // Here's a simplified overview:
      // ...
      return response.text();
    }
  }
}

***modified code:***

package com.example.demo;


import com.google.genai.Client;
import com.google.genai.types.Content;
import com.google.genai.types.GenerateContentResponse;
import org.springframework.boot.autoconfigure.SpringBootApplication;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.Part;


@SpringBootApplication
public class GenerateContentWithText {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.0-flash";
    generateContent(modelId);
  }

  public static String generateContent(String modelId) {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests.
    try (Client client = Client.builder()
        .httpOptions(HttpOptions.builder().apiVersion("v1").build())
        .build()) {

      GenerateContentResponse response =
          client.models.generateContent(modelId, Content.fromParts(
                  Part.fromText("How does AI work?")),
              null);

      System.out.print(response.text());
      // Example response:
      // Okay, let's break down how AI works. It's a broad field, so I'll focus on the ...
      //
      // Here's a simplified overview:
      // ...
      return response.text();
    }
  }
}


recall to add the springboot decarator to class and import

then try `mvn package, mvn clean install, mvn build` and execute with :

javageminiapp-97980373:~/javageminiapp$ mvn exec:java -Dexec.mainClass="com.GenerateContentWithText.App" 

check class appart if necesary richt click over main class and select `run java` for debbuging

**you should** have a response from model like this one :


refence(s):

https://cloud.google.com/vertex-ai/generative-ai/docs/start/quickstarts/quickstart-multimodal#send-text-only-request