Package com.sap.ai.sdk.foundationmodels.openai

Class OpenAiClient

java.lang.Object

com.sap.ai.sdk.foundationmodels.openai.OpenAiClient

public final class OpenAiClient
extends Object

Client for interacting with OpenAI models.

Method Summary

Modifier and Type	Method	Description
CreateChatCompletionResponse	chatCompletion(CreateChatCompletionRequest request)	Generate a completion for the given low-level request object.
OpenAiChatCompletionOutput	chatCompletion(OpenAiChatCompletionParameters parameters)	Deprecated. Use chatCompletion(OpenAiChatCompletionRequest) instead.
OpenAiChatCompletionResponse	chatCompletion(OpenAiChatCompletionRequest request)	Generate a completion for the given conversation and request parameters.
OpenAiChatCompletionOutput	chatCompletion(String prompt)	Deprecated. Use chatCompletion(OpenAiChatCompletionRequest) instead.
EmbeddingsCreate200Response	embedding(EmbeddingsCreateRequest request)	Get a vector representation of a given inputs using low-level request.
OpenAiEmbeddingOutput	embedding(OpenAiEmbeddingParameters parameters)	Deprecated.
OpenAiEmbeddingResponse	embedding(OpenAiEmbeddingRequest request)	Get a vector representation of a given request that can be easily consumed by machine learning models and algorithms using high-level request object.
static OpenAiClient	forModel(OpenAiModel foundationModel)	Create a new OpenAI client for the given foundation model, using the default resource group.
Stream<String>	streamChatCompletion(String prompt)	Stream a completion for the given string prompt as user.
Stream<OpenAiChatCompletionDelta>	streamChatCompletionDeltas(CreateChatCompletionRequest request)	Stream a completion for the given low-level request object.
Stream<OpenAiChatCompletionDelta>	streamChatCompletionDeltas(OpenAiChatCompletionParameters parameters)	Deprecated. Use streamChatCompletionDeltas(OpenAiChatCompletionRequest) instead.
Stream<OpenAiChatCompletionDelta>	streamChatCompletionDeltas(OpenAiChatCompletionRequest request)	Stream a completion for the given conversation and request parameters.
OpenAiClient	withApiVersion(String apiVersion)	Create a new OpenAI client targeting the specified API version.
static OpenAiClient	withCustomDestination(com.sap.cloud.sdk.cloudplatform.connectivity.Destination destination)	Create a new OpenAI client with a custom destination, allowing for a custom resource group or otherwise custom destination.
OpenAiClient	withHeader(String key, String value)	Create a new OpenAI client with a custom header added to every call made with this client
OpenAiClient	withSystemPrompt(String systemPrompt)	Add a system prompt before user prompts.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Details

forModel

@Nonnull
public static OpenAiClient forModel(@Nonnull
 OpenAiModel foundationModel)
                             throws DeploymentResolutionException

Create a new OpenAI client for the given foundation model, using the default resource group.

Parameters:

foundationModel - the OpenAI model which is deployed.

Returns:

a new OpenAI client.

Throws:

DeploymentResolutionException - if no deployment for the given model was found in the default resource group.

withApiVersion

@Beta
@Nonnull
public OpenAiClient withApiVersion(@Nonnull
 String apiVersion)

Create a new OpenAI client targeting the specified API version.

Parameters:

apiVersion - the API version to target.

Returns:

a new client.

withCustomDestination

@Nonnull
public static OpenAiClient withCustomDestination(@Nonnull
 com.sap.cloud.sdk.cloudplatform.connectivity.Destination destination)

Create a new OpenAI client with a custom destination, allowing for a custom resource group or otherwise custom destination. The destination needs to be configured with a URL pointing to an OpenAI model deployment. Typically, such a destination should be obtained using AiCoreService.getInferenceDestination(String).

