Update app.py

app.py

@@ -3,63 +3,64 @@ import fitz  # PyMuPDF for PDF parsing
 from tika import parser  # Apache Tika for document parsing
 import openpyxl
 from pptx import Presentation
+import torch
 from PIL import Image
 from transformers import pipeline
 import gradio as gr
-from fastapi.responses import RedirectResponse
 import numpy as np
 import easyocr
 
-# Initialize FastAPI
+# Initialize FastAPI (not needed for HF Spaces, but kept for flexibility)
 app = FastAPI()
 
 print(f"🔄 Loading models")
 
-doc_qa_pipeline = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+doc_qa_pipeline = pipeline("text2text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", device=-1)
 image_captioning_pipeline = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
-print("Models loaded")
+print("✅ Models loaded")
 
-# Initialize OCR Model (Lazy Load)
-reader = easyocr.Reader(["en"], gpu=True)
+# Initialize OCR Model (CPU Mode)
+reader = easyocr.Reader(["en"], gpu=False)
 
 # Allowed File Extensions
 ALLOWED_EXTENSIONS = {"pdf", "docx", "pptx", "xlsx"}
 
-def validate_file_type(file: UploadFile):
+def validate_file_type(file):
     ext = file.filename.split(".")[-1].lower()
     print(f"🔍 Validating file type: {ext}")
     if ext not in ALLOWED_EXTENSIONS:
         return f"❌ Unsupported file format: {ext}"
     return None
 
+# Function to truncate text to 450 tokens
 def truncate_text(text, max_tokens=450):
     words = text.split()
     truncated = " ".join(words[:max_tokens])
     print(f"✂️ Truncated text to {max_tokens} tokens.")
     return truncated
 
-def extract_text_from_pdf(pdf_file: UploadFile):
+# Document Text Extraction Functions
+def extract_text_from_pdf(pdf_bytes):
     try:
-        print("📝 Extracting text from PDF...")
-        pdf_bytes = pdf_file.file.read()
+        print("📄 Extracting text from PDF...")
         doc = fitz.open(stream=pdf_bytes, filetype="pdf")
         text = "\n".join([page.get_text("text") for page in doc])
         return text if text else "⚠️ No text found."
     except Exception as e:
         return f"❌ Error reading PDF: {str(e)}"
 
-def extract_text_with_tika(file: UploadFile):
+def extract_text_with_tika(file_bytes):
     try:
         print("📝 Extracting text with Tika...")
-        parsed = parser.from_buffer(file.file.read())
+        parsed = parser.from_buffer(file_bytes)
         return parsed.get("content", "⚠️ No text found.").strip()
     except Exception as e:
         return f"❌ Error reading document: {str(e)}"
 
-def extract_text_from_excel(excel_file: UploadFile):
+def extract_text_from_excel(excel_bytes):
     try:
-        print("📝 Extracting text from Excel...")
-        wb = openpyxl.load_workbook(excel_file.file, read_only=True)
+        print("📊 Extracting text from Excel...")
+        wb = openpyxl.load_workbook(excel_bytes, read_only=True)
         text = []
         for sheet in wb.worksheets:
             for row in sheet.iter_rows(values_only=True):
@@ -75,13 +76,14 @@ def answer_question_from_document(file: UploadFile, question: str):
         return validation_error
     
     file_ext = file.filename.split(".")[-1].lower()
-    
+    file_bytes = file.file.read()
+
     if file_ext == "pdf":
-        text = extract_text_from_pdf(file)
+        text = extract_text_from_pdf(file_bytes)
     elif file_ext in ["docx", "pptx"]:
-        text = extract_text_with_tika(file)
+        text = extract_text_with_tika(file_bytes)
     elif file_ext == "xlsx":
-        text = extract_text_from_excel(file)
+        text = extract_text_from_excel(file_bytes)
     else:
         return "❌ Unsupported file format!"
     
@@ -94,13 +96,13 @@ def answer_question_from_document(file: UploadFile, question: str):
     
     return response[0]["generated_text"]
 
-def answer_question_from_image(image, question: str):
+def answer_question_from_image(image, question):
     try:
-        print("🎨 Converting image for processing...")
-        if isinstance(image, np.ndarray):
-            image = Image.fromarray(image)  # Convert NumPy array to PIL Image
+        print("🖼️ Processing image for QA...")
+        if isinstance(image, np.ndarray):  # If it's a NumPy array from Gradio
+            image = Image.fromarray(image)  # Convert to PIL Image
         
-        print("🎨 Generating caption for image...")
+        print("🖼️ Generating caption for image...")
         caption = image_captioning_pipeline(image)[0]['generated_text']
 
         print("🤖 Answering question based on caption...")
@@ -110,6 +112,7 @@ def answer_question_from_image(image, question: str):
     except Exception as e:
         return f"❌ Error processing image: {str(e)}"
 
+# 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")],
@@ -119,24 +122,13 @@ doc_interface = gr.Interface(
 
 img_interface = gr.Interface(
     fn=answer_question_from_image,
-    inputs=[gr.Image(label="🎨 Upload Image"), gr.Textbox(label="💬 Ask a Question")],
+    inputs=[gr.Image(label="🖼️ Upload Image"), gr.Textbox(label="💬 Ask a Question")],
     outputs="text",
-    title="🎨 AI Image Question Answering"
+    title="🖼️ AI Image Question Answering"
 )
 
-# Use Gradio Blocks (instead of TabbedInterface)
-with gr.Blocks() as demo:
-    gr.TabbedLayout(
-        [doc_interface, img_interface],
-        ["📄 Document QA", "🎨 Image QA"]
-    )
-
-# Mount Gradio to FastAPI properly
-from gradio.routes import App as GradioApp
-gradio_app = GradioApp.create_app(demo)
-app.mount("/", gradio_app)
-
-# Redirect FastAPI root to Gradio UI
-@app.get("/")
-def home():
-    return RedirectResponse(url="/")
+# Launch Gradio
+app = gr.TabbedInterface([doc_interface, img_interface], ["📄 Document QA", "🖼️ Image QA"])
+
+if __name__ == "__main__":
+    app.launch(share=True)  # For Hugging Face Spaces