Typo fix to MathpixPDFLoader - changed processed_file_format default … (#10960)

…from mmd to md. https://github.com/langchain-ai/langchain/issues/7282

<!-- 
- **Description:** minor fix to a breaking typo - MathPixPDFLoader
processed_file_format is "mmd" by default, doesn't work, changing to
"md" fixes the issue,
- **Issue:** 7282
(https://github.com/langchain-ai/langchain/issues/7282),
  - **Dependencies:** none,
  - **Tag maintainer:** @hwchase17,
  - **Twitter handle:** none
 -->

Co-authored-by: jare0530 <7915+jare0530@users.noreply.ghe.oculus-rep.com>

libs/langchain/langchain/document_loaders/pdf.py

@@ -326,7 +326,7 @@ class MathpixPDFLoader(BasePDFLoader):
     def __init__(
         self,
         file_path: str,
-        processed_file_format: str = "mmd",
+        processed_file_format: str = "md",
         max_wait_time_seconds: int = 500,
         should_clean_pdf: bool = False,
         **kwargs: Any,
@@ -335,7 +335,7 @@ class MathpixPDFLoader(BasePDFLoader):
 
         Args:
             file_path: a file for loading.
-            processed_file_format: a format of the processed file. Default is "mmd".
+            processed_file_format: a format of the processed file. Default is "md".
             max_wait_time_seconds: a maximum time to wait for the response from
              the server. Default is 500.
             should_clean_pdf: a flag to clean the PDF file. Default is False.