Example:

 var destination = new AiCoreService().getInferenceDestination("custom-rg").forModel(GPT_4O);
 OpenAiClient.withCustomDestination(destination);
 

Parameters:

destination - The specific HttpDestination to use.

Returns:

a new OpenAI client.

See Also:

• AiCoreService.getInferenceDestination(String)

withSystemPrompt

@Nonnull
public OpenAiClient withSystemPrompt(@Nonnull
 String systemPrompt)

Add a system prompt before user prompts.

Note: The system prompt is ignored on chat completions invoked with OpenAiChatCompletionPrompt.

Parameters:

systemPrompt - the system prompt

Returns:

the client

withHeader

@Nonnull
public OpenAiClient withHeader(@Nonnull
 String key,
 @Nonnull
 String value)

Create a new OpenAI client with a custom header added to every call made with this client

Parameters:

key - the key of the custom header to add

value - the value of the custom header to add

Returns:

a new client.

Since:

1.11.0

chatCompletion

@Nonnull
@Deprecated
public OpenAiChatCompletionOutput chatCompletion(@Nonnull
 String prompt)
                                          throws OpenAiClientException

Deprecated.

Use chatCompletion(OpenAiChatCompletionRequest) instead.

Generate a completion for the given string prompt as user.

Parameters:

prompt - a text message.

Returns:

the completion output

Throws:

OpenAiClientException - if the request fails

chatCompletion

@Nonnull
public OpenAiChatCompletionResponse chatCompletion(@Nonnull
 OpenAiChatCompletionRequest request)
                                            throws OpenAiClientException

Generate a completion for the given conversation and request parameters.

Parameters:

request - the completion request.

Returns:

the completion output

Throws:

OpenAiClientException - if the request fails

Since:

1.4.0

chatCompletion

@Nonnull
public CreateChatCompletionResponse chatCompletion(@Nonnull
 CreateChatCompletionRequest request)
                                            throws OpenAiClientException

Generate a completion for the given low-level request object.

Parameters:

request - the completion request.

Returns:

the completion output

Throws:

OpenAiClientException - if the request fails

Since:

1.4.0

chatCompletion

@Nonnull
@Deprecated
public OpenAiChatCompletionOutput chatCompletion(@Nonnull
 OpenAiChatCompletionParameters parameters)
                                          throws OpenAiClientException

Deprecated.

Use chatCompletion(OpenAiChatCompletionRequest) instead.

Generate a completion for the given conversation and request parameters.

Parameters:

parameters - the completion request.

Returns:

the completion output

Throws:

OpenAiClientException - if the request fails

streamChatCompletion

@Nonnull
public Stream<String> streamChatCompletion(@Nonnull
 String prompt)
                                    throws OpenAiClientException

Stream a completion for the given string prompt as user.

Returns a lazily populated stream of text chunks. To access more details about the individual chunks, use streamChatCompletionDeltas(OpenAiChatCompletionRequest).

The stream should be consumed using a try-with-resources block to ensure that the underlying HTTP connection is closed.

Example:

 try (var stream = client.streamChatCompletion("...")) {
       stream.forEach(System.out::println);
 }
 

Please keep in mind that using a terminal stream operation like Stream.forEach(java.util.function.Consumer<? super T>) will block until all chunks are consumed. Also, for obvious reasons, invoking BaseStream.parallel() on this stream is not supported.

Parameters:

prompt - a text message.

Returns:

A stream of text chunks

Throws:

OpenAiClientException - if the request fails or if the finish reason is content_filter

See Also:

• streamChatCompletionDeltas(OpenAiChatCompletionRequest)

streamChatCompletionDeltas

@Nonnull
public Stream<OpenAiChatCompletionDelta> streamChatCompletionDeltas(@Nonnull
 OpenAiChatCompletionRequest request)
                                                             throws OpenAiClientException

Stream a completion for the given conversation and request parameters.

