Ground - NDI Platform API

Ground is target location, not claim verification. Pass 1–30 targets.

from ndi_sdk import NdiClient
from ndi_sdk.models.document_ops import GroundTarget

with NdiClient() as client:
    upload = client.documents.create_upload("report.pdf")
    job = client.jobs.wait(
        client.documents.ground(
            upload,
            targets=[GroundTarget(id="total", text="1,200.50")],
            wait_seconds=30,
        ).job_id
    )
    for target in job.result.targets:
        for match in target.matches:
            print(target.id, match.matched_text, match.location)

Method signature

def ground(
    source: DocumentSource | UploadResponse,
    *,
    targets: list[GroundTarget],
    options: GroundOptions | None = None,
    wait_seconds: int = 0,
    idempotency_key: str | None = None,
) -> Job

Parameters

Parameter	Type	Required	Description
`source`	`DocumentSource` or `UploadResponse`	Yes	File or prior parse
`targets`	`list[GroundTarget]`	Yes	1–30 quoted strings
`options`	`GroundOptions`	No	`max_matches`, `include_previews`
`wait_seconds`	`int`	No	Hold the HTTP response open (max 300)

Returns

A Job. On success, result.targets[].matches carries locators. not_found is an answer about the document. Set options.include_previews=True to mint crop URLs. Fetch them with client.jobs.ground_crop(job_id, artifact_ref). See Ground guide and Ground response.