fix parsing, add ContentType to Cloudflare video upload

app.py

@@ -1,4 +1,5 @@
 from document_to_gloss import DocumentToASLConverter
+from document_parsing import DocumentParser
 from vectorizer import Vectorizer
 from video_gen import create_multi_stitched_video
 import gradio as gr
@@ -41,6 +42,7 @@ outputs = [
     gr.HTML(label="Download Link")
 ]
 
+parser = DocumentParser()
 asl_converter = DocumentToASLConverter()
 vectorizer = Vectorizer()
 session = boto3.session.Session()
@@ -278,6 +280,7 @@ def predict_unified(input_data):
                 "message": "Please provide text or upload a document"
             }, None
         
+        print("Input", input_data)
         # Use the unified processing function
         result = parse_vectorize_and_search_unified_sync(input_data)
         
@@ -319,28 +322,9 @@ def predict_unified(input_data):
 def create_interface():
     """Create and configure the Gradio interface"""
     
-    def process_inputs(text, file):
-        """Process text or file input and return results"""
-        # Determine which input to use
-        if text and text.strip():
-            # Use text input
-            input_data = text.strip()
-        elif file is not None:
-            # Use file input
-            input_data = file
-        else:
-            # No input provided
-            return {
-                "status": "error",
-                "message": "Please provide either text or upload a file"
-            }, None
-        
-        # Process using the unified function
-        return predict_unified(input_data)
-    
     # Create the interface
     interface = gr.Interface(
-        fn=process_inputs,
+        fn=predict,
         inputs=[
             gr.Textbox(
                 label="Enter text to convert to ASL",
@@ -376,7 +360,7 @@ def predict(text, file):
         input_data = text.strip()
     elif file is not None:
         # Use file input
-        input_data = file
+        input_data = parser.extract_text(file)
     else:
         # No input provided
         return {