bbchops/transcription
1
0
Fork 0
generated from john/python-template
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

boundaries

Browse Source
This commit is contained in:
John Lancaster
2026-06-28 12:33:57 -05:00
parent c409b42077
commit 4e4bf50219
5 changed files with 46 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/transcription/models.py
+5
View File
@@ -49,6 +49,11 @@ class Job(SQLModel, table=True):
document: Document = Relationship(back_populates="jobs")
transcript: Optional["Transcript"] = Relationship(back_populates="job")
@property
def filename(self) -> str:
"""Return the filename of the associated document."""
return self.document.filename if self.document else "unknown"
class Transcript(SQLModel, table=True):
"""The output of a transcription job."""
src/transcription/services/jobs.py
+19 -13
View File
@@ -29,16 +29,17 @@ class JobService(ServiceBase):
async def read_job(self, job_id: UUID, session: AsyncSession | None = None) -> Job:
"""Read an existing job from the database.
The selectinload option is used to eagerly load the related document for the job, which makes the full Document
model object available in the return Job object.
The related document is always eagerly loaded so callers can safely
access ``job.document`` in async contexts without triggering lazy-load IO.
"""
async with self._session_scope(session) as _session:
job = await _session.get(
Job,
job_id,
# Makes the full Document model object available in the return Job object
options=(selectinload(Job.document),), # pyright: ignore[reportArgumentType]
query = (
select(Job)
.options(selectinload(Job.document)) # pyright: ignore[reportArgumentType]
.where(Job.id == job_id)
.execution_options(populate_existing=True)
)
job = (await _session.exec(query)).first()
if job is None:
raise ValueError(f"Job with id {job_id} not found")
return job
@@ -67,7 +68,7 @@ class JobService(ServiceBase):
) -> Sequence[Job]:
"""Query jobs from the database based on provided filters."""
async with self._session_scope(session) as _session:
query = select(Job)
query = select(Job).options(selectinload(Job.document)) # pyright: ignore[reportArgumentType]
if status is not None:
query = query.where(Job.status == status)
if filename is not None:
@@ -81,11 +82,10 @@ class JobService(ServiceBase):
load_docs: bool = False,
session: AsyncSession | None = None,
) -> Sequence[Job]:
"""List all jobs in the database."""
"""List all jobs in the database with eagerly loaded documents."""
_ = load_docs
async with self._session_scope(session) as _session:
query = select(Job)
if load_docs:
query = query.options(selectinload(Job.document)) # pyright: ignore[reportArgumentType]
query = select(Job).options(selectinload(Job.document)) # pyright: ignore[reportArgumentType]
result = await _session.exec(query)
return result.all()
@@ -114,7 +114,13 @@ class JobService(ServiceBase):
once at an orchestration boundary.
"""
async with self._session_scope(session) as _session:
job = await _session.get(Job, job_id)
query = (
select(Job)
.options(selectinload(Job.document)) # pyright: ignore[reportArgumentType]
.where(Job.id == job_id)
.execution_options(populate_existing=True)
)
job = (await _session.exec(query)).first()
if job is None:
raise ValueError(f"Job with id {job_id} not found")
job.status = status
src/transcription/services/workflows.py
+18 -46
View File
@@ -6,7 +6,6 @@ from sqlmodel.ext.asyncio.session import AsyncSession
from ..config import Settings
from ..config import get_settings
from ..errors import AppError
from ..errors import ErrorCategory
from ..errors import classify_unexpected_error
from ..errors import format_error_detail
from ..models import Job
@@ -23,18 +22,20 @@ async def advance_job(
job: Job,
services: ServiceBundle,
settings: Settings | None = None,
session: AsyncSession | None = None,
) -> Job | None:
"""Advance a single job by lifecycle status."""
settings = settings or get_settings()
match job.status:
case JobStatus.QUEUED:
return await process_job(job=job, services=services, settings=settings)
return await process_queued_job(job=job, services=services, session=session)
case JobStatus.FAILED:
if job.retry_count < settings.worker_max_retries:
return await services.jobs.update_job_state(
job_id=job.id,
status=JobStatus.QUEUED,
retry_count_increment=1,
session=session,
)
else:
logger.error(f"Job {job.id} has failed and reached max retries.")
