Name	Name	Last commit message	Last commit date
Latest commit History 359 Commits
.devcontainer	.devcontainer
.github	.github
bin	bin
buildSrc	buildSrc
gradle/wrapper	gradle/wrapper
openai-java-client-okhttp	openai-java-client-okhttp
openai-java-core	openai-java-core
openai-java-example	openai-java-example
openai-java-lib	openai-java-lib
openai-java	openai-java
scripts	scripts
.gitattributes	.gitattributes
.gitignore	.gitignore
.release-please-manifest.json	.release-please-manifest.json
.stats.yml	.stats.yml
CHANGELOG.md	CHANGELOG.md
LICENSE	LICENSE
README.md	README.md
SECURITY.md	SECURITY.md
build.gradle.kts	build.gradle.kts
gradle.properties	gradle.properties
gradlew	gradlew
gradlew.bat	gradlew.bat
release-please-config.json	release-please-config.json
settings.gradle.kts	settings.gradle.kts

OpenAI Java API Library

The OpenAI Java SDK provides convenient access to the OpenAI REST API from applications written in Java.

The REST API documentation can be found on platform.openai.com. Javadocs are available on javadoc.io.

Installation

Gradle

implementation("com.openai:openai-java:1.6.0")

Maven

<dependency>
  <groupId>com.openai</groupId>
  <artifactId>openai-java</artifactId>
  <version>1.6.0</version>
</dependency>

Requirements

This library requires Java 8 or later.

Usage

See the openai-java-example directory for complete and runnable examples.

The primary API for interacting with OpenAI models is the Responses API. You can generate text from the model with the code below.

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.ChatModel;
import com.openai.models.responses.Response;
import com.openai.models.responses.ResponseCreateParams;

// Configures using the `OPENAI_API_KEY`, `OPENAI_ORG_ID` and `OPENAI_PROJECT_ID` environment variables
OpenAIClient client = OpenAIOkHttpClient.fromEnv();

ResponseCreateParams params = ResponseCreateParams.builder()
        .input("Say this is a test")
        .model(ChatModel.GPT_4_1)
        .build();
Response response = client.responses().create(params);

The previous standard (supported indefinitely) for generating text is the Chat Completions API. You can use that API to generate text from the model with the code below.

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.ChatModel;
import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

// Configures using the `OPENAI_API_KEY`, `OPENAI_ORG_ID`, `OPENAI_PROJECT_ID` and `OPENAI_BASE_URL` environment variables
OpenAIClient client = OpenAIOkHttpClient.fromEnv();

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .addUserMessage("Say this is a test")
    .model(ChatModel.GPT_4_1)
    .build();
ChatCompletion chatCompletion = client.chat().completions().create(params);

Client configuration

Configure the client using environment variables:

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;

// Configures using the `OPENAI_API_KEY`, `OPENAI_ORG_ID`, `OPENAI_PROJECT_ID` and `OPENAI_BASE_URL` environment variables
OpenAIClient client = OpenAIOkHttpClient.fromEnv();

Or manually:

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .apiKey("My API Key")
    .build();

Or using a combination of the two approaches:

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;

OpenAIClient client = OpenAIOkHttpClient.builder()
    // Configures using the `OPENAI_API_KEY`, `OPENAI_ORG_ID`, `OPENAI_PROJECT_ID` and `OPENAI_BASE_URL` environment variables
    .fromEnv()
    .apiKey("My API Key")
    .build();

See this table for the available options:

Setter	Environment variable	Required	Default value
`apiKey`	`OPENAI_API_KEY`	true	-
`organization`	`OPENAI_ORG_ID`	false	-
`project`	`OPENAI_PROJECT_ID`	false	-
`baseUrl`	`OPENAI_BASE_URL`	true	`"https://api.openai.com/v1"`

Tip

Don't create more than one client in the same application. Each client has a connection pool and thread pools, which are more efficient to share between requests.

Requests and responses

To send a request to the OpenAI API, build an instance of some Params class and pass it to the corresponding client method. When the response is received, it will be deserialized into an instance of a Java class.

For example, client.chat().completions().create(...) should be called with an instance of ChatCompletionCreateParams, and it will return an instance of ChatCompletion.

Immutability

Each class in the SDK has an associated builder or factory method for constructing it.

