Retrieve Full Document Content | PrivateGPT

Retrieve the full content of filtered documents.

This endpoint provides access to complete document content rather than semantic chunks. Use this when you need the entire context of documents rather than relevant excerpts.

Key Features:

Full Content: Get complete documents rather than chunks
Multiple Formats: Return as markdown text or structured objects
Node Type Filtering: Include or exclude images, tables, and other node types
Node ID Filtering: Retrieve specific sections by their node IDs
Filtered Retrieval: Select specific documents using metadata filters
Bulk Retrieval: Get multiple documents in one request

Format Options:

markdown (default): Returns flattened markdown text representation
object: Returns hierarchical tree structure with typed nodes

Content Filtering:

Use include to retrieve only specific node types
Use exclude to omit unwanted content types
Use node_ids to retrieve specific sections or nodes by ID
Supports TextNode, ImageNode, TableNode, and other node types

Subtree Filtering:

Specify node_ids to retrieve only certain sections/nodes
Set include_children=True (default) to get full subtrees
Set include_children=False to get only specified nodes
Set include_ancestors=True to include parent context

Notes:

Node type filtering is applied to all retrieved documents
Object format preserves document structure and hierarchy
Markdown format provides a flattened, readable text representation
When node_ids is specified, returns filtered tree structure

Retrieve the full content of filtered documents. This endpoint provides access to complete document content rather than semantic chunks. Use this when you need the entire context of documents rather than relevant excerpts. Key Features: * Full Content: Get complete documents rather than chunks * Multiple Formats: Return as markdown text or structured objects * Node Type Filtering: Include or exclude images, tables, and other node types * Node ID Filtering: Retrieve specific sections by their node IDs * Filtered Retrieval: Select specific documents using metadata filters * Bulk Retrieval: Get multiple documents in one request Format Options: * markdown (default): Returns flattened markdown text representation * object: Returns hierarchical tree structure with typed nodes Content Filtering: * Use include to retrieve only specific node types * Use exclude to omit unwanted content types * Use node_ids to retrieve specific sections or nodes by ID * Supports TextNode, ImageNode, TableNode, and other node types Subtree Filtering: * Specify node_ids to retrieve only certain sections/nodes * Set include_children=True (default) to get full subtrees * Set include_children=False to get only specified nodes * Set include_ancestors=True to include parent context Notes: * Node type filtering is applied to all retrieved documents * Object format preserves document structure and hierarchy * Markdown format provides a flattened, readable text representation * When node_ids is specified, returns filtered tree structure

Request

Request body for retrieving full document content.

Contains context filtering options to select specific documents by collection, artifacts, and metadata criteria. Unlike chunk retrieval, this returns complete document content rather than excerpts.

Format Options:

markdown (default): Returns content as formatted markdown text
object: Returns structured tree representation of document hierarchy

Content Filtering:

include: Specify node types to include (TextNode, ImageNode, TableNode, etc.)
exclude: Specify node types to exclude from the response
node_ids: Specify exact node IDs to retrieve specific sections or parts
include_children: Whether to include full subtrees below selected nodes
include_ancestors: Whether to include ancestor path for context

The request body defines filtering criteria for bulk document content retrieval from the ingested knowledge base.

Request body for retrieving full document content. Contains context filtering options to select specific documents by collection, artifacts, and metadata criteria. Unlike chunk retrieval, this returns complete document content rather than excerpts. Format Options: * markdown (default): Returns content as formatted markdown text * object: Returns structured tree representation of document hierarchy Content Filtering: * include: Specify node types to include (TextNode, ImageNode, TableNode, etc.) * exclude: Specify node types to exclude from the response * node_ids: Specify exact node IDs to retrieve specific sections or parts * include_children: Whether to include full subtrees below selected nodes * include_ancestors: Whether to include ancestor path for context The request body defines filtering criteria for bulk document content retrieval from the ingested knowledge base.

context_filterobjectRequired

Filter to select documents to retrieve. Supports filtering by collection, artifacts, and metadata.

formatenumOptional

Format for returned content. 'object' returns structured data, 'markdown' returns content formatted as markdown text.

filterobject or nullOptional

Content filtering options to include or exclude specific node types. Use this to control the types of content returned in the response.

max_tokensinteger or nullOptional>=1

Maximum number of tokens to return in the content. If not set, returns full content of the documents.

Response

Successful content retrieval

datalist of objects

List of documents with their full content

Errors

401

Unauthorized Error

422

Unprocessable Entity Error

Retrieve the full content of filtered documents.

This endpoint provides access to complete document content rather than semantic chunks. Use this when you need the entire context of documents rather than relevant excerpts.

Key Features:

Full Content: Get complete documents rather than chunks
Multiple Formats: Return as markdown text or structured objects
Node Type Filtering: Include or exclude images, tables, and other node types
Node ID Filtering: Retrieve specific sections by their node IDs
Filtered Retrieval: Select specific documents using metadata filters
Bulk Retrieval: Get multiple documents in one request

Format Options:

markdown (default): Returns flattened markdown text representation
object: Returns hierarchical tree structure with typed nodes

Content Filtering:

Use include to retrieve only specific node types
Use exclude to omit unwanted content types
Use node_ids to retrieve specific sections or nodes by ID
Supports TextNode, ImageNode, TableNode, and other node types

Subtree Filtering:

Specify node_ids to retrieve only certain sections/nodes
Set include_children=True (default) to get full subtrees
Set include_children=False to get only specified nodes
Set include_ancestors=True to include parent context

Notes:

Node type filtering is applied to all retrieved documents
Object format preserves document structure and hierarchy
Markdown format provides a flattened, readable text representation
When node_ids is specified, returns filtered tree structure

$	curl -X POST /v1/artifacts/content \
>	-H "Content-Type: application/json" \
>	-d '{
>	"context_filter": {}
>	}'

1	{
2	"data": [
3	{
4	"artifact_id": "annual_report_2023",
5	"content": "ANNUAL REPORT 2023\n\nExecutive Summary\n\nFiscal year 2023 marked a transformative period for our organization with record-breaking performance across all key metrics...\n\n[Full document content continues...]"
6	},
7	{
8	"artifact_id": "quarterly_summary_q4",
9	"content": "Q4 QUARTERLY SUMMARY\n\nQuarter Overview\n\nThe fourth quarter concluded our strongest year on record, with revenue growth of 34% year-over-year...\n\n[Full document content continues...]"
10	}
11	]
12	}