mirror of
https://github.com/hwchase17/langchain.git
synced 2026-01-29 21:30:18 +00:00
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
33 lines
1.1 KiB
Python
33 lines
1.1 KiB
Python
"""Loading logic for loading documents from an s3 directory."""
|
|
from typing import List
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.document_loaders.base import BaseLoader
|
|
from langchain.document_loaders.s3_file import S3FileLoader
|
|
|
|
|
|
class S3DirectoryLoader(BaseLoader):
|
|
"""Loading logic for loading documents from s3."""
|
|
|
|
def __init__(self, bucket: str, prefix: str = ""):
|
|
"""Initialize with bucket and key name."""
|
|
self.bucket = bucket
|
|
self.prefix = prefix
|
|
|
|
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.resource("s3")
|
|
bucket = s3.Bucket(self.bucket)
|
|
docs = []
|
|
for obj in bucket.objects.filter(Prefix=self.prefix):
|
|
loader = S3FileLoader(self.bucket, obj.key)
|
|
docs.extend(loader.load())
|
|
return docs
|