Package com.oracle.bmc.generativeaiinference

Class GenerativeAiInferenceAsyncClient

java.lang.Object

com.oracle.bmc.http.internal.BaseAsyncClient

com.oracle.bmc.generativeaiinference.GenerativeAiInferenceAsyncClient

All Implemented Interfaces:

GenerativeAiInferenceAsync, AutoCloseable

@Generated(value="OracleSDKGenerator",
           comments="API Version: 20231130")
public class GenerativeAiInferenceAsyncClient
extends BaseAsyncClient
implements GenerativeAiInferenceAsync

Async client implementation for GenerativeAiInference service.
There are two ways to use async client: 1. Use AsyncHandler: using AsyncHandler, if the response to the call is an InputStream, like getObject Api in object storage service, developers need to process the stream in AsyncHandler, and not anywhere else, because the stream will be closed right after the AsyncHandler is invoked.
2. Use Java Future: using Java Future, developers need to close the stream after they are done with the Java Future.
Accessing the result should be done in a mutually exclusive manner, either through the Future or the AsyncHandler, but not both. If the Future is used, the caller should pass in null as the AsyncHandler. If the AsyncHandler is used, it is still safe to use the Future to determine whether or not the request was completed via Future.isDone/isCancelled.
Please refer to https://github.com/oracle/oci-java-sdk/blob/master/bmc-examples/src/main/java/ResteasyClientWithObjectStorageExample.java

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	GenerativeAiInferenceAsyncClient.Builder	Builder class for this client.

Field Summary

Fields

Modifier and Type	Field	Description
String	clientCommonLibraryVersion	Compatible SDK version, provided by the codegen.
Optional<String>	minimumClientCommonLibraryVersionFromClient	Minimum compatible SDK version, maybe provided by the codegen.
static Service	SERVICE	Service instance for GenerativeAiInference.

Constructor Summary

Constructors

Constructor	Description
GenerativeAiInferenceAsyncClient(AbstractAuthenticationDetailsProvider authenticationDetailsProvider, ClientConfiguration configuration, ClientConfigurator clientConfigurator, RequestSignerFactory defaultRequestSignerFactory)	Deprecated. Use the builder instead.
GenerativeAiInferenceAsyncClient(AbstractAuthenticationDetailsProvider authenticationDetailsProvider, ClientConfiguration configuration, ClientConfigurator clientConfigurator, RequestSignerFactory defaultRequestSignerFactory, List<ClientConfigurator> additionalClientConfigurators)	Deprecated. Use the builder instead.
GenerativeAiInferenceAsyncClient(AbstractAuthenticationDetailsProvider authenticationDetailsProvider, ClientConfiguration configuration, ClientConfigurator clientConfigurator, RequestSignerFactory defaultRequestSignerFactory, List<ClientConfigurator> additionalClientConfigurators, String endpoint)	Deprecated. Use the builder instead.
GenerativeAiInferenceAsyncClient(AbstractAuthenticationDetailsProvider authenticationDetailsProvider, ClientConfiguration configuration, ClientConfigurator clientConfigurator, RequestSignerFactory defaultRequestSignerFactory, Map<SigningStrategy,RequestSignerFactory> signingStrategyRequestSignerFactories, List<ClientConfigurator> additionalClientConfigurators, String endpoint)	Deprecated. Use the builder instead.
GenerativeAiInferenceAsyncClient(BasicAuthenticationDetailsProvider authenticationDetailsProvider)	Deprecated. Use the builder instead.
GenerativeAiInferenceAsyncClient(BasicAuthenticationDetailsProvider authenticationDetailsProvider, ClientConfiguration configuration)	Deprecated. Use the builder instead.
GenerativeAiInferenceAsyncClient(BasicAuthenticationDetailsProvider authenticationDetailsProvider, ClientConfiguration configuration, ClientConfigurator clientConfigurator)	Deprecated. Use the builder instead.

