Pasha 4e189cd89a community[patch]: youtube loader transcript format (#16625) ...

- **Description**: YoutubeLoader right now returns one document that
contains the entire transcript. I think it would be useful to add an
option to return multiple documents, where each document would contain
one line of transcript with the start time and duration in the metadata.
For example,
[AssemblyAIAudioTranscriptLoader](https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/document_loaders/assemblyai.py)
is implemented in a similar way, it allows you to choose between the
format to use for the document loader.

2024-01-26 15:26:09 -08:00

..

cli

cli[patch]: add integration tests to default makefile (#16479)

2024-01-23 16:09:16 -07:00

community

community[patch]: youtube loader transcript format (#16625)

2024-01-26 15:26:09 -08:00

core

core: expand docstring for RunnableParallel (#16600)

2024-01-26 10:03:32 -05:00

experimental

core[patch]: simple prompt pretty printing (#15968)

2024-01-12 21:08:51 -05:00

langchain

langchain[patch]: inconsistent results with RecursiveCharacterTextSplitter's add_start_index=True (#16583)

2024-01-25 15:50:06 -08:00

partners

google-vertexai[patch]: streaming bug (#16603)

2024-01-26 09:45:34 -08:00