Ingest Manual Document
manual-ingest
Ingest Manual Document
Ingest a single document manually.
The document will be processed through the full pipeline:
- Stored in PostgreSQL
- Chunked into smaller pieces
- Embedded with OpenAI embeddings
- Entities and relations extracted
- Knowledge graph updated in Neo4j
This is useful for:
- Testing with real transcripts
- Importing external documents
- Quick demos without OAuth setup
POST
Ingest Manual Document
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
Request to manually ingest a document.
Target workspace
The text content to ingest
Minimum string length:
10Document title
Required string length:
1 - 500Optional vault to associate with
Type of document being ingested
Available options:
transcript, notes, document, article, email, chat Author name
Author email
Original source URL if applicable
Original creation date
Tags for categorization
Additional metadata