جهّز بيانات تدريب موثوقة

from fusionpointai_training.client import DatasetManifest

# Continue with an authenticated client and an owned session.
ready = client.prepare_session(session["id"])
for item in ready["datasets"]:
    manifest = DatasetManifest(
        split=item["split"], sha256=item["sha256"],
        bytes=item["bytes"], rows=item["rows"],
    )
    rows = client.download_dataset(ready["id"], manifest)
    print(manifest.split, len(rows), manifest.sha256)
    # Each row has a text field. Do not log private training content.

import os
from fusionpointai_training import TrainingClient

client = TrainingClient(api_key=os.environ["FUSIONPOINTAI_API_KEY"])
session = client.get_session(os.environ["FUSIONPOINTAI_SESSION_ID"])
for manifest in session["datasets"]:
    print(
        manifest["split"],
        "rows:", manifest["rows"],
        "bytes:", manifest["bytes"],
        "sha256:", manifest["sha256"],
    )
# These are server-provided manifest values, not a local integrity pass.

import hashlib
from pathlib import Path

dataset_path = Path("train.jsonl")
expected_bytes = int(input("Manifest bytes: "))
expected_rows = int(input("Manifest rows: "))
expected_sha256 = input("Manifest SHA-256: ").strip()
body = dataset_path.read_bytes()
actual_sha256 = hashlib.sha256(body).hexdigest()
actual_rows = sum(1 for line in body.splitlines() if line)
print("Byte count matches:", len(body) == expected_bytes)
print("Row count matches:", actual_rows == expected_rows)
print("SHA-256 matches:", actual_sha256 == expected_sha256)
# Use values copied from the session manifest; do not log dataset contents.