Add explicit markdown parser (#532)

TileDB-Inc · Sep 25, 2024 · aa10001 · aa10001
1 parent f34ac2c
commit aa10001
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/apis/python/src/tiledb/vector_search/object_readers/directory_reader.py b/apis/python/src/tiledb/vector_search/object_readers/directory_reader.py
@@ -355,6 +355,7 @@ def __init__(
             handlers={
                 "application/pdf": PyMuPDFParser(),
                 "text/plain": TextParser(),
+                "text/markdown": TextParser(),
                 "text/html": BS4HTMLParser(),
                 "application/msword": MsWordParser(),
                 "application/vnd.openxmlformats-officedocument.wordprocessingml.document": (
@@ -385,7 +386,7 @@ def lazy_load(
             mime_type = mimetypes.guess_type(self.uri)[0]
             f = vfs.open(self.uri)
 
-        if mime_type is None:
+        if mime_type is None or mime_type.startswith("text"):
             mime_type = "text/plain"
 
         if mime_type.startswith("image/"):