ingest_document
Load, segment, and index documents for search by processing txt, md, pdf, epub, and html files. Automatically detects chapters and sections to prepare content for efficient retrieval.
Instructions
Load, segment, and index a document for search.
Supports txt, md, pdf, epub, and html formats. Automatically detects chapters and sections.
Args: path: Absolute path to the document file. title: Optional title for the document (defaults to filename). chunk_size: Target size in words for each chunk (default: 2000). overlap: Number of words to overlap between chunks (default: 100). force: Force re-indexing even if document already exists.
Returns: Ingestion result with document ID and structure.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| title | No | ||
| chunk_size | No | ||
| overlap | No | ||
| force | No |