Each class is immutable once constructed. If the class has an associated builder, then it has a toBuilder() method, which can be used to convert it back to a builder for making a modified copy.

Because each class is immutable, builder modification will never affect already built class instances.

Asynchronous execution

The default client is synchronous. To switch to asynchronous execution, call the async() method:

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.ChatModel;
import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionCreateParams;
import java.util.concurrent.CompletableFuture;

// Configures using the `OPENAI_API_KEY`, `OPENAI_ORG_ID`, `OPENAI_PROJECT_ID` and `OPENAI_BASE_URL` environment variables
OpenAIClient client = OpenAIOkHttpClient.fromEnv();

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .addUserMessage("Say this is a test")
    .model(ChatModel.GPT_4_1)
    .build();
CompletableFuture<ChatCompletion> chatCompletion = client.async().chat().completions().create(params);

Or create an asynchronous client from the beginning:

import com.openai.client.OpenAIClientAsync;
import com.openai.client.okhttp.OpenAIOkHttpClientAsync;
import com.openai.models.ChatModel;
import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionCreateParams;
import java.util.concurrent.CompletableFuture;

// Configures using the `OPENAI_API_KEY`, `OPENAI_ORG_ID`, `OPENAI_PROJECT_ID` and `OPENAI_BASE_URL` environment variables
OpenAIClientAsync client = OpenAIOkHttpClientAsync.fromEnv();

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .addUserMessage("Say this is a test")
    .model(ChatModel.GPT_4_1)
    .build();
CompletableFuture<ChatCompletion> chatCompletion = client.chat().completions().create(params);

The asynchronous client supports the same options as the synchronous one, except most methods return CompletableFutures.

Streaming

The SDK defines methods that return response "chunk" streams, where each chunk can be individually processed as soon as it arrives instead of waiting on the full response. Streaming methods generally correspond to SSE or JSONL responses.

Some of these methods may have streaming and non-streaming variants, but a streaming method will always have a Streaming suffix in its name, even if it doesn't have a non-streaming variant.

These streaming methods return StreamResponse for synchronous clients:

import com.openai.core.http.StreamResponse;
import com.openai.models.chat.completions.ChatCompletionChunk;

try (StreamResponse<ChatCompletionChunk> streamResponse = client.chat().completions().createStreaming(params)) {
    streamResponse.stream().forEach(chunk -> {
        System.out.println(chunk);
    });
    System.out.println("No more chunks!");
}

Or AsyncStreamResponse for asynchronous clients:

import com.openai.core.http.AsyncStreamResponse;
import com.openai.models.chat.completions.ChatCompletionChunk;
import java.util.Optional;

client.async().chat().completions().createStreaming(params).subscribe(chunk -> {
    System.out.println(chunk);
});

// If you need to handle errors or completion of the stream
client.async().chat().completions().createStreaming(params).subscribe(new AsyncStreamResponse.Handler<>() {
    @Override
    public void onNext(ChatCompletionChunk chunk) {
        System.out.println(chunk);
    }

    @Override
    public void onComplete(Optional<Throwable> error) {
        if (error.isPresent()) {
            System.out.println("Something went wrong!");
            throw new RuntimeException(error.get());
        } else {
            System.out.println("No more chunks!");
        }
    }
});

// Or use futures
client.async().chat().completions().createStreaming(params)
    .subscribe(chunk -> {
        System.out.println(chunk);
    })
    .onCompleteFuture();
    .whenComplete((unused, error) -> {
        if (error != null) {
            System.out.println("Something went wrong!");
            throw new RuntimeException(error);
        } else {
            System.out.println("No more chunks!");
        }
    });

Async streaming uses a dedicated per-client cached thread pool Executor to stream without blocking the current thread. This default is suitable for most purposes.

To use a different Executor, configure the subscription using the executor parameter:

import java.util.concurrent.Executor;
import java.util.concurrent.Executors;

Executor executor = Executors.newFixedThreadPool(4);
client.async().chat().completions().createStreaming(params).subscribe(
    chunk -> System.out.println(chunk), executor
);

Or configure the client globally using the streamHandlerExecutor method:

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import java.util.concurrent.Executors;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .fromEnv()
    .streamHandlerExecutor(Executors.newFixedThreadPool(4))
    .build();

Streaming helpers

The SDK provides conveniences for streamed chat completions. A ChatCompletionAccumulator can record the stream of chat completion chunks in the response as they are processed and accumulate a ChatCompletion object similar to that which would have been returned by the non-streaming API.

