mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-04 12:13:05 +00:00
Alex
574f96341e
The backend import package is now docsgpt, the name it will carry on PyPI; application was far too generic to install into anyone's site-packages. git mv plus a mechanical rewrite of every import, dotted string and path reference: 734 Python files, the compose files, Dockerfile, workflows, docs, setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage config, .gitignore. Behaviour is unchanged. Kept for one release: - A top-level application package whose meta-path finder resolves application.x.y to the already-imported docsgpt.x.y object, so old imports and entry points (celery -A application.app.celery, uvicorn application.asgi:asgi_app) keep working with a FutureWarning. - Celery registers every application.* task name as an alias of its docsgpt.* task on start-up, so messages queued by the previous release still run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries the previous release wrote are left unread instead of firing twice. The backend image builds from the repository root (docker build -f docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore allow-lists docsgpt/ and application/ and keeps caches, local data, .env files, the sample index files and the Dockerfile out. Compose and the image workflows point at the new context.
49 lines
1.6 KiB
Python
49 lines
1.6 KiB
Python
from pathlib import Path
|
|
from typing import Dict, Union
|
|
|
|
from docsgpt.core.settings import settings
|
|
from docsgpt.parser.file.base_parser import BaseParser
|
|
from docsgpt.stt.stt_creator import STTCreator
|
|
from docsgpt.stt.upload_limits import enforce_audio_file_size_limit
|
|
|
|
|
|
class AudioParser(BaseParser):
|
|
def __init__(self, parser_config=None):
|
|
super().__init__(parser_config=parser_config)
|
|
self._transcript_metadata: Dict[str, Dict] = {}
|
|
|
|
def _init_parser(self) -> Dict:
|
|
return {}
|
|
|
|
def parse_file(self, file: Path, errors: str = "ignore") -> Union[str, list[str]]:
|
|
_ = errors
|
|
try:
|
|
enforce_audio_file_size_limit(file.stat().st_size)
|
|
except OSError:
|
|
pass
|
|
stt = STTCreator.create_stt(settings.STT_PROVIDER)
|
|
result = stt.transcribe(
|
|
file,
|
|
language=settings.STT_LANGUAGE,
|
|
timestamps=settings.STT_ENABLE_TIMESTAMPS,
|
|
diarize=settings.STT_ENABLE_DIARIZATION,
|
|
)
|
|
|
|
transcript_metadata = {
|
|
"transcript_duration_s": result.get("duration_s"),
|
|
"transcript_language": result.get("language"),
|
|
"transcript_provider": result.get("provider"),
|
|
}
|
|
if result.get("segments"):
|
|
transcript_metadata["transcript_segments"] = result["segments"]
|
|
|
|
self._transcript_metadata[str(file)] = {
|
|
key: value
|
|
for key, value in transcript_metadata.items()
|
|
if value not in (None, [], {})
|
|
}
|
|
return result.get("text", "")
|
|
|
|
def get_file_metadata(self, file: Path) -> Dict:
|
|
return self._transcript_metadata.get(str(file), {})
|