If you program in Java and have never 'played' with GeminiAI, this article will be a great introductory guide, here I will present in a very simple way how to send requests to Gemini and return JSON, like a Rest API. ???
What am I using? ?
- Java 17
- Intelligence Community 2024.1.1
- Postman Card
- GeminiAI access key
LET'S START?
Start a simple project using the spring launcher, and include the following dependencies in your POM
<dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-web</artifactId> </dependency> <dependency> <groupId>org.projectlombok</groupId> <artifactId>lombok</artifactId> <version>1.18.36</version> <scope>provided</scope> </dependency> <dependency> <groupId>com.fasterxml.jackson.core</groupId> <artifactId>jackson-databind</artifactId> <version>2.18.2</version> </dependency>
These dependencies will enable the use of Lombok, RestTemplate and ObjectMapper.
Lombok: to avoid repetitive codes (famous boilerplates) and to improve the readability of our code
RestTemplate: to make the http request to the GeminiAI API
ObjectMapper: to convert the Gemini api return into JSON
?
CONFIGURING THE RESTTEMPLATE
Let's configure the RestTemplate in our Java project, for this we create a class with the @Configuration annotation and the Bean to define it:
@Configuration public class RestTemplateConfig { @Bean public RestTemplate restTemplate(RestTemplateBuilder builder) { return builder.build(); } }
?
CREATING THE SERVICE
Let's create a service class to communicate with GeminiAI, this class will be responsible for all communication and processing of Gemini's response, and should look like this:
@Service public class TalkService { private final RestTemplate restTemplate; private final ObjectMapper objectMapper; @Value("${gemini.ai.api.url}") private String geminiApiUrl; @Value("${gemini.ai.api.key}") private String geminiApiKey; public TalkService(RestTemplate restTemplate, ObjectMapper objectMapper) { this.restTemplate = restTemplate; this.objectMapper = objectMapper; } public String callGeminiAI(TalkRequest input) { String url = geminiApiUrl + geminiApiKey; GeminiRequest request = new GeminiRequest(); GeminiRequest.Content content = new GeminiRequest.Content(); GeminiRequest.Part part = new GeminiRequest.Part(); part.setText(input.getChat()); content.setParts(Collections.singletonList(part)); request.setContents(Collections.singletonList(content)); HttpHeaders headers = new HttpHeaders(); headers.setContentType(MediaType.APPLICATION_JSON); HttpEntity<GeminiRequest> entity = new HttpEntity<>(request, headers); ResponseEntity<String> response = restTemplate.exchange(url, HttpMethod.POST, entity, String.class); try { GeminiResponse geminiAIResponse = objectMapper.readValue(response.getBody(), GeminiResponse.class); if (geminiAIResponse.getCandidates() != null && !geminiAIResponse.getCandidates().isEmpty()) { GeminiResponse.Candidate candidate = geminiAIResponse.getCandidates().get(0); if (candidate.getContent() != null && candidate.getContent().getParts() != null && !candidate.getContent().getParts().isEmpty()) { return candidate.getContent().getParts().get(0).getText(); } } } catch (Exception e) { e.printStackTrace(); } return "Falha ao processar resposta da API"; } }
Note that in this class we are using the POJO's GeminiRequest and GeminiResponse, below is the code to create them
GeminiRequest
@Getter @Setter @AllArgsConstructor @NoArgsConstructor public class GeminiRequest { private List<Content> contents; @Getter @Setter @AllArgsConstructor @NoArgsConstructor public static class Content { private List<Part> parts; } @Getter @Setter @AllArgsConstructor @NoArgsConstructor public static class Part { private String text; } }
GeminiResponse
@Getter @Setter @AllArgsConstructor @NoArgsConstructor @JsonIgnoreProperties(ignoreUnknown = true) public class GeminiResponse { private List<Candidate> candidates; private UsageMetadata usageMetadata; private String modelVersion; @Getter @Setter @AllArgsConstructor @NoArgsConstructor @JsonIgnoreProperties(ignoreUnknown = true) public static class Candidate { private Content content; private String finishReason; private double avgLogprobs; } @Getter @Setter @AllArgsConstructor @NoArgsConstructor @JsonIgnoreProperties(ignoreUnknown = true) public static class Content { private List<Part> parts; } @Getter @Setter @AllArgsConstructor @NoArgsConstructor @JsonIgnoreProperties(ignoreUnknown = true) public static class Part { private String text; } @Getter @Setter @AllArgsConstructor @NoArgsConstructor @JsonIgnoreProperties(ignoreUnknown = true) public static class UsageMetadata { private int promptTokenCount; private int candidatesTokenCount; private int totalTokenCount; } }
?
CREATING A CONTROLLER
Now let's create a controller to listen to a Rest request and process it through our Service
@RestController @RequestMapping("v1") public class TalkController { private final TalkService talkService; @Autowired public TalkController(final TalkService talkService) { this.talkService = talkService; } @PostMapping("/chat-gemini") public TalkResponse talk(@RequestBody TalkRequest talkRequest) { TalkResponse response = new TalkResponse(); response.setResponse(talkService.callGeminiAI(talkRequest)); return response; } }
Our controller also has POJO's, check out their code below
TalkRequest
@Getter @Setter @AllArgsConstructor public class TalkRequest { private String chat; }
TalkResponse
@Getter @Setter @AllArgsConstructor @NoArgsConstructor public class TalkResponse { private String response; }
?
CONFIGURING VARIABLES IN PROPERTIES
You will need to inform the GeminiAI access endpoint and also your access key. I stored this information in the properties file, since we are talking about a simple test. Check the properties file with the necessary variables
spring.application.name=NOME_DA_SUA_APLICACAO gemini.ai.api.url=https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key= gemini.ai.api.key=SUA_CHAVE_DE_ACESSO
?
LET'S TEST IT???
We already have communication with GeminiAI, now we can test our application using postman, to do this start your application in Intellij and execute the request in postman as shown in the image below:
CONCLUSION ?
The purpose of this article was to introduce Java programmers to connecting GeminiAI with a Java application, creating infinite new possibilities for use. I hope you enjoyed it, see you next time! ?
The above is the detailed content of Communicating JAVA with GeminiAI. For more information, please follow other related articles on the PHP Chinese website!