For a synchronous response add a Stream.peek() call to the stream pipeline to accumulate each chunk:

import com.openai.core.http.StreamResponse;
import com.openai.helpers.ChatCompletionAccumulator;
import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionChunk;

ChatCompletionAccumulator chatCompletionAccumulator = ChatCompletionAccumulator.create();

try (StreamResponse<ChatCompletionChunk> streamResponse =
        client.chat().completions().createStreaming(createParams)) {
    streamResponse.stream()
            .peek(chatCompletionAccumulator::accumulate)
            .flatMap(completion -> completion.choices().stream())
            .flatMap(choice -> choice.delta().content().stream())
            .forEach(System.out::print);
}

ChatCompletion chatCompletion = chatCompletionAccumulator.chatCompletion();

For an asynchronous response, add the ChatCompletionAccumulator to the subscribe() call:

import com.openai.helpers.ChatCompletionAccumulator;
import com.openai.models.chat.completions.ChatCompletion;

ChatCompletionAccumulator chatCompletionAccumulator = ChatCompletionAccumulator.create();

client.chat()
        .completions()
        .createStreaming(createParams)
        .subscribe(chunk -> chatCompletionAccumulator.accumulate(chunk).choices().stream()
                .flatMap(choice -> choice.delta().content().stream())
                .forEach(System.out::print))
        .onCompleteFuture()
        .join();

ChatCompletion chatCompletion = chatCompletionAccumulator.chatCompletion();

Structured outputs with JSON schemas

Open AI Structured Outputs is a feature that ensures that the model will always generate responses that adhere to a supplied JSON schema.

A JSON schema can be defined by creating a ResponseFormatJsonSchema and setting it on the input parameters. However, for greater convenience, a JSON schema can instead be derived automatically from the structure of an arbitrary Java class. The JSON content from the response will then be converted automatically to an instance of that Java class. A full, working example of the use of Structured Outputs with arbitrary Java classes can be seen in StructuredOutputsClassExample.

Java classes can contain fields declared to be instances of other classes and can use collections:

class Person {
    public String name;
    public int birthYear;
}

class Book {
    public String title;
    public Person author;
    public int publicationYear;
}

class BookList {
    public List<Book> books;
}

Pass the top-level class—BookList in this example—to responseFormat(Class<T>) when building the parameters and then access an instance of BookList from the generated message content in the response:

import com.openai.models.ChatModel;
import com.openai.models.chat.completions.ChatCompletionCreateParams;
import com.openai.models.chat.completions.StructuredChatCompletionCreateParams;

StructuredChatCompletionCreateParams<BookList> params = ChatCompletionCreateParams.builder()
        .addUserMessage("List some famous late twentieth century novels.")
        .model(ChatModel.GPT_4_1)
        .responseFormat(BookList.class)
        .build();

client.chat().completions().create(params).choices().stream()
        .flatMap(choice -> choice.message().content().stream())
        .flatMap(bookList -> bookList.books.stream())
        .forEach(book -> System.out.println(book.title + " by " + book.author.name));

You can start building the parameters with an instance of ChatCompletionCreateParams.Builder or StructuredChatCompletionCreateParams.Builder. If you start with the former (which allows for more compact code) the builder type will change to the latter when ChatCompletionCreateParams.Builder.responseFormat(Class<T>) is called.

If a field in a class is optional and does not require a defined value, you can represent this using the java.util.Optional class. It is up to the AI model to decide whether to provide a value for that field or leave it empty.

import java.util.Optional;

class Book {
    public String title;
    public Person author;
    public int publicationYear;
    public Optional<String> isbn;
}

Generic type information for fields is retained in the class's metadata, but generic type erasure applies in other scopes. While, for example, a JSON schema defining an array of strings can be derived from the BoolList.books field with type List<String>, a valid JSON schema cannot be derived from a local variable of that same type, so the following will not work:

List<String> books = new ArrayList<>();

StructuredChatCompletionCreateParams<BookList> params = ChatCompletionCreateParams.builder()
        .responseFormat(books.class)
        // ...
        .build();

If an error occurs while converting a JSON response to an instance of a Java class, the error message will include the JSON response to assist in diagnosis. For instance, if the response is truncated, the JSON data will be incomplete and cannot be converted to a class instance. If your JSON response may contain sensitive information, avoid logging it directly, or ensure that you redact any sensitive details from the error message.