Method Summary

Modifier and Type	Method	Description
Future<ApplyGuardrailsResponse>	applyGuardrails(ApplyGuardrailsRequest request, AsyncHandler<ApplyGuardrailsRequest,ApplyGuardrailsResponse> handler)	Applies guardrails to the input text, including content moderation, PII detection, and prompt injection protection.
static GenerativeAiInferenceAsyncClient.Builder	builder()	Create a builder for this client.
Future<ChatResponse>	chat(ChatRequest request, AsyncHandler<ChatRequest,ChatResponse> handler)	Creates a response for the given conversation.
protected <REQ extends BmcRequest<?>,RESP extends BmcResponse,RESP_BUILDER extends BmcResponse.Builder<RESP>> ClientCall<REQ,RESP,RESP_BUILDER>	clientCall(REQ request, Supplier<RESP_BUILDER> responseBuilder)
void	close()
Future<EmbedTextResponse>	embedText(EmbedTextRequest request, AsyncHandler<EmbedTextRequest,EmbedTextResponse> handler)	Produces embeddings for the inputs.
Future<GenerateTextResponse>	generateText(GenerateTextRequest request, AsyncHandler<GenerateTextRequest,GenerateTextResponse> handler)	Generates a text response based on the user prompt.
String	getClientCommonLibraryVersion()
protected ClientConfigurator	getDefaultConfigurator()
String	getEndpoint()
Optional<String>	getMinimumClientCommonLibraryVersionFromClient()
void	populateServiceParametersInEndpoint(String endpoint, Map<String,Object> requiredParametersMap)	Populate the parameters in the endpoint with its corresponding value and update the base endpoint.
void	refreshClient()	Rebuild the backing HttpClient.
Future<RerankTextResponse>	rerankText(RerankTextRequest request, AsyncHandler<RerankTextRequest,RerankTextResponse> handler)	Reranks the text responses based on the input documents and a prompt.
void	setEndpoint(String endpoint)
void	setRegion(Region region)	Sets the region to call (ex, Region.US_PHOENIX_1).
void	setRegion(String regionId)	Sets the region to call (ex, ‘us-phoenix-1’).
Future<SummarizeTextResponse>	summarizeText(SummarizeTextRequest request, AsyncHandler<SummarizeTextRequest,SummarizeTextResponse> handler)	Summarizes the input text.
void	updateBaseEndpoint(String endpoint)	This method should be used for parameterized endpoint templates only.
void	useRealmSpecificEndpointTemplate(boolean useOfRealmSpecificEndpointTemplateEnabled)	This method should be used to enable or disable the use of realm-specific endpoint template.

Methods inherited from class java.lang.Object

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

Methods inherited from interface java.lang.AutoCloseable

close

Methods inherited from interface com.oracle.bmc.generativeaiinference.GenerativeAiInferenceAsync

getEndpoint, refreshClient, setEndpoint, useRealmSpecificEndpointTemplate

Field Detail

SERVICE

public static final Service SERVICE

Service instance for GenerativeAiInference.

clientCommonLibraryVersion

public final String clientCommonLibraryVersion

Compatible SDK version, provided by the codegen.

minimumClientCommonLibraryVersionFromClient

public final Optional<String> minimumClientCommonLibraryVersionFromClient

Minimum compatible SDK version, maybe provided by the codegen.

Constructor Detail

GenerativeAiInferenceAsyncClient

@Deprecated
public GenerativeAiInferenceAsyncClient(BasicAuthenticationDetailsProvider authenticationDetailsProvider)

Deprecated.

Use the builder instead.

Create a new client instance.

Parameters:

authenticationDetailsProvider - The authentication details (see GenerativeAiInferenceAsyncClient.Builder.build(com.oracle.bmc.auth.AbstractAuthenticationDetailsProvider))

GenerativeAiInferenceAsyncClient

@Deprecated
public GenerativeAiInferenceAsyncClient(BasicAuthenticationDetailsProvider authenticationDetailsProvider,
                                        ClientConfiguration configuration)

Deprecated.

Use the builder instead.

Create a new client instance.

Parameters:

authenticationDetailsProvider - The authentication details (see GenerativeAiInferenceAsyncClient.Builder.build(com.oracle.bmc.auth.AbstractAuthenticationDetailsProvider))

configuration - ClientBuilderBase.configuration

GenerativeAiInferenceAsyncClient

@Deprecated
public GenerativeAiInferenceAsyncClient(BasicAuthenticationDetailsProvider authenticationDetailsProvider,
                                        ClientConfiguration configuration,
                                        ClientConfigurator clientConfigurator)

Deprecated.