@@ -43,15 +44,13 @@ async def advance_job(
return
async def process_job(
async def process_queued_job(
*,
job: Job,
services: ServiceBundle,
settings: Settings | None = None,
session: AsyncSession | None = None,
) -> Job | None:
"""Process a queued job with workflow-owned transaction boundaries."""
runtime_settings = settings or get_settings()
"""Process one complete transcription attempt for a queued job."""
if job.status != JobStatus.QUEUED:
logger.warning(f"Job {job.id} is not queued. Current status: {job.status}")
return
@@ -60,28 +59,19 @@ async def process_job(
if session is None:
job = await services.jobs.mark_job_status(job.id, JobStatus.PROCESSING)
else:
# If we're sharing the session, need to make sure setting the Job to PROCESSING is committed before we start
# the transcription, otherwise other workers may see the job as still QUEUED and try to process it.
job = await services.jobs.mark_job_status(job.id, JobStatus.PROCESSING, session=session)
await session.commit()
document = job.document
if document is None:
error = AppError(
"Document not found",
category=ErrorCategory.NOT_FOUND,
suggestion="Re-upload the source document and retry processing.",
)
await _finalize_failed(job=job, services=services, error=error, session=session)
logger.error(
"Job failed operation=worker.process_job job_id=%s error_id=%s category=%s",
job.id,
error.error_id,
error.category.value,
)
return job
assert document is not None, (
f"Job {job.id} has no associated document or the document failed to be loaded by the job service."
)
try:
result = await transcribe_document_image(document.file_path)
await _finalize_transcribed(job=job, services=services, result=result, session=session)
job = await _finalize_transcribed(job=job, services=services, result=result, session=session)
logger.info(
"Job transcribed operation=worker.process_job job_id=%s document_id=%s provider=%s",
job.id,
@@ -89,27 +79,13 @@ async def process_job(
result.provider,
)
except Exception as exc: # noqa: BLE001
error = exc if isinstance(exc, AppError) else classify_unexpected_error(exc, operation="worker.process_job")
if _should_retry(job=job, error=error, settings=runtime_settings):
await _finalize_retry(
job=job,
services=services,
error=error,
settings=runtime_settings,
session=session,
)
logger.warning(
"Job retried operation=worker.process_job "
"job_id=%s document_id=%s retry_count=%s error_id=%s category=%s",
job.id,
document.id,
job.retry_count,
error.error_id,
error.category.value,
)
return job
match exc:
case AppError() as error:
pass
case _:
error = classify_unexpected_error(exc, operation="worker.process_job")
await _finalize_failed(job=job, services=services, error=error, session=session)
job = await _finalize_failed(job=job, services=services, error=error, session=session)
logger.error(
"Job failed operation=worker.process_job job_id=%s document_id=%s error_id=%s category=%s",
job.id,
@@ -131,14 +107,10 @@ async def process_next_queued_job(
if job is None:
return False
await process_job(job=job, services=services, settings=settings, session=session)
await advance_job(job=job, services=services, settings=settings, session=session)
return True
def _should_retry(*, job: Job, error: AppError, settings: Settings) -> bool:
return error.retriable and job.retry_count < settings.worker_max_retries
async def _finalize_transcribed(
*,
job: Job,
src/transcription/worker.py
+2 -2
View File
@@ -21,7 +21,7 @@ from .services import ServiceBundle
from .services.documents import DocumentService
from .services.jobs import JobService
from .services.transcription import TranscriptionService
from .services.workflows import process_job
from .services.workflows import advance_job
from .services.workflows import process_next_queued_job as process_next_queued_job_workflow
logger = logging.getLogger(__name__)
@@ -37,7 +37,7 @@ async def queue_consumer_loop(queue: asyncio.Queue[UUID], stop_event: asyncio.Ev
with handle_worker_exceptions():
async with _get_queue_item(queue) as job_id:
job = await service.read_job(job_id)
asyncio.create_task(process_job(job=job, services=ServiceBundle()))
asyncio.create_task(advance_job(job=job, services=ServiceBundle()))
@contextmanager