Intelligence APIs
Ingest
Extract claims, predictions, and causal edges from a URL, text, or file and store them in your knowledge graph.
POST
Ingest external content — 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.
Results include chunks, claims, and predictions from your personal knowledge graph.
Endpoints
| Method | Path | Input |
|---|---|---|
POST | /api/v1/ingest | JSON body with url or content |
POST | /api/v1/ingest/file | multipart/form-data with file |
POST /api/v1/ingest
Request Body
URL to fetch and ingest. Either
url or content is required.Raw text content to ingest (max 20,000 characters). Either
url or content is required.Access control for the ingested content.
private (default) — only accessible to you. public — accessible to anyone with your API key.POST /api/v1/ingest/file
Request Body (multipart/form-data)
PDF, Markdown, or TXT file to ingest.
Access control.
private or public.Response
Unique ID of the ingested source document.
ID of the TKG graph created for this document.
Title extracted from the source content.
List of falsifiable factual statements extracted from the content.
List of future predictions extracted from the content.
Causal relationships between extracted claims and predictions.
Character length of the original content stored as vector chunks.
Number of vector chunks stored for semantic search.
Searching Ingested Content
UseGET /api/v1/fact-search with source=ingest to search your ingested content:

