langchain.document_loaders.quip.QuipLoader

class langchain.document_loaders.quip.QuipLoader(api_url: str, access_token: str, request_timeout: Optional[int] = 60)[source]

Load Quip pages.

Port of https://github.com/quip/quip-api/tree/master/samples/baqup

Parameters
  • api_urlhttps://platform.quip.com

  • access_token – token of access quip API. Please refer:

  • https – //quip.com/dev/automation/documentation/current#section/Authentication/Get-Access-to-Quip’s-APIs

  • request_timeout – timeout of request, default 60s.

Methods

__init__(api_url, access_token[, ...])

param api_url

https://platform.quip.com

get_thread_ids_by_folder_id(folder_id, ...)

Get thread ids by folder id and update in thread_ids

lazy_load()

A lazy loader for Documents.

load([folder_ids, thread_ids, max_docs, ...])

:param : param folder_ids: List of specific folder IDs to load, defaults to None :param : param thread_ids: List of specific thread IDs to load, defaults to None :param : param max_docs: Maximum number of docs to retrieve in total, defaults 1000 :param : param include_all_folders: Include all folders that your access_token can access, but doesn't include your private folder :param : param include_comments: Include comments, defaults to False :param : param include_images: Include images, defaults to False

load_and_split([text_splitter])

Load Documents and split into chunks.

process_thread(thread_id, include_images, ...)

process_thread_images(tree)

process_thread_messages(thread_id)

process_threads(thread_ids, include_images, ...)

Process a list of thread into a list of documents.

__init__(api_url: str, access_token: str, request_timeout: Optional[int] = 60)[source]
Parameters
  • api_urlhttps://platform.quip.com

  • access_token – token of access quip API. Please refer:

  • https – //quip.com/dev/automation/documentation/current#section/Authentication/Get-Access-to-Quip’s-APIs

  • request_timeout – timeout of request, default 60s.

get_thread_ids_by_folder_id(folder_id: str, depth: int, thread_ids: List[str]) None[source]

Get thread ids by folder id and update in thread_ids

lazy_load() Iterator[Document]

A lazy loader for Documents.

load(folder_ids: Optional[List[str]] = None, thread_ids: Optional[List[str]] = None, max_docs: Optional[int] = 1000, include_all_folders: bool = False, include_comments: bool = False, include_images: bool = False) List[Document][source]

:param : param folder_ids: List of specific folder IDs to load, defaults to None :param : param thread_ids: List of specific thread IDs to load, defaults to None :param : param max_docs: Maximum number of docs to retrieve in total, defaults 1000 :param : param include_all_folders: Include all folders that your access_token

can access, but doesn’t include your private folder

:param : param include_comments: Include comments, defaults to False :param : param include_images: Include images, defaults to False

load_and_split(text_splitter: Optional[TextSplitter] = None) List[Document]

Load Documents and split into chunks. Chunks are returned as Documents.

Parameters

text_splitter – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.

Returns

List of Documents.

process_thread(thread_id: str, include_images: bool, include_messages: bool) Optional[Document][source]
process_thread_images(tree: ElementTree) str[source]
process_thread_messages(thread_id: str) str[source]
process_threads(thread_ids: Sequence[str], include_images: bool, include_messages: bool) List[Document][source]

Process a list of thread into a list of documents.