Use the builder instead.

Create a new client instance.

Parameters:

authenticationDetailsProvider - The authentication details (see GenerativeAiInferenceAsyncClient.Builder.build(com.oracle.bmc.auth.AbstractAuthenticationDetailsProvider))

configuration - ClientBuilderBase.configuration

clientConfigurator - ClientBuilderBase.clientConfigurator(com.oracle.bmc.http.ClientConfigurator)

GenerativeAiInferenceAsyncClient

@Deprecated
public GenerativeAiInferenceAsyncClient(AbstractAuthenticationDetailsProvider authenticationDetailsProvider,
                                        ClientConfiguration configuration,
                                        ClientConfigurator clientConfigurator,
                                        RequestSignerFactory defaultRequestSignerFactory)

Deprecated.

Use the builder instead.

Create a new client instance.

Parameters:

authenticationDetailsProvider - The authentication details (see GenerativeAiInferenceAsyncClient.Builder.build(com.oracle.bmc.auth.AbstractAuthenticationDetailsProvider))

configuration - ClientBuilderBase.configuration

clientConfigurator - ClientBuilderBase.clientConfigurator(com.oracle.bmc.http.ClientConfigurator)

defaultRequestSignerFactory - ClientBuilderBase.requestSignerFactory

GenerativeAiInferenceAsyncClient

@Deprecated
public GenerativeAiInferenceAsyncClient(AbstractAuthenticationDetailsProvider authenticationDetailsProvider,
                                        ClientConfiguration configuration,
                                        ClientConfigurator clientConfigurator,
                                        RequestSignerFactory defaultRequestSignerFactory,
                                        List<ClientConfigurator> additionalClientConfigurators)

Deprecated.

Use the builder instead.

Create a new client instance.

Parameters:

authenticationDetailsProvider - The authentication details (see GenerativeAiInferenceAsyncClient.Builder.build(com.oracle.bmc.auth.AbstractAuthenticationDetailsProvider))

configuration - ClientBuilderBase.configuration

clientConfigurator - ClientBuilderBase.clientConfigurator(com.oracle.bmc.http.ClientConfigurator)

defaultRequestSignerFactory - ClientBuilderBase.requestSignerFactory

additionalClientConfigurators - ClientBuilderBase.additionalClientConfigurators

GenerativeAiInferenceAsyncClient

@Deprecated
public GenerativeAiInferenceAsyncClient(AbstractAuthenticationDetailsProvider authenticationDetailsProvider,
                                        ClientConfiguration configuration,
                                        ClientConfigurator clientConfigurator,
                                        RequestSignerFactory defaultRequestSignerFactory,
                                        List<ClientConfigurator> additionalClientConfigurators,
                                        String endpoint)

Deprecated.

Use the builder instead.

Create a new client instance.

Parameters:

authenticationDetailsProvider - The authentication details (see GenerativeAiInferenceAsyncClient.Builder.build(com.oracle.bmc.auth.AbstractAuthenticationDetailsProvider))

configuration - ClientBuilderBase.configuration

clientConfigurator - ClientBuilderBase.clientConfigurator(com.oracle.bmc.http.ClientConfigurator)

defaultRequestSignerFactory - ClientBuilderBase.requestSignerFactory

additionalClientConfigurators - ClientBuilderBase.additionalClientConfigurators

endpoint - ClientBuilderBase.endpoint(java.lang.String)

GenerativeAiInferenceAsyncClient

@Deprecated
public GenerativeAiInferenceAsyncClient(AbstractAuthenticationDetailsProvider authenticationDetailsProvider,
                                        ClientConfiguration configuration,
                                        ClientConfigurator clientConfigurator,
                                        RequestSignerFactory defaultRequestSignerFactory,
                                        Map<SigningStrategy,RequestSignerFactory> signingStrategyRequestSignerFactories,
                                        List<ClientConfigurator> additionalClientConfigurators,
                                        String endpoint)

Deprecated.

Use the builder instead.

Create a new client instance.