Local JSON schema validation

Structured Outputs supports a subset of the JSON Schema language. Schemas are generated automatically from classes to align with this subset. However, due to the inherent structure of the classes, the generated schema may still violate certain OpenAI schema restrictions, such as exceeding the maximum nesting depth or utilizing unsupported data types.

To facilitate compliance, the method responseFormat(Class<T>) performs a validation check on the schema derived from the specified class. This validation ensures that all restrictions are adhered to. If any issues are detected, an exception will be thrown, providing a detailed message outlining the reasons for the validation failure.

Local Validation: The validation process occurs locally, meaning no requests are sent to the remote AI model. If the schema passes local validation, it is likely to pass remote validation as well.
Remote Validation: The remote AI model will conduct its own validation upon receiving the JSON schema in the request.
Version Compatibility: There may be instances where local validation fails while remote validation succeeds. This can occur if the SDK version is outdated compared to the restrictions enforced by the remote AI model.
Disabling Local Validation: If you encounter compatibility issues and wish to bypass local validation, you can disable it by passing JsonSchemaLocalValidation.NO to the responseFormat(Class<T>, JsonSchemaLocalValidation) method when building the parameters. (The default value for this parameter is JsonSchemaLocalValidation.YES.)

import com.openai.core.JsonSchemaLocalValidation;
import com.openai.models.ChatModel;
import com.openai.models.chat.completions.ChatCompletionCreateParams;
import com.openai.models.chat.completions.StructuredChatCompletionCreateParams;

StructuredChatCompletionCreateParams<BookList> params = ChatCompletionCreateParams.builder()
        .addUserMessage("List some famous late twentieth century novels.")
        .model(ChatModel.GPT_4_1)
        .responseFormat(BookList.class, JsonSchemaLocalValidation.NO)
        .build();

By following these guidelines, you can ensure that your structured outputs conform to the necessary schema requirements and minimize the risk of remote validation errors.

Annotating classes and JSON schemas

You can use annotations to add further information to the JSON schema derived from your Java classes, or to exclude individual fields from the schema. Details from annotations captured in the JSON schema may be used by the AI model to improve its response. The SDK supports the use of Jackson Databind annotations.

import com.fasterxml.jackson.annotation.JsonClassDescription;
import com.fasterxml.jackson.annotation.JsonIgnore;
import com.fasterxml.jackson.annotation.JsonPropertyDescription;

class Person {
    @JsonPropertyDescription("The first name and surname of the person")
    public String name;
    public int birthYear;
    @JsonPropertyDescription("The year the person died, or 'present' if the person is living.")
    public String deathYear;
}

@JsonClassDescription("The details of one published book")
class Book {
    public String title;
    public Person author;
    @JsonPropertyDescription("The year in which the book was first published.")
    public int publicationYear;
    @JsonIgnore public String genre;
}

class BookList {
    public List<Book> books;
}

Use @JsonClassDescription to add a detailed description to a class.
Use @JsonPropertyDescription to add a detailed description to a field of a class.
Use @JsonIgnore to omit a field of a class from the generated JSON schema.

If you use @JsonProperty(required = false), the false value will be ignored. OpenAI JSON schemas must mark all properties as required, so the schema generated from your Java classes will respect that restriction and ignore any annotation that would violate it.

File uploads

The SDK defines methods that accept files.

