Class ChatCompletionsHttpClient

java.lang.Object
com.google.adk.models.chat.ChatCompletionsHttpClient
public class ChatCompletionsHttpClient extends Object
An HTTP client for interacting with OpenAI-compatible chat completions endpoints.

Supports both non-streaming responses (single LlmResponse emission) and streaming Server-Sent Events (SSE) responses (multiple incremental LlmResponse emissions). See the OpenAI Chat Completions API reference for the wire protocol.

  • Constructor Details

    • ChatCompletionsHttpClient

      public ChatCompletionsHttpClient(com.google.genai.types.HttpOptions httpOptions)
      Constructs a new ChatCompletionsHttpClient that facilitates API interaction with the standard /chat/completions REST endpoint.

      All configuration is sourced from the supplied HttpOptions:

      • HttpOptions.baseUrl() -- required. The base URL of the chat completions endpoint. The chat/completions path segments are appended automatically using HttpUrl, which handles trailing slashes and percent-encoding deterministically. Set via HttpOptions.builder().baseUrl("https://...").build().
      • HttpOptions.headers() -- optional. Extra HTTP headers to include in outgoing requests. The Content-Type header is set automatically and cannot be overridden. Set via HttpOptions.builder().headers(Map.of("Authorization", "Bearer ...")) .
      • HttpOptions.timeout() -- optional. Per-call timeout in milliseconds. A missing timeout defaults to 5 minutes (DEFAULT_CALL_TIMEOUT). A timeout of 0 is respected as the explicit caller opt-in to infinite wait. Set via HttpOptions.builder().timeout(10_000).build().

      Example: 

      HttpOptions options =
    HttpOptions.builder()
        .baseUrl("https://example.com/v1/")
        .headers(ImmutableMap.of("Authorization", "Bearer my-token"))
        .timeout(30_000)
        .build();
ChatCompletionsHttpClient client = new ChatCompletionsHttpClient(options);
      Parameters:
      httpOptions - HTTP configuration. Must not be null, and HttpOptions.baseUrl() must be present and parseable as an HTTP(S) URL.
      Throws:
      IllegalArgumentException - if httpOptions.baseUrl() is missing or is not a valid HTTP(S) URL.

  • Method Details

    • complete

      public io.reactivex.rxjava3.core.Flowable<LlmResponse> complete(LlmRequest llmRequest, boolean stream)
      Generates a conversational response from the chat completions endpoint based on the provided messages. This encapsulates building the HTTP payload, sending the request to the completions endpoint, and initiating the handling of complete calls.
      Parameters:
      llmRequest - The request containing the model, configuration, and sequence of messages.
      stream - Whether to request a streaming response.
      Returns:
      A Flowable emitting the discrete (or combined) LlmResponse objects.