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/tencent_cos_directory.py

51 lines
1.7 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
from typing import Any, Iterator, List
from langchain_core.documents import Document
from langchain_community.document_loaders.base import BaseLoader
from langchain_community.document_loaders.tencent_cos_file import TencentCOSFileLoader
class TencentCOSDirectoryLoader(BaseLoader):
"""Load from `Tencent Cloud COS` directory."""
def __init__(self, conf: Any, bucket: str, prefix: str = ""):
"""Initialize with COS config, bucket and prefix.
:param conf(CosConfig): COS config.
:param bucket(str): COS bucket.
:param prefix(str): prefix.
"""
self.conf = conf
self.bucket = bucket
self.prefix = prefix
def load(self) -> List[Document]:
return list(self.lazy_load())
def lazy_load(self) -> Iterator[Document]:
"""Load documents."""
try:
from qcloud_cos import CosS3Client
except ImportError:
raise ImportError(
"Could not import cos-python-sdk-v5 python package. "
"Please install it with `pip install cos-python-sdk-v5`."
)
client = CosS3Client(self.conf)
contents = []
marker = ""
while True:
response = client.list_objects(
Bucket=self.bucket, Prefix=self.prefix, Marker=marker, MaxKeys=1000
)
if "Contents" in response:
contents.extend(response["Contents"])
if response["IsTruncated"] == "false":
break
marker = response["NextMarker"]
for content in contents:
if content["Key"].endswith("/"):
continue
loader = TencentCOSFileLoader(self.conf, self.bucket, content["Key"])
yield loader.load()[0]