bbchops/transcription
1
0
Fork 0
generated from john/python-template
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

V3 Updated V3 core documents. Added data folder backup/restore before/after running destructive tests.

Browse Source
This commit is contained in:
Jim Lancaster
2026-08-09 10:51:30 -05:00
parent b59d3da23e
commit e6549277c6
14 changed files with 417 additions and 271 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/transcription/services/jobs.py
+5 -5
View File
@@ -270,8 +270,8 @@ class JobService(ServiceBase):
await self._finalize(session=_session, caller_session=session, refresh=(job,))
return job
async def resubmit_non_transcribed_sources(self, *, job_id: UUID, session: AsyncSession | None = None) -> int:
"""Reset non-transcribed source executions and queue the job for reprocessing."""
async def resubmit_failed_sources(self, *, job_id: UUID, session: AsyncSession | None = None) -> int:
"""Reset failed source executions and queue the job for reprocessing."""
async with self._session_scope(session) as _session:
query = (
select(Job)
@@ -292,12 +292,12 @@ class JobService(ServiceBase):
suggestion="Cancel processing first, then resubmit remaining sources.",
)
candidates = [job_source for job_source in job.job_sources if job_source.status != JobSourceStatus.TRANSCRIBED]
candidates = [job_source for job_source in job.job_sources if job_source.status == JobSourceStatus.FAILED]
if not candidates:
raise JobResubmitBlockedError(
"Job has no non-transcribed sources to resubmit",
"Job has no failed sources to resubmit",
category=ErrorCategory.VALIDATION,
suggestion="Only failed or pending sources can be resubmitted.",
suggestion="Only failed sources can be resubmitted.",
)
now = datetime.now(UTC)
src/transcription/services/transcription.py
-84
View File
@@ -346,90 +346,6 @@ class TranscriptionService(ServiceBase):
result = await _session.exec(query)
return result.all()
async def transcribe_document(
self,
image_path: str | Path,
job_id: UUID,
*,
prompt_name: str = DEFAULT_PROMPT_FILE,
session: AsyncSession | None = None,
) -> None:
"""Transcribe a local image using the configured prompt and provider."""
result = await transcribe_document_image(
image_path=image_path,
prompt_name=prompt_name,
settings=self.settings,
provider=self.provider,
)
await self.update_job_transcription(
job_id=job_id,
text=result.text,
error_detail=None,
provider=result.provider,
model=result.model,
prompt_name=result.prompt_name,
prompt_hash=result.prompt_hash,
system_prompt=result.system_prompt,
user_prompt=result.user_prompt,
temperature=result.temperature,
top_p=result.top_p,
session=session,
)
async def update_job_transcription(
self,
*,
job_id: UUID,
text: str | None,
error_detail: str | None = None,
provider: str | None = None,
model: str | None = None,
prompt_name: str = DEFAULT_PROMPT_FILE,
prompt_hash: str | None = None,
system_prompt: str | None = None,
user_prompt: str | None = None,
temperature: float | None = None,
top_p: float | None = None,
session: AsyncSession | None = None,
) -> Job:
"""Persist transcription output for the first ordered source in a job's document.
This compatibility helper keeps legacy single-source workflows working.
New multi-source flows should use ``update_job_source_transcription``.
"""
async with self._session_scope(session) as _session:
job = await _session.get(Job, job_id)
if job is None:
raise TranscriptionNotFoundError(
f"Job with id {job_id} not found",
category=ErrorCategory.NOT_FOUND,
suggestion="Verify the job id and retry.",
)
job.provider = provider or job.provider or self.settings.provider.value
job.model = model or job.model or _resolve_transcript_model(provider=self.provider, settings=self.settings)
job.date_updated = datetime.now(UTC)
source = await _session.exec(
select(Source)
.where(Source.document_id == job.document_id)
.order_by(Source.page_number) # pyright: ignore[reportArgumentType]
)
source_row = source.first()
if source_row is not None:
await self.update_job_source_transcription(
job_id=job.id,
source_id=source_row.id,
text=text,
error_detail=error_detail,
provider=provider,
model=model,
session=_session,
)
await self._finalize(session=_session, caller_session=session, refresh=(job,))
return job
async def update_job_source_transcription(
self,
*,
src/transcription/services/workflows.py
-138
View File
@@ -213,144 +213,6 @@ async def process_next_queued_job(
return True
async def _finalize_transcribed(
*,
job: Job,
services: ServiceBundle,
result: TranscriptionResult,
session: AsyncSession | None = None,
) -> Job:
"""Transaction B: job transcription output + TRANSCRIBED in one commit."""