Hot AI Tools

Undress AI Tool
Undress images for free

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Clothoff.io
AI clothes remover

Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Article

Hot Tools

Notepad++7.3.1
Easy-to-use and free code editor

SublimeText3 Chinese version
Chinese version, very easy to use

Zend Studio 13.0.1
Powerful PHP integrated development environment

Dreamweaver CS6
Visual web development tools

SublimeText3 Mac version
God-level code editing software (SublimeText3)

Hot Topics

The difference between HashMap and Hashtable is mainly reflected in thread safety, null value support and performance. 1. In terms of thread safety, Hashtable is thread-safe, and its methods are mostly synchronous methods, while HashMap does not perform synchronization processing, which is not thread-safe; 2. In terms of null value support, HashMap allows one null key and multiple null values, while Hashtable does not allow null keys or values, otherwise a NullPointerException will be thrown; 3. In terms of performance, HashMap is more efficient because there is no synchronization mechanism, and Hashtable has a low locking performance for each operation. It is recommended to use ConcurrentHashMap instead.

Java uses wrapper classes because basic data types cannot directly participate in object-oriented operations, and object forms are often required in actual needs; 1. Collection classes can only store objects, such as Lists use automatic boxing to store numerical values; 2. Generics do not support basic types, and packaging classes must be used as type parameters; 3. Packaging classes can represent null values ??to distinguish unset or missing data; 4. Packaging classes provide practical methods such as string conversion to facilitate data parsing and processing, so in scenarios where these characteristics are needed, packaging classes are indispensable.

StaticmethodsininterfaceswereintroducedinJava8toallowutilityfunctionswithintheinterfaceitself.BeforeJava8,suchfunctionsrequiredseparatehelperclasses,leadingtodisorganizedcode.Now,staticmethodsprovidethreekeybenefits:1)theyenableutilitymethodsdirectly

The JIT compiler optimizes code through four methods: method inline, hot spot detection and compilation, type speculation and devirtualization, and redundant operation elimination. 1. Method inline reduces call overhead and inserts frequently called small methods directly into the call; 2. Hot spot detection and high-frequency code execution and centrally optimize it to save resources; 3. Type speculation collects runtime type information to achieve devirtualization calls, improving efficiency; 4. Redundant operations eliminate useless calculations and inspections based on operational data deletion, enhancing performance.

Instance initialization blocks are used in Java to run initialization logic when creating objects, which are executed before the constructor. It is suitable for scenarios where multiple constructors share initialization code, complex field initialization, or anonymous class initialization scenarios. Unlike static initialization blocks, it is executed every time it is instantiated, while static initialization blocks only run once when the class is loaded.

InJava,thefinalkeywordpreventsavariable’svaluefrombeingchangedafterassignment,butitsbehaviordiffersforprimitivesandobjectreferences.Forprimitivevariables,finalmakesthevalueconstant,asinfinalintMAX_SPEED=100;wherereassignmentcausesanerror.Forobjectref

There are two types of conversion: implicit and explicit. 1. Implicit conversion occurs automatically, such as converting int to double; 2. Explicit conversion requires manual operation, such as using (int)myDouble. A case where type conversion is required includes processing user input, mathematical operations, or passing different types of values ??between functions. Issues that need to be noted are: turning floating-point numbers into integers will truncate the fractional part, turning large types into small types may lead to data loss, and some languages ??do not allow direct conversion of specific types. A proper understanding of language conversion rules helps avoid errors.

Factory mode is used to encapsulate object creation logic, making the code more flexible, easy to maintain, and loosely coupled. The core answer is: by centrally managing object creation logic, hiding implementation details, and supporting the creation of multiple related objects. The specific description is as follows: the factory mode handes object creation to a special factory class or method for processing, avoiding the use of newClass() directly; it is suitable for scenarios where multiple types of related objects are created, creation logic may change, and implementation details need to be hidden; for example, in the payment processor, Stripe, PayPal and other instances are created through factories; its implementation includes the object returned by the factory class based on input parameters, and all objects realize a common interface; common variants include simple factories, factory methods and abstract factories, which are suitable for different complexities.