Parameters:

authenticationDetailsProvider - The authentication details (see GenerativeAiInferenceAsyncClient.Builder.build(com.oracle.bmc.auth.AbstractAuthenticationDetailsProvider))

configuration - ClientBuilderBase.configuration

clientConfigurator - ClientBuilderBase.clientConfigurator(com.oracle.bmc.http.ClientConfigurator)

defaultRequestSignerFactory - ClientBuilderBase.requestSignerFactory

additionalClientConfigurators - ClientBuilderBase.additionalClientConfigurators

endpoint - ClientBuilderBase.endpoint(java.lang.String)

signingStrategyRequestSignerFactories - ClientBuilderBase.signingStrategyRequestSignerFactories

Method Detail

builder

public static GenerativeAiInferenceAsyncClient.Builder builder()

Create a builder for this client.

Returns:

builder

setRegion

public void setRegion(Region region)

Description copied from interface: GenerativeAiInferenceAsync

Sets the region to call (ex, Region.US_PHOENIX_1).

Note, this will call setEndpoint after resolving the endpoint. If the service is not available in this region, however, an IllegalArgumentException will be raised.

Specified by:

setRegion in interface GenerativeAiInferenceAsync

Parameters:

region - The region of the service.

setRegion

public void setRegion(String regionId)

Description copied from interface: GenerativeAiInferenceAsync

Sets the region to call (ex, ‘us-phoenix-1’).

Note, this will first try to map the region ID to a known Region and call setRegion.

If no known Region could be determined, it will create an endpoint based on the default endpoint format (Region.formatDefaultRegionEndpoint(Service, String) and then call setEndpoint.

Specified by:

setRegion in interface GenerativeAiInferenceAsync

Parameters:

regionId - The public region ID.

applyGuardrails

public Future<ApplyGuardrailsResponse> applyGuardrails(ApplyGuardrailsRequest request,
                                                       AsyncHandler<ApplyGuardrailsRequest,ApplyGuardrailsResponse> handler)

Description copied from interface: GenerativeAiInferenceAsync

Applies guardrails to the input text, including content moderation, PII detection, and prompt injection protection.

Specified by:

applyGuardrails in interface GenerativeAiInferenceAsync

Parameters:

request - The request object containing the details to send

handler - The request handler to invoke upon completion, may be null.

Returns:

A Future that can be used to get the response if no AsyncHandler was provided. Note, if you provide an AsyncHandler and use the Future, some types of responses (like java.io.InputStream) may not be able to be read in both places as the underlying stream may only be consumed once.

chat

public Future<ChatResponse> chat(ChatRequest request,
                                 AsyncHandler<ChatRequest,ChatResponse> handler)

Description copied from interface: GenerativeAiInferenceAsync

Creates a response for the given conversation.

Specified by:

chat in interface GenerativeAiInferenceAsync

Parameters:

request - The request object containing the details to send

handler - The request handler to invoke upon completion, may be null.

Returns:

A Future that can be used to get the response if no AsyncHandler was provided. Note, if you provide an AsyncHandler and use the Future, some types of responses (like java.io.InputStream) may not be able to be read in both places as the underlying stream may only be consumed once.

embedText

public Future<EmbedTextResponse> embedText(EmbedTextRequest request,
                                           AsyncHandler<EmbedTextRequest,EmbedTextResponse> handler)

Description copied from interface: GenerativeAiInferenceAsync

Produces embeddings for the inputs.

An embedding is numeric representation of a piece of text. This text can be a phrase, a sentence, or one or more paragraphs. The Generative AI embedding model transforms each phrase, sentence, or paragraph that you input, into an array with 1024 numbers. You can use these embeddings for finding similarity in your input text such as finding phrases that are similar in context or category. Embeddings are mostly used for semantic searches where the search function focuses on the meaning of the text that it's searching through rather than finding results based on keywords.

Specified by:

embedText in interface GenerativeAiInferenceAsync

Parameters:

request - The request object containing the details to send

handler - The request handler to invoke upon completion, may be null.

Returns:

A Future that can be used to get the response if no AsyncHandler was provided. Note, if you provide an AsyncHandler and use the Future, some types of responses (like java.io.InputStream) may not be able to be read in both places as the underlying stream may only be consumed once.

generateText

public Future<GenerateTextResponse> generateText(GenerateTextRequest request,
                                                 AsyncHandler<GenerateTextRequest,GenerateTextResponse> handler)

Description copied from interface: GenerativeAiInferenceAsync

Generates a text response based on the user prompt.

