langchain_community.document_loaders.wikipedia.WikipediaLoader¶
- class langchain_community.document_loaders.wikipedia.WikipediaLoader(query: str, lang: str = 'en', load_max_docs: Optional[int] = 25, load_all_available_meta: Optional[bool] = False, doc_content_chars_max: Optional[int] = 4000)[source]¶
Load from Wikipedia.
The hard limit on the length of the query is 300 for now.
Each wiki page represents one Document.
Initializes a new instance of the WikipediaLoader class.
- Parameters
query (str) – The query string to search on Wikipedia.
lang (str, optional) – The language code for the Wikipedia language edition. Defaults to “en”.
load_max_docs (int, optional) – The maximum number of documents to load. Defaults to 100.
load_all_available_meta (bool, optional) – Indicates whether to load all available metadata for each document. Defaults to False.
doc_content_chars_max (int, optional) – The maximum number of characters for the document content. Defaults to 4000.
Methods
__init__(query[, lang, load_max_docs, ...])Initializes a new instance of the WikipediaLoader class.
A lazy loader for Documents.
Loads the query result from Wikipedia into a list of Documents.
load()Load data into Document objects.
load_and_split([text_splitter])Load Documents and split into chunks.
- __init__(query: str, lang: str = 'en', load_max_docs: Optional[int] = 25, load_all_available_meta: Optional[bool] = False, doc_content_chars_max: Optional[int] = 4000)[source]¶
Initializes a new instance of the WikipediaLoader class.
- Parameters
query (str) – The query string to search on Wikipedia.
lang (str, optional) – The language code for the Wikipedia language edition. Defaults to “en”.
load_max_docs (int, optional) – The maximum number of documents to load. Defaults to 100.
load_all_available_meta (bool, optional) – Indicates whether to load all available metadata for each document. Defaults to False.
doc_content_chars_max (int, optional) – The maximum number of characters for the document content. Defaults to 4000.
- async alazy_load() AsyncIterator[Document]¶
A lazy loader for Documents.
- Return type
AsyncIterator[Document]
- lazy_load() Iterator[Document][source]¶
Loads the query result from Wikipedia into a list of Documents.
- Returns
- A list of Document objects representing the loaded
Wikipedia pages.
- Return type
Iterator[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]