Interface OpenAiRestApi

@Path("") @Consumes("application/json") @Produces("application/json") @RegisterProvider(OpenAiRestApi.OpenAiRestApiJacksonReader.class) @RegisterProvider(OpenAiRestApi.OpenAiRestApiJacksonWriter.class) @RegisterProvider(OpenAiRestApi.OpenAiRestApiReaderInterceptor.class) @RegisterProvider(OpenAiRestApi.OpenAiRestApiWriterInterceptor.class) public interface OpenAiRestApi
This Microprofile REST client is used as the building block of all the API calls to OpenAI. The implementation is provided by the Reactive REST Client in Quarkus.

  • Nested Class Summary

    Nested Classes
    Modifier and Type
    Interface
    Description
    static class 
    OpenAiRestApi.ApiMetadata
     
    static class 
    OpenAiRestApi.DoneFilter
    Ensures that the terminal event sent by OpenAI is not processed (as it is not a valid json event)
    static class 
    OpenAiRestApi.ObjectMapperHolder
     
    static class 
    OpenAiRestApi.OpenAiClientLogger
    Introduce a custom logger as the stock one logs at the DEBUG level by default...
    static class 
    OpenAiRestApi.OpenAIRestAPIFilter
     
    static class 
    OpenAiRestApi.OpenAiRestApiJacksonReader
     
    static class 
    OpenAiRestApi.OpenAiRestApiJacksonWriter
     
    static class 
    OpenAiRestApi.OpenAiRestApiReaderInterceptor
    This method validates that the response is not empty, which happens when the API returns an error object
    static class 
    OpenAiRestApi.OpenAiRestApiWriterInterceptor
    The point of this is to properly set the stream value of the request so users don't have to remember to set it manually

  • Method Summary

    Modifier and Type
    Method
    Description
    dev.langchain4j.model.openai.internal.chat.ChatCompletionResponse
    blockingChatCompletion(dev.langchain4j.model.openai.internal.chat.ChatCompletionRequest request, OpenAiRestApi.ApiMetadata input)
    Perform a blocking request for a chat completion response
    dev.langchain4j.model.openai.internal.completion.CompletionResponse
    blockingCompletion(dev.langchain4j.model.openai.internal.completion.CompletionRequest request, OpenAiRestApi.ApiMetadata input)
    Perform a blocking request for a completion response
    dev.langchain4j.model.openai.internal.embedding.EmbeddingResponse
    blockingEmbedding(dev.langchain4j.model.openai.internal.embedding.EmbeddingRequest request, OpenAiRestApi.ApiMetadata input)
    Perform a blocking request to get the embeddings of an input text
    dev.langchain4j.model.openai.internal.image.GenerateImagesResponse
    blockingImagesGenerations(dev.langchain4j.model.openai.internal.image.GenerateImagesRequest request, OpenAiRestApi.ApiMetadata input)
     
    dev.langchain4j.model.openai.internal.moderation.ModerationResponse
    blockingModeration(dev.langchain4j.model.openai.internal.moderation.ModerationRequest request, OpenAiRestApi.ApiMetadata input)
    Perform a blocking request to get a moderated version of an input text
    io.smallrye.mutiny.Uni<dev.langchain4j.model.openai.internal.completion.CompletionResponse>
    completion(dev.langchain4j.model.openai.internal.completion.CompletionRequest request, OpenAiRestApi.ApiMetadata input)
    Perform a non-blocking request for a completion response
    io.smallrye.mutiny.Uni<dev.langchain4j.model.openai.internal.chat.ChatCompletionResponse>
    createChatCompletion(dev.langchain4j.model.openai.internal.chat.ChatCompletionRequest request, OpenAiRestApi.ApiMetadata input)
    Perform a non-blocking request for a chat completion response
    io.smallrye.mutiny.Uni<dev.langchain4j.model.openai.internal.embedding.EmbeddingResponse>
    embedding(dev.langchain4j.model.openai.internal.embedding.EmbeddingRequest request, OpenAiRestApi.ApiMetadata input)
    Perform a non-blocking request to get the embeddings of an input text
    io.smallrye.mutiny.Uni<dev.langchain4j.model.openai.internal.image.GenerateImagesResponse>
    imagesGenerations(dev.langchain4j.model.openai.internal.image.GenerateImagesRequest request, OpenAiRestApi.ApiMetadata input)
     
