You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs/community/langchain_community/document_loaders/azure_blob_storage_file.py

45 lines
1.6 KiB
Python

community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463) Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
9 months ago
import os
import tempfile
from typing import List
from langchain_core.documents import Document
from langchain_community.document_loaders.base import BaseLoader
from langchain_community.document_loaders.unstructured import UnstructuredFileLoader
class AzureBlobStorageFileLoader(BaseLoader):
"""Load from `Azure Blob Storage` files."""
def __init__(self, conn_str: str, container: str, blob_name: str):
"""Initialize with connection string, container and blob name."""
self.conn_str = conn_str
"""Connection string for Azure Blob Storage."""
self.container = container
"""Container name."""
self.blob = blob_name
"""Blob name."""
def load(self) -> List[Document]:
"""Load documents."""
try:
from azure.storage.blob import BlobClient
except ImportError as exc:
raise ImportError(
"Could not import azure storage blob python package. "
"Please install it with `pip install azure-storage-blob`."
) from exc
client = BlobClient.from_connection_string(
conn_str=self.conn_str, container_name=self.container, blob_name=self.blob
)
with tempfile.TemporaryDirectory() as temp_dir:
file_path = f"{temp_dir}/{self.container}/{self.blob}"
os.makedirs(os.path.dirname(file_path), exist_ok=True)
with open(f"{file_path}", "wb") as file:
blob_data = client.download_blob()
blob_data.readinto(file)
loader = UnstructuredFileLoader(file_path)
return loader.load()