Added multilingual support for the Wikipedia reader.

llama-index-integrations/readers/llama-index-readers-wikipedia/llama_index/readers/wikipedia/base.py

@@ -1,4 +1,5 @@
 """Simple reader that reads wikipedia."""
+
 from typing import Any, List
 
 from llama_index.core.readers.base import BasePydanticReader
@@ -27,15 +28,26 @@ def __init__(self) -> None:
     def class_name(cls) -> str:
         return "WikipediaReader"
 
-    def load_data(self, pages: List[str], **load_kwargs: Any) -> List[Document]:
+    def load_data(
+        self, pages: List[str], lang_prefix: str = "en", **load_kwargs: Any
+    ) -> List[Document]:
         """Load data from the input directory.
 
         Args:
             pages (List[str]): List of pages to read.
-
+            lang_prefix (str): Language prefix for Wikipedia. Defaults to English. Valid Wikipedia language codes
+            can be found at https://en.wikipedia.org/wiki/List_of_Wikipedias.
         """
         import wikipedia
 
+        if lang_prefix.lower() != "en":
+            if lang_prefix.lower() in wikipedia.languages():
+                wikipedia.set_lang(lang_prefix.lower())
+            else:
+                raise ValueError(
+                    f"Language prefix '{lang_prefix}' for Wikipedia is not supported. Check supported languages at https://en.wikipedia.org/wiki/List_of_Wikipedias."
+                )
+
         results = []
         for page in pages:
             wiki_page = wikipedia.page(page, **load_kwargs)

llama-index-integrations/readers/llama-index-readers-wikipedia/pyproject.toml

@@ -28,7 +28,7 @@ license = "MIT"
 maintainers = ["jerryjliu"]
 name = "llama-index-readers-wikipedia"
 readme = "README.md"
-version = "0.1.3"
+version = "0.1.4"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"