To upload a file, pass a Path:

import com.openai.models.files.FileCreateParams;
import com.openai.models.files.FileObject;
import com.openai.models.files.FilePurpose;
import java.nio.file.Paths;

FileCreateParams params = FileCreateParams.builder()
    .purpose(FilePurpose.FINE_TUNE)
    .file(Paths.get("input.jsonl"))
    .build();
FileObject fileObject = client.files().create(params);

Or an arbitrary InputStream:

import com.openai.models.files.FileCreateParams;
import com.openai.models.files.FileObject;
import com.openai.models.files.FilePurpose;
import java.net.URL;

FileCreateParams params = FileCreateParams.builder()
    .purpose(FilePurpose.FINE_TUNE)
    .file(new URL("https://example.com/input.jsonl").openStream())
    .build();
FileObject fileObject = client.files().create(params);

Or a byte[] array:

import com.openai.models.files.FileCreateParams;
import com.openai.models.files.FileObject;
import com.openai.models.files.FilePurpose;

FileCreateParams params = FileCreateParams.builder()
    .purpose(FilePurpose.FINE_TUNE)
    .file("content".getBytes())
    .build();
FileObject fileObject = client.files().create(params);

Note that when passing a non-Path its filename is unknown so it will not be included in the request. To manually set a filename, pass a MultipartField:

import com.openai.core.MultipartField;
import com.openai.models.files.FileCreateParams;
import com.openai.models.files.FileObject;
import com.openai.models.files.FilePurpose;
import java.io.InputStream;
import java.net.URL;

FileCreateParams params = FileCreateParams.builder()
    .purpose(FilePurpose.FINE_TUNE)
    .file(MultipartField.<InputStream>builder()
        .value(new URL("https://example.com/input.jsonl").openStream())
        .filename("input.jsonl")
        .build())
    .build();
FileObject fileObject = client.files().create(params);

Binary responses

The SDK defines methods that return binary responses, which are used for API responses that shouldn't necessarily be parsed, like non-JSON data.

These methods return HttpResponse:

import com.openai.core.http.HttpResponse;
import com.openai.models.files.FileContentParams;

FileContentParams params = FileContentParams.builder()
    .fileId("file_id")
    .build();
HttpResponse response = client.files().content(params);

To save the response content to a file, use the Files.copy(...) method:

import com.openai.core.http.HttpResponse;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.nio.file.StandardCopyOption;

try (HttpResponse response = client.files().content(params)) {
    Files.copy(
        response.body(),
        Paths.get(path),
        StandardCopyOption.REPLACE_EXISTING
    );
} catch (Exception e) {
    System.out.println("Something went wrong!");
    throw new RuntimeException(e);
}

Or transfer the response content to any OutputStream:

import com.openai.core.http.HttpResponse;
import java.nio.file.Files;
import java.nio.file.Paths;

try (HttpResponse response = client.files().content(params)) {
    response.body().transferTo(Files.newOutputStream(Paths.get(path)));
} catch (Exception e) {
    System.out.println("Something went wrong!");
    throw new RuntimeException(e);
}

Raw responses

The SDK defines methods that deserialize responses into instances of Java classes. However, these methods don't provide access to the response headers, status code, or the raw response body.

To access this data, prefix any HTTP method call on a client or service with withRawResponse():

import com.openai.core.http.Headers;
import com.openai.core.http.HttpResponseFor;
import com.openai.models.ChatModel;
import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .addUserMessage("Say this is a test")
    .model(ChatModel.GPT_4_1)
    .build();
HttpResponseFor<ChatCompletion> chatCompletion = client.chat().completions().withRawResponse().create(params);

int statusCode = chatCompletion.statusCode();
Headers headers = chatCompletion.headers();

You can still deserialize the response into an instance of a Java class if needed:

import com.openai.models.chat.completions.ChatCompletion;

ChatCompletion parsedChatCompletion = chatCompletion.parse();

Request IDs

For more information on debugging requests, see the API docs.

When using raw responses, you can access the x-request-id response header using the requestId() method:

import com.openai.core.http.HttpResponseFor;
import com.openai.models.chat.completions.ChatCompletion;
import java.util.Optional;

HttpResponseFor<ChatCompletion> chatCompletion = client.chat().completions().withRawResponse().create(params);
Optional<String> requestId = chatCompletion.requestId();

This can be used to quickly log failing requests and report them back to OpenAI.

Error handling

The SDK throws custom unchecked exception types:

OpenAIServiceException: Base class for HTTP errors. See this table for which exception subclass is thrown for each HTTP status code:

Status	Exception
400	`BadRequestException`
401	`UnauthorizedException`
403	`PermissionDeniedException`
404	`NotFoundException`
422	`UnprocessableEntityException`
429	`RateLimitException`
5xx	`InternalServerException`
others	`UnexpectedStatusCodeException`

SseException is thrown for errors encountered during SSE streaming after a successful initial HTTP response.

