diff --git a/specification/inference/_types/CommonTypes.ts b/specification/inference/_types/CommonTypes.ts index 3d99554483..ffa5392999 100644 --- a/specification/inference/_types/CommonTypes.ts +++ b/specification/inference/_types/CommonTypes.ts @@ -1711,6 +1711,15 @@ export class JinaAITaskSettings { * * `search`: Use it for storing embeddings of search queries run against a vector database to find relevant documents. */ task?: JinaAITextEmbeddingTask + /** + * For a `text_embedding` task, controls when text is split into chunks. + * When set to `true`, a request from Elasticsearch contains only chunks related to a single document. Instead of batching chunks across documents, Elasticsearch sends them in separate requests. This ensures that chunk embeddings retain context from the entire document, improving semantic quality. + * + * If a document exceeds the model's context limits, late chunking is automatically disabled for that document only and standard chunking is used instead. + * + * If not specified, defaults to `false`. + */ + late_chunking?: boolean /** * For a `rerank` task, the number of most relevant documents to return. * It defaults to the number of the documents.