Improvement[Community] Improve Document Loaders and Splitters (#27568)

- Fix word spelling error - Add static method decorator - Fix language splitter Co-authored-by: Erick Friis <[email protected]>
langchain-ai · Oct 24, 2024 · 455ab7d · 455ab7d
1 parent 7345470
commit 455ab7d
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 3 deletions.
diff --git a/libs/community/langchain_community/document_loaders/pdf.py b/libs/community/langchain_community/document_loaders/pdf.py
@@ -178,7 +178,7 @@ class PyPDFLoader(BasePDFLoader):
 
             loader = PyPDFLoader(
                 file_path = "./example_data/layout-parser-paper.pdf",
-                password = "my-pasword",
+                password = "my-password",
                 extract_images = True,
                 # headers = None
                 # extraction_mode = "plain",
@@ -572,7 +572,8 @@ def get_processed_pdf(self, pdf_id: str) -> str:
         response = requests.get(url, headers=self._mathpix_headers)
         return response.content.decode("utf-8")
 
-    def clean_pdf(self, contents: str) -> str:
+    @staticmethod
+    def clean_pdf(contents: str) -> str:
         """Clean the PDF file.
 
         Args:

diff --git a/libs/text-splitters/langchain_text_splitters/character.py b/libs/text-splitters/langchain_text_splitters/character.py
@@ -465,7 +465,7 @@ def get_separators_for_language(language: Language) -> List[str]:
                 "\n\\\\begin{verse}",
                 "\n\\\\begin{verbatim}",
                 # Now split by math environments
-                "\n\\\begin{align}",
+                "\n\\\\begin{align}",
                 "$$",
                 "$",
                 # Now split by the normal type of lines