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/baiducloud_bos_directory.py

53 lines
1.7 KiB
Python

from typing import Any, Iterator
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
7 months ago
from langchain_core.documents import Document
from langchain_community.document_loaders.base import BaseLoader
class BaiduBOSDirectoryLoader(BaseLoader):
"""Load from `Baidu BOS directory`."""
def __init__(self, conf: Any, bucket: str, prefix: str = ""):
"""Initialize with BOS config, bucket and prefix.
:param conf(BosConfig): BOS config.
:param bucket(str): BOS bucket.
:param prefix(str): prefix.
"""
self.conf = conf
self.bucket = bucket
self.prefix = prefix
def lazy_load(self) -> Iterator[Document]:
"""Load documents."""
try:
from baidubce.services.bos.bos_client import BosClient
except ImportError:
raise ImportError(
"Please install bce-python-sdk with `pip install bce-python-sdk`."
)
client = BosClient(self.conf)
contents = []
marker = ""
while True:
response = client.list_objects(
bucket_name=self.bucket,
prefix=self.prefix,
marker=marker,
max_keys=1000,
)
contents_len = len(response.contents)
contents.extend(response.contents)
if response.is_truncated or contents_len < int(str(response.max_keys)):
break
marker = response.next_marker
from langchain_community.document_loaders.baiducloud_bos_file import (
BaiduBOSFileLoader,
)
for content in contents:
if str(content.key).endswith("/"):
continue
loader = BaiduBOSFileLoader(self.conf, self.bucket, str(content.key))
yield loader.load()[0]