Ingesting Documents
If you are using the APIs directly, choose from one of the following methods.
Ingest documents hosted on public URLs into a GroundX bucket.
Upload documents hosted on a local file system into a GroundX bucket.
If you are using one of the supported SDKs, the ingest
method can be used to ingest both local and remote documents.
Ingest
An array of Document objects.
A flag that will block until the ingest process is complete. Default is false.
The size of each batch ingest request. Default is 10. Min is 1 and Max is 50.
An endpoint that returns a presigned URL within a JSON dictionary with key URL
. Default is the EyeLevel.ai file upload endpoint.
Document
The bucketId of the bucket which this file will be ingested to.
The local file path or remote URL of the document being ingested by GroundX.
The name of the file being ingested.
The type of document (one of the currently supported file types).
The amount of processing to perform on chunks (default ‘full’).
Custom metadata which can be used to influence GroundX’s search functionality. This data can be used to further hone GroundX search.