Uploaded code files

app.py

@@ -41,7 +41,7 @@ def extract_text(image, query):
 def post_process_text(text):
     # Remove extra whitespace
     text = re.sub(r'\s+', ' ', text).strip()
-    # Remove repeated phrases (which sometimes occur in multi-pass extraction)
+    # Remove repeated phrases
     phrases = text.split('. ')
     unique_phrases = list(dict.fromkeys(phrases))
     text = '. '.join(unique_phrases)
@@ -77,8 +77,8 @@ def main_fun(image, keyword):
 iface = gr.Interface(
     fn=main_fun,
     inputs=[
-        gr.Image(type="pil", label="Upload an Image").
-        gr.Textbox(label="Enter search term")
+        gr.Image(type="pil", label="Upload an Image"),
+        gr.Textbox(label="Enter search term", placeholder="Search")
     ],
     outputs=[
         gr.Textbox(label="Extracted Text"),

requirements.txt

@@ -3,7 +3,6 @@ byaldi
 qwen-vl-utils
 numpy==1.24.4
 Pillow==10.3.0
-Requests==2.31.0
 torch
 torchvision
 git+https://github.com/huggingface/transformers.git