Ingest Document

Go to Product

Ingests the document into the engine's knowledge base under a stable documentId (default: content hash). Returns a ZIP containing the original PDF when includeOriginal is true and any selected markdown or chunks JSONL exports. Pipelines unpack the ZIP for the next step. The X-Stirling-Tool-Report header contains the ingest summary JSON. Input:PDF Output:PDF Type:SIMO

Options

File Input
Document ID
Stable identifier for the ingested document; re-ingesting the same id replaces its chunks. Defaults to a content hash of the uploaded bytes.
Include Original
Include the input PDF alongside the requested corpus files
Chunk Size
Target chunk size in characters (64-32768)
Overlap
Overlap between adjacent chunks in characters (0-4096)
Index
Index the document into the built-in knowledge base
Export Markdown
Also return the parsed document as a markdown file, for delivery to external systems (vector DBs, training corpora)
Export Chunks as JSONL
Also return the chunks as a JSONL file (one chunk per line with page span and heading breadcrumb), ready for external embedding or indexing
Result Format

Specify how the response should be mapped to the table output. The following formats are available:

Raw Response: Returns the raw response in a single row with the following columns:

  • body: Response body
  • status: HTTP status code

Input Ports

Icon
Configuration data.

Output Ports

Icon
Result of the request depending on the selected Result Format.
Icon
Configuration data (this is the same as the input port; it is provided as passthrough for sequentially chaining nodes to declutter your workflow connections).

Popular Predecessors

  • No recommendations found

Popular Successors

  • No recommendations found

Views

This node has no views

Workflows

  • No workflows found

Links

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.