Update app.py

app.py

@@ -11,7 +11,6 @@ from transformers import pipeline
 import gradio as gr
 from fastapi.responses import RedirectResponse
 import numpy as np
-import easyocr
 
 # Initialize FastAPI
 print("🚀 FastAPI server is starting...")
@@ -30,10 +29,6 @@ weights = FasterRCNN_ResNet50_FPN_Weights.DEFAULT
 model = fasterrcnn_resnet50_fpn(weights=weights)
 model.eval()
 
-# Initialize OCR Model (Lazy Load)
-print("🔄 Initializing OCR Model...")
-reader = easyocr.Reader(["en"], gpu=True)
-
 # Image Transformations
 transform = transforms.Compose([
     transforms.ToTensor()
@@ -103,16 +98,6 @@ def extract_text_from_excel(excel_file):
     except Exception as e:
         return f"❌ Error reading Excel: {str(e)}"
 
-def extract_text_from_image(image_file):
-    print("🖼️ Extracting text from image...")
-    image = Image.open(image_file).convert("RGB")
-    if np.array(image).std() < 10:
-        print("⚠️ Low contrast detected. No meaningful content.")
-        return "⚠️ No meaningful content detected in the image."
-    result = reader.readtext(np.array(image))
-    print("✅ Image text extraction completed.")
-    return " ".join([res[1] for res in result]) if result else "⚠️ No text found."
-
 def answer_question_from_document(file, question):
     print("📂 Processing document for QA...")
     validation_error = validate_file_type(file)
@@ -135,23 +120,11 @@ def answer_question_from_document(file, question):
     print("✅ AI response generated.")
     return response[0]["generated_text"]
 
-def answer_question_from_image(image, question):
-    print("🖼️ Processing image for QA...")
-    image_text = extract_text_from_image(image)
-    if not image_text:
-        return "⚠️ No meaningful content detected in the image."
-    truncated_text = truncate_text(image_text)
-    print("🤖 Generating response...")
-    response = qa_pipeline(f"Question: {question}\nContext: {truncated_text}")
-    print("✅ AI response generated.")
-    return response[0]["generated_text"]
-
 print("✅ Models loaded successfully.")
 
 doc_interface = gr.Interface(fn=answer_question_from_document, inputs=[gr.File(), gr.Textbox()], outputs="text")
-img_interface = gr.Interface(fn=answer_question_from_image, inputs=[gr.Image(), gr.Textbox()], outputs="text")
 
-demo = gr.TabbedInterface([doc_interface, img_interface], ["Document QA", "Image QA"])
+demo = gr.TabbedInterface([doc_interface], ["Document QA"])
 app = gr.mount_gradio_app(app, demo, path="/")
 
 @app.get("/")