Parse

parse_result = await dex_file.parse(
    IrisParseJobParams(
        engine=ParseEngine.IRIS,
        options=IrisParseEngineOptions(
            layout="rt_detr_bce",
            text_ocr="openai/gpt-5.4",
            table_ocr="openai/gpt-5.4",
            confidence_threshold=0.5,
            img_method="description",
        ),
    )
)

import asyncio
from dex_sdk.types import (
    ParseEngine,
    IrisParseJobParams,
    IrisParseEngineOptions,
)

# Start a parse job (returns immediately)
parse_job = await project.start_parse_job(
    dex_file=dex_file,
    parameters=IrisParseJobParams(
        engine=ParseEngine.IRIS,
        options=IrisParseEngineOptions(
            layout="rt_detr_bce"
        )
    )
)

# Monitor job progress
while parse_job.data.status not in [JobStatus.SUCCEEDED, JobStatus.FAILED]:
    await asyncio.sleep(1)
    await parse_job.refresh()
    print(f"Job status: {parse_job.data.status}")

# Get result
if parse_job.data.status == JobStatus.SUCCEEDED:
    parse_result = await parse_job.get_result()
    print("Parse completed successfully")
else:
    print(f"Parse failed: {parse_job.data.error_message}")

from scale_gp_beta import SGPClient

sgp_client = SGPClient(
    api_key=os.getenv("SGP_API_KEY"),
    account_id=os.getenv("SGP_ACCOUNT_ID"),
)

# Search for job traces
spans = list(sgp_client.spans.search(
    sort_by="created_at",
    sort_order="desc",
    extra_metadata={"job_id": parse_job.data.id},
    parents_only=True,
))

if spans:
    trace_id = spans[0].trace_id
    all_spans = list(sgp_client.spans.search(trace_ids=[trace_id]))
    for span in all_spans:
        print(f"Span: {span.name}, Duration: {span.duration_ms}ms")

import asyncio
from dex_sdk.types import (
    ParseEngine,
    IrisParseJobParams,
    IrisParseEngineOptions,
)

# Parse all files in parallel
parse_tasks = [
    dex_file.parse(
        IrisParseJobParams(
            engine=ParseEngine.IRIS,
            options=IrisParseEngineOptions(
                layout="rt_detr_bce",  # native region-level chunks (IRIS v2 default)
            ),
        )
    )
    for dex_file in dex_files
]
parse_results = await asyncio.gather(*parse_tasks)
print(f"Parsed {len(parse_results)} documents")