Whatever message this page gives is out now! Go check it out!
DocumentService
Last update:
May 18, 2026
Creates and returns a DocumentProcessingService instance providing granular, standalone document operations: loading, splitting, transforming, and ingesting documents.
Syntax
DocumentService()Parameters
DocumentService() takes no arguments. All configuration is passed per-operation on the returned object.Returns
Returns a DocumentProcessingService object. See the DocumentProcessingService method reference topics for the full list of available methods:
load(), loadAsync(), lazyLoad(), split(), transform(), transformSegments(), ingest(), and registerCustomParser().Example: Standalone pipeline
docService = DocumentService();
documents = docService.load({
path: "./company-docs/",
recursive: true,
pattern: "*.{pdf,docx,txt,md}"
});
segments = docService.split(documents, {
splitterType: "recursive",
chunkSize: 1000,
chunkOverlap: 100
});
vectorStore = VectorStore({ provider: "inmemory" });
result = docService.ingest(segments, vectorStore, { batchSize: 50 });
writeOutput("Ingested: #result.successfulSegments# / #result.totalSegments#");
We're glad. Tell us how this page helped.
We're sorry. Can you tell us what didn't work for you?
Share additional feedback to help us improve.
0/255
|
