Update app.py

app.py

@@ -14,6 +14,7 @@ import numpy as np
 import easyocr
 
 # Initialize FastAPI
+print("🚀 FastAPI server is starting...")
 app = FastAPI()
 
 # Load AI Model for Question Answering (DeepSeek-V2-Chat)
@@ -21,18 +22,16 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Preload Hugging Face model
 print(f"🔄 Loading models")
+qa_pipeline = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", device=-1)
 
-qa_pipeline =  pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", device=-1)
 # Load Pretrained Object Detection Model (Torchvision)
 from torchvision.models.detection import FasterRCNN_ResNet50_FPN_Weights
 weights = FasterRCNN_ResNet50_FPN_Weights.DEFAULT
 model = fasterrcnn_resnet50_fpn(weights=weights)
 model.eval()
-# Load Pretrained Object Detection Model (if needed)
-model = fasterrcnn_resnet50_fpn(pretrained=True)
-model.eval()
 
 # Initialize OCR Model (Lazy Load)
+print("🔄 Initializing OCR Model...")
 reader = easyocr.Reader(["en"], gpu=True)
 
 # Image Transformations
@@ -63,6 +62,7 @@ def extract_text_from_pdf(pdf_file):
         print("📄 Extracting text from PDF...")
         doc = fitz.open(pdf_file)
         text = "\n".join([page.get_text("text") for page in doc])
+        print("✅ PDF text extraction completed.")
         return text if text else "⚠️ No text found."
     except Exception as e:
         return f"❌ Error reading PDF: {str(e)}"
@@ -71,6 +71,7 @@ def extract_text_with_tika(file):
     try:
         print("📝 Extracting text with Tika...")
         parsed = parser.from_buffer(file)
+        print("✅ Tika text extraction completed.")
         return parsed.get("content", "⚠️ No text found.").strip()
     except Exception as e:
         return f"❌ Error reading document: {str(e)}"
@@ -84,6 +85,7 @@ def extract_text_from_pptx(pptx_file):
             for shape in slide.shapes:
                 if hasattr(shape, "text"):
                     text.append(shape.text)
+        print("✅ PPTX text extraction completed.")
         return "\n".join(text) if text else "⚠️ No text found."
     except Exception as e:
         return f"❌ Error reading PPTX: {str(e)}"
@@ -96,6 +98,7 @@ def extract_text_from_excel(excel_file):
         for sheet in wb.worksheets:
             for row in sheet.iter_rows(values_only=True):
                 text.append(" ".join(map(str, row)))
+        print("✅ Excel text extraction completed.")
         return "\n".join(text) if text else "⚠️ No text found."
     except Exception as e:
         return f"❌ Error reading Excel: {str(e)}"
@@ -103,19 +106,18 @@ def extract_text_from_excel(excel_file):
 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:  # Low contrast = likely empty
+    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."
 
-# Function to answer questions based on document content
 def answer_question_from_document(file, question):
     print("📂 Processing document for QA...")
     validation_error = validate_file_type(file)
     if validation_error:
         return validation_error
-    
     file_ext = file.name.split(".")[-1].lower()
     if file_ext == "pdf":
         text = extract_text_from_pdf(file)
@@ -125,14 +127,12 @@ def answer_question_from_document(file, question):
         text = extract_text_from_excel(file)
     else:
         return "❌ Unsupported file format!"
-    
     if not text:
         return "⚠️ No text extracted from the document."
-    
     truncated_text = truncate_text(text)
     print("🤖 Generating response...")
     response = qa_pipeline(f"Question: {question}\nContext: {truncated_text}")
-    
+    print("✅ AI response generated.")
     return response[0]["generated_text"]
 
 def answer_question_from_image(image, question):
@@ -140,30 +140,18 @@ def answer_question_from_image(image, question):
     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"]
 
-# Gradio UI for Document & Image QA
-doc_interface = gr.Interface(
-    fn=answer_question_from_document,
-    inputs=[gr.File(label="📂 Upload Document"), gr.Textbox(label="💬 Ask a Question")],
-    outputs="text",
-    title="📄 AI Document Question Answering"
-)
-
-img_interface = gr.Interface(
-    fn=answer_question_from_image,
-    inputs=[gr.Image(label="🖼️ Upload Image"), gr.Textbox(label="💬 Ask a Question")],
-    outputs="text",
-    title="🖼️ AI Image Question Answering"
-)
-
-# Mount Gradio Interfaces
-demo = gr.TabbedInterface([doc_interface, img_interface], ["📄 Document QA", "🖼️ Image QA"])
+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"])
 app = gr.mount_gradio_app(app, demo, path="/")
 
 @app.get("/")