if session is None:
async with services.jobs._session_scope() as local_session:
await services.transcriptions.update_job_transcription(
job_id=job.id,
text=result.text,
error_detail=None,
provider=result.provider,
model=result.model,
prompt_name=result.prompt_name,
session=local_session,
)
updated_job = await services.jobs.mark_job_status(
job.id,
JobStatus.TRANSCRIBED,
session=local_session,
)
await local_session.commit()
return updated_job
await services.transcriptions.update_job_transcription(
job_id=job.id,
text=result.text,
error_detail=None,
provider=result.provider,
model=result.model,
prompt_name=result.prompt_name,
session=session,
)
updated_job = await services.jobs.mark_job_status(
job.id,
JobStatus.TRANSCRIBED,
session=session,
)
await session.commit()
return updated_job
async def _finalize_retry(
*,
job: Job,
services: ServiceBundle,
error: AppError,
settings: Settings,
session: AsyncSession | None = None,
) -> Job:
"""Transaction C: job error detail + QUEUED + retry increment in one commit."""
if session is None:
async with services.jobs._session_scope() as local_session:
await services.transcriptions.update_job_transcription(
job_id=job.id,
text=None,
error_detail=format_error_detail(error),
prompt_name=DEFAULT_PROMPT_FILE,
session=local_session,
)
updated_job = await services.jobs.update_job_state(
job_id=job.id,
status=JobStatus.QUEUED,
retry_count_increment=1,
session=local_session,
)
await local_session.commit()
else:
await services.transcriptions.update_job_transcription(
job_id=job.id,
text=None,
error_detail=format_error_detail(error),
prompt_name=DEFAULT_PROMPT_FILE,
session=session,
)
updated_job = await services.jobs.update_job_state(
job_id=job.id,
status=JobStatus.QUEUED,
retry_count_increment=1,
session=session,
)
await session.commit()
if settings.worker_retry_backoff_seconds > 0:
await asyncio.sleep(settings.worker_retry_backoff_seconds)
return updated_job
async def _finalize_failed(
*,
job: Job,
services: ServiceBundle,
error: AppError,
session: AsyncSession | None = None,
) -> Job:
"""Transaction B: job error detail + FAILED in one commit."""
if session is None:
async with services.jobs._session_scope() as local_session:
await services.transcriptions.update_job_transcription(
job_id=job.id,
text=None,
error_detail=format_error_detail(error),
prompt_name=DEFAULT_PROMPT_FILE,
session=local_session,
)
updated_job = await services.jobs.mark_job_status(
job.id,
JobStatus.FAILED,
session=local_session,
)
await local_session.commit()
return updated_job
await services.transcriptions.update_job_transcription(
job_id=job.id,
text=None,
error_detail=format_error_detail(error),
prompt_name=DEFAULT_PROMPT_FILE,
session=session,
)
updated_job = await services.jobs.mark_job_status(
job.id,
JobStatus.FAILED,
session=session,
)
await session.commit()
return updated_job
def _resolve_primary_source(job: Job) -> Source | None:
if not job.job_sources:
return None
return next((job_source.source for job_source in job.job_sources if job_source.source is not None), None)
def _resolve_job_sources(job: Job) -> list[Source]:
"""Resolve non-transcribed linked sources for a job in deterministic page order."""
if not job.job_sources:
src/transcription/ui/pages/jobs_page.py
+4 -4
View File
@@ -219,7 +219,7 @@ def register_page() -> None: # noqa: PLR0915
ui.label("Job not found").classes("text-h6 ui-text-danger p-4")
return
non_transcribed_count = sum(1 for js in job.job_sources if js.status != JobSourceStatus.TRANSCRIBED)
failed_count = sum(1 for js in job.job_sources if js.status == JobSourceStatus.FAILED)
with ui.column().classes("w-full max-w-xl mx-auto p-4 gap-4"):
page_header("Resubmit Job")
@@ -227,14 +227,14 @@ def register_page() -> None: # noqa: PLR0915
with archival_card(extra_classes="gap-2"):
ui.label(f"Job ID: {job.id}").classes("text-sm font-semibold font-mono ui-text-primary")
metadata_row("Current Status:", job.status.value)
metadata_row("Non-Transcribed Sources:", str(non_transcribed_count))
metadata_row("Failed Sources:", str(failed_count))
ui.label(
"Resubmit queues all non-transcribed linked sources. New results overwrite prior page-level results."
"Resubmit queues only failed linked sources. New results overwrite prior page-level results."
).classes("text-xs ui-text-muted")
async def submit_resubmit() -> None:
try:
resubmitted_count = await jobs_service.resubmit_non_transcribed_sources(job_id=job.id)
resubmitted_count = await jobs_service.resubmit_failed_sources(job_id=job.id)
except JobResubmitBlockedError as exc:
ui.notify(exc.message, type="warning")
return