OpenAIIoException: I/O networking errors.
OpenAIInvalidDataException: Failure to interpret successfully parsed data. For example, when accessing a property that's supposed to be required, but the API unexpectedly omitted it from the response.
OpenAIException: Base class for all exceptions. Most errors will result in one of the previously mentioned ones, but completely generic errors may be thrown using the base class.

Pagination

For methods that return a paginated list of results, this library provides convenient ways access the results either one page at a time, or item-by-item across all pages.

Auto-pagination

To iterate through all results across all pages, you can use autoPager, which automatically handles fetching more pages for you:

Synchronous

import com.openai.models.finetuning.jobs.FineTuningJob;
import com.openai.models.finetuning.jobs.JobListPage;

// As an Iterable:
JobListPage page = client.fineTuning().jobs().list(params);
for (FineTuningJob job : page.autoPager()) {
    System.out.println(job);
};

// As a Stream:
client.fineTuning().jobs().list(params).autoPager().stream()
    .limit(50)
    .forEach(job -> System.out.println(job));

Asynchronous

// Using forEach, which returns CompletableFuture<Void>:
asyncClient.fineTuning().jobs().list(params).autoPager()
    .forEach(job -> System.out.println(job), executor);

Manual pagination

If none of the above helpers meet your needs, you can also manually request pages one-by-one. A page of results has a data() method to fetch the list of objects, as well as top-level response and other methods to fetch top-level data about the page. It also has methods hasNextPage, getNextPage, and getNextPageParams methods to help with pagination.

import com.openai.models.finetuning.jobs.FineTuningJob;
import com.openai.models.finetuning.jobs.JobListPage;

JobListPage page = client.fineTuning().jobs().list(params);
while (page != null) {
    for (FineTuningJob job : page.data()) {
        System.out.println(job);
    }

    page = page.getNextPage().orElse(null);
}

Logging

The SDK uses the standard OkHttp logging interceptor.

Enable logging by setting the OPENAI_LOG environment variable to info:

$ export OPENAI_LOG=info

Or to debug for more verbose logging:

$ export OPENAI_LOG=debug

Jackson

The SDK depends on Jackson for JSON serialization/deserialization. It is compatible with version 2.13.4 or higher, but depends on version 2.18.2 by default.

The SDK throws an exception if it detects an incompatible Jackson version at runtime (e.g. if the default version was overridden in your Maven or Gradle config).

If the SDK threw an exception, but you're certain the version is compatible, then disable the version check using the checkJacksonVersionCompatibility on OpenAIOkHttpClient or OpenAIOkHttpClientAsync.

Caution

We make no guarantee that the SDK works correctly when the Jackson version check is disabled.

Microsoft Azure

To use this library with Azure OpenAI, use the same OpenAI client builder but with the Azure-specific configuration.

OpenAIClient client = OpenAIOkHttpClient.builder()
        // Gets the API key and endpoint from the `AZURE_OPENAI_KEY` and `OPENAI_BASE_URL` environment variables, respectively
        .fromEnv()
        // Set the Azure Entra ID
        .credential(BearerTokenCredential.create(AuthenticationUtil.getBearerTokenSupplier(
                new DefaultAzureCredentialBuilder().build(), "https://cognitiveservices.azure.com/.default")))
        .build();

See the complete Azure OpenAI example in the openai-java-example directory. The other examples in the directory also work with Azure as long as the client is configured to use it.

Network options

Retries

The SDK automatically retries 2 times by default, with a short exponential backoff.

Only the following error types are retried:

Connection errors (for example, due to a network connectivity problem)
408 Request Timeout
409 Conflict
429 Rate Limit
5xx Internal

The API may also explicitly instruct the SDK to retry or not retry a response.

To set a custom number of retries, configure the client using the maxRetries method:

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .fromEnv()
    .maxRetries(4)
    .build();

Timeouts

Requests time out after 10 minutes by default.