    io.smallrye.mutiny.Uni<dev.langchain4j.model.openai.internal.moderation.ModerationResponse>
    moderation(dev.langchain4j.model.openai.internal.moderation.ModerationRequest request, OpenAiRestApi.ApiMetadata input)
    Perform a non-blocking request to get a moderated version of an input text
    io.smallrye.mutiny.Multi<dev.langchain4j.model.openai.internal.chat.ChatCompletionResponse>
    streamingChatCompletion(dev.langchain4j.model.openai.internal.chat.ChatCompletionRequest request, OpenAiRestApi.ApiMetadata input)
    Performs a non-blocking request for a streaming chat completion request
    io.smallrye.mutiny.Multi<dev.langchain4j.model.openai.internal.completion.CompletionResponse>
    streamingCompletion(dev.langchain4j.model.openai.internal.completion.CompletionRequest request, OpenAiRestApi.ApiMetadata input)
    Performs a non-blocking request for a streaming completion request
    static RuntimeException
    toException(jakarta.ws.rs.core.Response response)
     

  • Method Details

    • completion

      @Path("completions") @POST io.smallrye.mutiny.Uni<dev.langchain4j.model.openai.internal.completion.CompletionResponse> completion(dev.langchain4j.model.openai.internal.completion.CompletionRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)
      Perform a non-blocking request for a completion response

    • blockingCompletion

      @Path("completions") @POST dev.langchain4j.model.openai.internal.completion.CompletionResponse blockingCompletion(dev.langchain4j.model.openai.internal.completion.CompletionRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)
      Perform a blocking request for a completion response

    • streamingCompletion

      @Path("chat/completions") @POST @RestStreamElementType("application/json") io.smallrye.mutiny.Multi<dev.langchain4j.model.openai.internal.completion.CompletionResponse> streamingCompletion(dev.langchain4j.model.openai.internal.completion.CompletionRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)
      Performs a non-blocking request for a streaming completion request

    • createChatCompletion

      @Path("chat/completions") @POST io.smallrye.mutiny.Uni<dev.langchain4j.model.openai.internal.chat.ChatCompletionResponse> createChatCompletion(dev.langchain4j.model.openai.internal.chat.ChatCompletionRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)
      Perform a non-blocking request for a chat completion response

    • blockingChatCompletion

      @Path("chat/completions") @POST dev.langchain4j.model.openai.internal.chat.ChatCompletionResponse blockingChatCompletion(dev.langchain4j.model.openai.internal.chat.ChatCompletionRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)
      Perform a blocking request for a chat completion response

    • streamingChatCompletion

      @Path("chat/completions") @POST @RestStreamElementType("application/json") io.smallrye.mutiny.Multi<dev.langchain4j.model.openai.internal.chat.ChatCompletionResponse> streamingChatCompletion(dev.langchain4j.model.openai.internal.chat.ChatCompletionRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)
      Performs a non-blocking request for a streaming chat completion request

    • embedding

      @Path("embeddings") @POST io.smallrye.mutiny.Uni<dev.langchain4j.model.openai.internal.embedding.EmbeddingResponse> embedding(dev.langchain4j.model.openai.internal.embedding.EmbeddingRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)
      Perform a non-blocking request to get the embeddings of an input text

    • blockingEmbedding

      @Path("embeddings") @POST dev.langchain4j.model.openai.internal.embedding.EmbeddingResponse blockingEmbedding(dev.langchain4j.model.openai.internal.embedding.EmbeddingRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)
      Perform a blocking request to get the embeddings of an input text

    • moderation

      @Path("moderations") @POST io.smallrye.mutiny.Uni<dev.langchain4j.model.openai.internal.moderation.ModerationResponse> moderation(dev.langchain4j.model.openai.internal.moderation.ModerationRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)
      Perform a non-blocking request to get a moderated version of an input text

    • blockingModeration

      @Path("moderations") @POST dev.langchain4j.model.openai.internal.moderation.ModerationResponse blockingModeration(dev.langchain4j.model.openai.internal.moderation.ModerationRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)
      Perform a blocking request to get a moderated version of an input text

    • blockingImagesGenerations

      @Path("images/generations") @POST dev.langchain4j.model.openai.internal.image.GenerateImagesResponse blockingImagesGenerations(dev.langchain4j.model.openai.internal.image.GenerateImagesRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)

    • imagesGenerations

      @Path("images/generations") @POST io.smallrye.mutiny.Uni<dev.langchain4j.model.openai.internal.image.GenerateImagesResponse> imagesGenerations(dev.langchain4j.model.openai.internal.image.GenerateImagesRequest request, @BeanParam OpenAiRestApi.ApiMetadata input)

    • toException

      static RuntimeException toException(jakarta.ws.rs.core.Response response)