Terminal streaming chat event carrying the aggregated ChatResponse, emitted last after all partial chunks. Reuse when handling final results from streaming chat models.
// Source: https://github.com/langchain4j/langchain4j | License: Apache-2.0 | Copyright You must retain, in the Source form of any Derivative Works
// Provided via justclaw.it.com; keep this notice with the code.
package dev.langchain4j.model.chat.response;
import static dev.langchain4j.internal.ValidationUtils.ensureNotNull;
import dev.langchain4j.Experimental;
import dev.langchain4j.internal.JacocoIgnoreCoverageGenerated;
import java.util.Objects;
/**
* The terminal {@link ChatModelStreamingEvent} of a streaming chat: the complete, aggregated {@link ChatResponse}.
* It is the streaming counterpart of {@link PartialResponse} (a single text chunk) — emitted once, last,
* after all partial events.
* <p>
* Wrapping {@link ChatResponse} (rather than having it implement {@link ChatMod
... (truncated -- full source via MCP)
See the full source, get the GitHub permalink, and search for more like it.
Get a free API key