To set a custom timeout, configure the method call using the timeout method:

import com.openai.models.ChatModel;
import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

ChatCompletion chatCompletion = client.chat().completions().create(
  params, RequestOptions.builder().timeout(Duration.ofSeconds(30)).build()
);

Or configure the default for all method calls at the client level:

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import java.time.Duration;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .fromEnv()
    .timeout(Duration.ofSeconds(30))
    .build();

Proxies

To route requests through a proxy, configure the client using the proxy method:

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import java.net.InetSocketAddress;
import java.net.Proxy;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .fromEnv()
    .proxy(new Proxy(
      Proxy.Type.HTTP, new InetSocketAddress(
        "https://example.com", 8080
      )
    ))
    .build();

Custom HTTP client

The SDK consists of three artifacts:

openai-java-core
- Contains core SDK logic
- Does not depend on OkHttp
- Exposes OpenAIClient, OpenAIClientAsync, OpenAIClientImpl, and OpenAIClientAsyncImpl, all of which can work with any HTTP client
openai-java-client-okhttp
- Depends on OkHttp
- Exposes OpenAIOkHttpClient and OpenAIOkHttpClientAsync, which provide a way to construct OpenAIClientImpl and OpenAIClientAsyncImpl, respectively, using OkHttp
openai-java
- Depends on and exposes the APIs of both openai-java-core and openai-java-client-okhttp
- Does not have its own logic

This structure allows replacing the SDK's default HTTP client without pulling in unnecessary dependencies.

Customized `OkHttpClient`

Tip

Try the available network options before replacing the default client.

To use a customized OkHttpClient:

Replace your openai-java dependency with openai-java-core
Copy openai-java-client-okhttp's OkHttpClient class into your code and customize it
Construct OpenAIClientImpl or OpenAIClientAsyncImpl, similarly to OpenAIOkHttpClient or OpenAIOkHttpClientAsync, using your customized client

Completely custom HTTP client

To use a completely custom HTTP client:

Replace your openai-java dependency with openai-java-core
Write a class that implements the HttpClient interface
Construct OpenAIClientImpl or OpenAIClientAsyncImpl, similarly to OpenAIOkHttpClient or OpenAIOkHttpClientAsync, using your new client class

Undocumented API functionality

The SDK is typed for convenient usage of the documented API. However, it also supports working with undocumented or not yet supported parts of the API.

Parameters

To set undocumented parameters, call the putAdditionalHeader, putAdditionalQueryParam, or putAdditionalBodyProperty methods on any Params class:

import com.openai.core.JsonValue;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .putAdditionalHeader("Secret-Header", "42")
    .putAdditionalQueryParam("secret_query_param", "42")
    .putAdditionalBodyProperty("secretProperty", JsonValue.from("42"))
    .build();

These can be accessed on the built object later using the _additionalHeaders(), _additionalQueryParams(), and _additionalBodyProperties() methods.

To set undocumented parameters on nested headers, query params, or body classes, call the putAdditionalProperty method on the nested class:

import com.openai.core.JsonValue;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .responseFormat(ChatCompletionCreateParams.ResponseFormat.builder()
        .putAdditionalProperty("secretProperty", JsonValue.from("42"))
        .build())
    .build();

These properties can be accessed on the nested built object later using the _additionalProperties() method.

To set a documented parameter or property to an undocumented or not yet supported value, pass a JsonValue object to its setter:

import com.openai.core.JsonValue;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .addUserMessage("Say this is a test")
    .model(JsonValue.from(42))
    .build();

The most straightforward way to create a JsonValue is using its from(...) method:

import com.openai.core.JsonValue;
import java.util.List;
import java.util.Map;

// Create primitive JSON values
JsonValue nullValue = JsonValue.from(null);
JsonValue booleanValue = JsonValue.from(true);
JsonValue numberValue = JsonValue.from(42);
JsonValue stringValue = JsonValue.from("Hello World!");

// Create a JSON array value equivalent to `["Hello", "World"]`
JsonValue arrayValue = JsonValue.from(List.of(
  "Hello", "World"
));

// Create a JSON object value equivalent to `{ "a": 1, "b": 2 }`
JsonValue objectValue = JsonValue.from(Map.of(
  "a", 1,
  "b", 2
));

// Create an arbitrarily nested JSON equivalent to:
// {
//   "a": [1, 2],
//   "b": [3, 4]
// }
JsonValue complexValue = JsonValue.from(Map.of(
  "a", List.of(
    1, 2
  ),
  "b", List.of(
    3, 4
  )
));

Normally a Builder class's build method will throw IllegalStateException if any required parameter or property is unset.

