mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-07-19 13:26:32 -04:00
Leonid Ganeline
c28cc0f1ac
# changed ValueError to ImportError Code cleaning. Fixed inconsistencies in ImportError handling. Sometimes it raises ImportError and sometime ValueError. I've changed all cases to the `raise ImportError` Also: - added installation instruction in the error message, where it missed; - fixed several installation instructions in the error message; - fixed several error handling in regards to the ImportError
35 lines
1.2 KiB
Python
35 lines
1.2 KiB
Python
"""Loading logic for loading documents from an s3 file."""
|
|
import os
|
|
import tempfile
|
|
from typing import List
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.document_loaders.base import BaseLoader
|
|
from langchain.document_loaders.unstructured import UnstructuredFileLoader
|
|
|
|
|
|
class S3FileLoader(BaseLoader):
|
|
"""Loading logic for loading documents from s3."""
|
|
|
|
def __init__(self, bucket: str, key: str):
|
|
"""Initialize with bucket and key name."""
|
|
self.bucket = bucket
|
|
self.key = key
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load documents."""
|
|
try:
|
|
import boto3
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Could not import `boto3` python package. "
|
|
"Please install it with `pip install boto3`."
|
|
)
|
|
s3 = boto3.client("s3")
|
|
with tempfile.TemporaryDirectory() as temp_dir:
|
|
file_path = f"{temp_dir}/{self.key}"
|
|
os.makedirs(os.path.dirname(file_path), exist_ok=True)
|
|
s3.download_file(self.bucket, self.key, file_path)
|
|
loader = UnstructuredFileLoader(file_path)
|
|
return loader.load()
|