Specified by:

generateText in interface GenerativeAiInferenceAsync

Parameters:

request - The request object containing the details to send

handler - The request handler to invoke upon completion, may be null.

Returns:

A Future that can be used to get the response if no AsyncHandler was provided. Note, if you provide an AsyncHandler and use the Future, some types of responses (like java.io.InputStream) may not be able to be read in both places as the underlying stream may only be consumed once.

rerankText

public Future<RerankTextResponse> rerankText(RerankTextRequest request,
                                             AsyncHandler<RerankTextRequest,RerankTextResponse> handler)

Description copied from interface: GenerativeAiInferenceAsync

Reranks the text responses based on the input documents and a prompt.

Rerank assigns an index and a relevance score to each document, indicating which document is most related to the prompt.

Specified by:

rerankText in interface GenerativeAiInferenceAsync

Parameters:

request - The request object containing the details to send

handler - The request handler to invoke upon completion, may be null.

Returns:

A Future that can be used to get the response if no AsyncHandler was provided. Note, if you provide an AsyncHandler and use the Future, some types of responses (like java.io.InputStream) may not be able to be read in both places as the underlying stream may only be consumed once.

summarizeText

public Future<SummarizeTextResponse> summarizeText(SummarizeTextRequest request,
                                                   AsyncHandler<SummarizeTextRequest,SummarizeTextResponse> handler)

Description copied from interface: GenerativeAiInferenceAsync

Summarizes the input text.

Specified by:

summarizeText in interface GenerativeAiInferenceAsync

Parameters:

request - The request object containing the details to send

handler - The request handler to invoke upon completion, may be null.

Returns:

A Future that can be used to get the response if no AsyncHandler was provided. Note, if you provide an AsyncHandler and use the Future, some types of responses (like java.io.InputStream) may not be able to be read in both places as the underlying stream may only be consumed once.

getDefaultConfigurator

protected ClientConfigurator getDefaultConfigurator()

useRealmSpecificEndpointTemplate

public void useRealmSpecificEndpointTemplate(boolean useOfRealmSpecificEndpointTemplateEnabled)

This method should be used to enable or disable the use of realm-specific endpoint template.

The default value is null. To enable the use of endpoint template defined for the realm in use, set the flag to true To disable the use of endpoint template defined for the realm in use, set the flag to false

Parameters:

useOfRealmSpecificEndpointTemplateEnabled - This flag can be set to true or false to enable or disable the use of realm-specific endpoint template respectively

populateServiceParametersInEndpoint

public final void populateServiceParametersInEndpoint(String endpoint,
                                                      Map<String,Object> requiredParametersMap)

Populate the parameters in the endpoint with its corresponding value and update the base endpoint.

The value will be populated iff the parameter in endpoint is a required request path parameter or a required request query parameter. If not, the parameter in the endpoint will be ignored and left blank.

Parameters:

endpoint - The endpoint template in use

requiredParametersMap - Map of parameter name as key and value set in request path or query parameter as value

updateBaseEndpoint

public final void updateBaseEndpoint(String endpoint)

This method should be used for parameterized endpoint templates only.

This does not include {region} and {secondLevelDomain} parameters.

Parameters:

endpoint - The updated endpoint to use

setEndpoint

public final void setEndpoint(String endpoint)

getEndpoint

public final String getEndpoint()

refreshClient

public final void refreshClient()

Rebuild the backing HttpClient.

This will call ClientConfigurators again, and can be used to e.g. refresh the SSL certificate.

close

public final void close()

Specified by:

close in interface AutoCloseable

getClientCommonLibraryVersion

public String getClientCommonLibraryVersion()

getMinimumClientCommonLibraryVersionFromClient

public Optional<String> getMinimumClientCommonLibraryVersionFromClient()

clientCall

protected <REQ extends BmcRequest<?>,RESP extends BmcResponse,RESP_BUILDER extends BmcResponse.Builder<RESP>> ClientCall<REQ,RESP,RESP_BUILDER> clientCall(REQ request,
                                                                                                                                                                                   Supplier<RESP_BUILDER> responseBuilder)