Returns a lazily populated stream of delta objects. To simply stream the text chunks use streamChatCompletion(String)

The stream should be consumed using a try-with-resources block to ensure that the underlying HTTP connection is closed.

Example:

 try (var stream = client.streamChatCompletionDeltas(prompt)) {
       stream
           .peek(delta -> System.out.println(delta.getUsage()))
           .map(OpenAiChatCompletionDelta::getDeltaContent)
           .forEach(System.out::println);
 }
 

Please keep in mind that using a terminal stream operation like Stream.forEach(java.util.function.Consumer<? super T>) will block until all chunks are consumed. Also, for obvious reasons, invoking BaseStream.parallel() on this stream is not supported.

Parameters:

request - The prompt, including a list of messages.

Returns:

A stream of message deltas

Throws:

OpenAiClientException - if the request fails or if the finish reason is content_filter

Since:

1.4.0

See Also:

• streamChatCompletion(String)

streamChatCompletionDeltas

@Nonnull
public Stream<OpenAiChatCompletionDelta> streamChatCompletionDeltas(@Nonnull
 CreateChatCompletionRequest request)
                                                             throws OpenAiClientException

Stream a completion for the given low-level request object. Returns a lazily populated stream of delta objects.

Parameters:

request - The completion request.

Returns:

A stream of message deltas

Throws:

OpenAiClientException - if the request fails or if the finish reason is content_filter

Since:

1.4.0

See Also:

• for a higher-level API

streamChatCompletionDeltas

@Nonnull
@Deprecated
public Stream<OpenAiChatCompletionDelta> streamChatCompletionDeltas(@Nonnull
 OpenAiChatCompletionParameters parameters)
                                                             throws OpenAiClientException

Deprecated.

Use streamChatCompletionDeltas(OpenAiChatCompletionRequest) instead.

Stream a completion for the given conversation and request parameters.

Returns a lazily populated stream of delta objects. To simply stream the text chunks use streamChatCompletion(String)

The stream should be consumed using a try-with-resources block to ensure that the underlying HTTP connection is closed.

Example:

 try (var stream = client.streamChatCompletionDeltas(request)) {
       stream
           .peek(delta -> System.out.println(delta.getUsage()))
           .map(com.sap.ai.sdk.foundationmodels.openai.model.OpenAiChatCompletionDelta::getDeltaContent)
           .forEach(System.out::println);
 }
 

Please keep in mind that using a terminal stream operation like Stream.forEach(java.util.function.Consumer<? super T>) will block until all chunks are consumed. Also, for obvious reasons, invoking BaseStream.parallel() on this stream is not supported.

Parameters:

parameters - The prompt, including a list of messages.

Returns:

A stream of message deltas

Throws:

OpenAiClientException - if the request fails or if the finish reason is content_filter

embedding

@Nonnull
public OpenAiEmbeddingResponse embedding(@Nonnull
 OpenAiEmbeddingRequest request)
                                  throws OpenAiClientException

Get a vector representation of a given request that can be easily consumed by machine learning models and algorithms using high-level request object.

Parameters:

request - the request with input text.

Returns:

the embedding response convenience object

Throws:

OpenAiClientException - if the request fails

Since:

1.4.0

See Also:

• for full confgurability.

embedding

@Nonnull
public EmbeddingsCreate200Response embedding(@Nonnull
 EmbeddingsCreateRequest request)
                                      throws OpenAiClientException

Get a vector representation of a given inputs using low-level request.

Parameters:

request - the request with input text.

Returns:

the embedding output

Throws:

OpenAiClientException - if the request fails

Since:

1.4.0

See Also:

• for conveninece api

embedding

@Nonnull
@Deprecated
public OpenAiEmbeddingOutput embedding(@Nonnull
 OpenAiEmbeddingParameters parameters)
                                throws OpenAiClientException

Deprecated.

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.

Parameters:

parameters - the input text.

Returns:

the embedding output

Throws:

OpenAiClientException - if the request fails