langchain_community.document_loaders.notiondb
.NotionDBLoader¶
- class langchain_community.document_loaders.notiondb.NotionDBLoader(integration_token: str, database_id: str, request_timeout_sec: Optional[int] = 10, *, filter_object: Optional[Dict[str, Any]] = None)[source]¶
Load from Notion DB.
Reads content from pages within a Notion Database. :param integration_token: Notion integration token. :type integration_token: str :param database_id: Notion database id. :type database_id: str :param request_timeout_sec: Timeout for Notion requests in seconds.
Defaults to 10.
- Parameters
filter_object (Dict[str, Any]) –
Filter object used to limit returned entries based on specified criteria. E.g.: {
”timestamp”: “last_edited_time”, “last_edited_time”: {
”on_or_after”: “2024-02-07”
}
- } -> will only return entries that were last edited
on or after 2024-02-07
Notion docs: https://developers.notion.com/reference/post-database-query-filter Defaults to None, which will return ALL entries.
integration_token (str) –
database_id (str) –
request_timeout_sec (int) –
Initialize with parameters.
Methods
__init__
(integration_token, database_id[, ...])Initialize with parameters.
A lazy loader for Documents.
aload
()Load data into Document objects.
A lazy loader for Documents.
load
()Load documents from the Notion database.
load_and_split
([text_splitter])Load Documents and split into chunks.
load_page
(page_summary)Read a page.
- __init__(integration_token: str, database_id: str, request_timeout_sec: Optional[int] = 10, *, filter_object: Optional[Dict[str, Any]] = None) None [source]¶
Initialize with parameters.
- Parameters
integration_token (str) –
database_id (str) –
request_timeout_sec (Optional[int]) –
filter_object (Optional[Dict[str, Any]]) –
- Return type
None
- async alazy_load() AsyncIterator[Document] ¶
A lazy loader for Documents.
- Return type
AsyncIterator[Document]
- load() List[Document] [source]¶
Load documents from the Notion database. :returns: List of documents. :rtype: List[Document]
- Return type
List[Document]
- load_and_split(text_splitter: Optional[TextSplitter] = None) List[Document] ¶
Load Documents and split into chunks. Chunks are returned as Documents.
Do not override this method. It should be considered to be deprecated!
- Parameters
text_splitter (Optional[TextSplitter]) – TextSplitter instance to use for splitting documents. Defaults to RecursiveCharacterTextSplitter.
- Returns
List of Documents.
- Return type
List[Document]