Ingesting Documents

If you are using the APIs directly, choose from one of the following methods.

If you are using one of the supported SDKs, the ingest method can be used to ingest both local and remote documents.

Ingest

documents
arrayRequired

An array of Document objects.

wait_for_complete
bool

A flag that will block until the ingest process is complete. Default is false.

batch_size
int

The size of each batch ingest request. Default is 10. Min is 1 and Max is 50.

upload_api
str

An endpoint that returns a presigned URL within a JSON dictionary with key URL. Default is the EyeLevel.ai file upload endpoint.

Document

bucketId
integerRequired

The bucketId of the bucket which this file will be ingested to.

filePath
stringRequired

The local file path or remote URL of the document being ingested by GroundX.

fileName
string

The name of the file being ingested.

fileType
enum

The type of document (one of the currently supported file types).

processLevel
enum

The amount of processing to perform on chunks (default ‘full’).

searchData
object

Custom metadata which can be used to influence GroundX’s search functionality. This data can be used to further hone GroundX search.