jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

remove unnecessary function from youtube transcript (#4978)

Browse source 
* remove unnecessary function from youtube transctipt

* [autofix.ci] apply automated fixes

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Eric Hare <ericrhare@gmail.com>
This commit is contained in:
Rodrigo Nader 2024-12-03 12:46:50 -03:00 • committed by GitHub
commit a8470c89a2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 0 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

37
src/backend/base/langflow/components/tools/youtube_transcripts.py
View file

@ -225,40 +225,3 @@ class YouTubeTranscriptsComponent(Component):
except Exception as exc: # noqa: BLE001
# Using a specific error type for the return value
return Data(data={"error": f"Failed to get YouTube transcripts: {exc!s}"})
def youtube_transcripts(
self,
url: str = "",
transcript_format: TranscriptFormat = TranscriptFormat.TEXT,
chunk_size_seconds: int = 120,
language: str = "",
translation: str = "",
) -> Data | list[Data]:
"""Helper method to handle transcripts outside of component calls.
Args:
url: The YouTube URL to get transcripts from.
transcript_format: Format of transcripts ('text' or 'chunks').
chunk_size_seconds: Size of each transcript chunk in seconds.
language: Comma-separated list of language codes.
translation: Target language for translation.
Returns:
Data | list[Data]: Video transcripts as single Data or list of Data.
"""
if isinstance(transcript_format, str):
transcript_format = TranscriptFormat(transcript_format)
loader = YoutubeLoader.from_youtube_url(
url,
transcript_format=TranscriptFormat.TEXT
if transcript_format == TranscriptFormat.TEXT
else TranscriptFormat.CHUNKS,
chunk_size_seconds=chunk_size_seconds,
language=language.split(",") if language else ["en"],
translation=translation or None,
)
transcripts = loader.load()
if transcript_format == TranscriptFormat.TEXT and len(transcripts) > 0:
return Data(data={"transcript": transcripts[0].page_content})
return [Data(data={"content": doc.page_content, "metadata": doc.metadata}) for doc in transcripts]