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/larksuite.py

53 lines
2.0 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 json
import urllib.request
from typing import Any, Iterator, List
from langchain_core.documents import Document
from langchain_community.document_loaders.base import BaseLoader
class LarkSuiteDocLoader(BaseLoader):
"""Load from `LarkSuite` (`FeiShu`)."""
def __init__(self, domain: str, access_token: str, document_id: str):
"""Initialize with domain, access_token (tenant / user), and document_id.
Args:
domain: The domain to load the LarkSuite.
access_token: The access_token to use.
document_id: The document_id to load.
"""
self.domain = domain
self.access_token = access_token
self.document_id = document_id
def _get_larksuite_api_json_data(self, api_url: str) -> Any:
"""Get LarkSuite (FeiShu) API response json data."""
headers = {"Authorization": f"Bearer {self.access_token}"}
request = urllib.request.Request(api_url, headers=headers)
with urllib.request.urlopen(request) as response:
json_data = json.loads(response.read().decode())
return json_data
def lazy_load(self) -> Iterator[Document]:
"""Lazy load LarkSuite (FeiShu) document."""
api_url_prefix = f"{self.domain}/open-apis/docx/v1/documents"
metadata_json = self._get_larksuite_api_json_data(
f"{api_url_prefix}/{self.document_id}"
)
raw_content_json = self._get_larksuite_api_json_data(
f"{api_url_prefix}/{self.document_id}/raw_content"
)
text = raw_content_json["data"]["content"]
metadata = {
"document_id": self.document_id,
"revision_id": metadata_json["data"]["document"]["revision_id"],
"title": metadata_json["data"]["document"]["title"],
}
yield Document(page_content=text, metadata=metadata)
def load(self) -> List[Document]:
"""Load LarkSuite (FeiShu) document."""
return list(self.lazy_load())