Skip to main content
POST
Ingest external content, such as a URL, raw text, or uploaded file, and automatically extract structured knowledge (claims, predictions, causal edges) into your personal TKG (Temporal Knowledge Graph). Extracted knowledge is also stored as vector embeddings for semantic search.

Endpoints


POST /api/v1/ingest

Request Body

string
URL to fetch and ingest. Either url or content is required.
string
Raw text content to ingest (max 20,000 characters). Either url or content is required.
string
default:"private"
Access control for the ingested content. private (default) is only accessible to you. public is accessible to anyone with your API key.

POST /api/v1/ingest/file

Request Body (multipart/form-data)

file
required
PDF, Markdown, or TXT file to ingest.
string
default:"private"
Access control. private or public.

Response

string
Unique ID of the ingested source document.
string
ID of the TKG graph created for this document.
string
Title extracted from the source content.
array
List of falsifiable factual statements extracted from the content.
array
List of future predictions extracted from the content.
array
Causal relationships between extracted claims and predictions.
number
Character length of the original content stored as vector chunks.
number
Number of vector chunks stored for semantic search.

Searching Ingested Content

Use GET /api/v1/fact-search with source=ingest to search your ingested content:
Results include chunks, claims, and predictions from your personal knowledge graph.