Fix: video file suffix (#10740)

### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

api/utils/file_utils.py

@@ -173,7 +173,7 @@ def filename_type(filename):
     if re.match(r".*\.(wav|flac|ape|alac|wavpack|wv|mp3|aac|ogg|vorbis|opus)$", filename):
         return FileType.AURAL.value
 
-    if re.match(r".*\.(jpg|jpeg|png|tif|gif|pcx|tga|exif|fpx|svg|psd|cdr|pcd|dxf|ufo|eps|ai|raw|WMF|webp|avif|apng|icon|ico|mpg|mpeg|avi|rm|rmvb|mov|wmv|asf|dat|asx|wvx|mpe|mpa|mp4)$", filename):
+    if re.match(r".*\.(jpg|jpeg|png|tif|gif|pcx|tga|exif|fpx|svg|psd|cdr|pcd|dxf|ufo|eps|ai|raw|WMF|webp|avif|apng|icon|ico|mpg|mpeg|avi|rm|rmvb|mov|wmv|asf|dat|asx|wvx|mpe|mpa|mp4|avi|mkv)$", filename):
         return FileType.VISUAL.value
 
     return FileType.OTHER.value

rag/app/picture.py

@@ -29,7 +29,7 @@ from rag.utils import clean_markdown_block
 ocr = OCR()
 
 # Gemini supported MIME types
-VIDEO_EXTS = [".mp4", ".mov", ".avi", ".flv", ".mpeg", ".mpg", ".webm", ".wmv", ".3gp", ".3gpp"]
+VIDEO_EXTS = [".mp4", ".mov", ".avi", ".flv", ".mpeg", ".mpg", ".webm", ".wmv", ".3gp", ".3gpp", ".mkv"]
 
 
 def chunk(filename, binary, tenant_id, lang, callback=None, **kwargs):

rag/flow/parser/parser.py

@@ -144,7 +144,8 @@ class ParserParam(ProcessParamBase):
             "video": {
                 "suffix":[
                     "mp4",
-                    "av"
+                    "avi",
+                    "mkv"
                 ],
                 "output_format": "json",
             },