To forcibly omit a required parameter or property, pass JsonMissing:

import com.openai.core.JsonMissing;
import com.openai.models.ChatModel;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .model(ChatModel.GPT_4_1)
    .messages(JsonMissing.of())
    .build();

Response properties

To access undocumented response properties, call the _additionalProperties() method:

import com.openai.core.JsonValue;
import java.util.Map;

Map<String, JsonValue> additionalProperties = client.chat().completions().create(params)._additionalProperties();
JsonValue secretPropertyValue = additionalProperties.get("secretProperty");

String result = secretPropertyValue.accept(new JsonValue.Visitor<>() {
    @Override
    public String visitNull() {
        return "It's null!";
    }

    @Override
    public String visitBoolean(boolean value) {
        return "It's a boolean!";
    }

    @Override
    public String visitNumber(Number value) {
        return "It's a number!";
    }

    // Other methods include `visitMissing`, `visitString`, `visitArray`, and `visitObject`
    // The default implementation of each unimplemented method delegates to `visitDefault`, which throws by default, but can also be overridden
});

To access a property's raw JSON value, which may be undocumented, call its _ prefixed method:

import com.openai.core.JsonField;
import com.openai.models.chat.completions.ChatCompletionMessageParam;
import java.util.Optional;

JsonField<List<ChatCompletionMessageParam>> messages = client.chat().completions().create(params)._messages();

if (messages.isMissing()) {
  // The property is absent from the JSON response
} else if (messages.isNull()) {
  // The property was set to literal null
} else {
  // Check if value was provided as a string
  // Other methods include `asNumber()`, `asBoolean()`, etc.
  Optional<String> jsonString = messages.asString();

  // Try to deserialize into a custom type
  MyClass myObject = messages.asUnknown().orElseThrow().convert(MyClass.class);
}

Response validation

In rare cases, the API may return a response that doesn't match the expected type. For example, the SDK may expect a property to contain a String, but the API could return something else.

By default, the SDK will not throw an exception in this case. It will throw OpenAIInvalidDataException only if you directly access the property.

If you would prefer to check that the response is completely well-typed upfront, then either call validate():

import com.openai.models.chat.completions.ChatCompletion;

ChatCompletion chatCompletion = client.chat().completions().create(params).validate();

Or configure the method call to validate the response using the responseValidation method:

import com.openai.models.ChatModel;
import com.openai.models.chat.completions.ChatCompletion;
import com.openai.models.chat.completions.ChatCompletionCreateParams;

ChatCompletion chatCompletion = client.chat().completions().create(
  params, RequestOptions.builder().responseValidation(true).build()
);

Or configure the default for all method calls at the client level:

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .fromEnv()
    .responseValidation(true)
    .build();

FAQ

Why don't you use plain `enum` classes?

Java enum classes are not trivially forwards compatible. Using them in the SDK could cause runtime exceptions if the API is updated to respond with a new enum value.

Why do you represent fields using `JsonField<T>` instead of just plain `T`?

Using JsonField<T> enables a few features:

Allowing usage of undocumented API functionality
Lazily validating the API response against the expected shape
Representing absent vs explicitly null values

Why don't you use `data` classes?

It is not backwards compatible to add new fields to a data class and we don't want to introduce a breaking change every time we add a field to a class.

Why don't you use checked exceptions?

Checked exceptions are widely considered a mistake in the Java programming language. In fact, they were omitted from Kotlin for this reason.

Checked exceptions:

Are verbose to handle
Encourage error handling at the wrong level of abstraction, where nothing can be done about the error
Are tedious to propagate due to the function coloring problem
Don't play well with lambdas (also due to the function coloring problem)

Semantic versioning

This package generally follows SemVer conventions, though certain backwards-incompatible changes may be released as minor versions:

Changes to library internals which are technically public but not intended or documented for external use. (Please open a GitHub issue to let us know if you are relying on such internals.)
Changes that we do not expect to impact the vast majority of users in practice.

We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.

We are keen for your feedback; please open an issue with questions, bugs, or suggestions.

License

damo/openai-java

Folders and files

Latest commit

History

Repository files navigation