Overview

A Document in R2R is the system’s digital representation of any piece of content you ingest, like a PDF report, webpage text, image, or audio file. It acts as the central container for downstream Chunks, Entities, and more.

Key processes associated with a Document include:

• Ingestion: Content is accepted from various formats (.pdf, .docx, .txt, .png, .mp3, etc.) via file upload, raw text, or pre-defined chunks.
• Chunking: The document’s content is broken down into smaller, searchable Chunks.
• Metadata & Collections: Documents are associated with descriptive metadata (e.g., title, source) and organized into Collections for access control.
• Enrichment (Optional): The system can extract Entities and Relationships for knowledge graphs or generate embeddings for semantic search.
• Status Tracking: Ingestion and enrichment processes are monitored.

Essentially, the Document object is R2R’s foundational unit for turning your raw information into searchable, analyzable knowledge for RAG and agentic workflows.

Core Document Endpoints

This section provides a high-level overview. See the detailed endpoint documentation below for request/response schemas and examples.

Method	Endpoint	Description
POST	/documents	Ingest new information (file, text, or chunks) as a document. (r2r-docs.sciphi.ai)
GET	/documents	List existing documents with pagination and filtering.
GET	/documents/{id}	Retrieve details (metadata, status) about a specific document.
GET	/documents/{id}/download	Download the original source file of a document.
GET	/documents/{id}/chunks	List the text Chunks derived from a document’s content.
PATCH	/documents/{id}/metadata	Add or update metadata for a document.
PUT	/documents/{id}/metadata	Replace all metadata for a document.
DELETE	/documents/{id}	Delete a specific document and its associated data.
DELETE	/documents/by-filter	Delete multiple documents matching filter criteria.
POST	/documents/search	Search across generated document summaries.
GET	/documents/download_zip	Download multiple original document files as a zip archive.
POST	/documents/{id}/extract	Start knowledge graph entity/relationship extraction for a document.
GET	/documents/{id}/entities	List Entities identified within a document.
GET	/documents/{id}/relationship	List Relationships identified within a document.
POST	/documents/{id}/deduplicate	Start entity deduplication process for a document.