mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-06 21:43:44 +00:00
community: better support of pathlib paths in document loaders (#18396)
So this arose from the https://github.com/langchain-ai/langchain/pull/18397 problem of document loaders not supporting `pathlib.Path`. This pull request provides more uniform support for Path as an argument. The core ideas for this upgrade: - if there is a local file path used as an argument, it should be supported as `pathlib.Path` - if there are some external calls that may or may not support Pathlib, the argument is immidiately converted to `str` - if there `self.file_path` is used in a way that it allows for it to stay pathlib without conversion, is is only converted for the metadata. Twitter handle: https://twitter.com/mwmajewsk
This commit is contained in:
@@ -1,7 +1,8 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from enum import Enum
|
||||
from typing import TYPE_CHECKING, Iterator, Optional
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Iterator, Optional, Union
|
||||
|
||||
import requests
|
||||
from langchain_core.documents import Document
|
||||
@@ -44,7 +45,7 @@ class AssemblyAIAudioTranscriptLoader(BaseLoader):
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
file_path: str,
|
||||
file_path: Union[str, Path],
|
||||
*,
|
||||
transcript_format: TranscriptFormat = TranscriptFormat.TEXT,
|
||||
config: Optional[assemblyai.TranscriptionConfig] = None,
|
||||
@@ -71,7 +72,7 @@ class AssemblyAIAudioTranscriptLoader(BaseLoader):
|
||||
if api_key is not None:
|
||||
assemblyai.settings.api_key = api_key
|
||||
|
||||
self.file_path = file_path
|
||||
self.file_path = str(file_path)
|
||||
self.transcript_format = transcript_format
|
||||
self.transcriber = assemblyai.Transcriber(config=config)
|
||||
|
||||
|
Reference in New Issue
Block a user