Update app.py

app.py

@@ -1,4 +1,4 @@
-import gradio as gr
+"""import gradio as gr
 import uvicorn
 import numpy as np
 import fitz  # PyMuPDF
@@ -111,6 +111,137 @@ with gr.Blocks() as demo:
 # ✅ Mount Gradio with FastAPI
 app = gr.mount_gradio_app(app, demo, path="/")
 
+@app.get("/")
+def home():
+    return RedirectResponse(url="/")
+
+# ✅ Run FastAPI + Gradio
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)
+""" import gradio as gr
+import uvicorn
+import numpy as np
+import fitz  # PyMuPDF
+import tika
+import torch
+from fastapi import FastAPI
+from transformers import pipeline
+from PIL import Image
+from io import BytesIO
+from starlette.responses import RedirectResponse
+from tika import parser
+from openpyxl import load_workbook
+
+# Initialize Tika for DOCX & PPTX parsing
+tika.initVM()
+
+# Initialize FastAPI
+app = FastAPI()
+
+# Load models
+device = "cuda" if torch.cuda.is_available() else "cpu"
+qa_pipeline = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", device=device)
+image_captioning_pipeline = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+
+ALLOWED_EXTENSIONS = {"pdf", "docx", "pptx", "xlsx"}
+
+# ✅ Function to Validate File Type
+def validate_file_type(file):
+    if file is None:
+        return "❌ No file uploaded!"
+    if isinstance(file, str):  # Text-based input (NamedString)
+        return None
+    if hasattr(file, "name"):
+        ext = file.name.split(".")[-1].lower()
+        if ext not in ALLOWED_EXTENSIONS:
+            return f"❌ Unsupported file format: {ext}"
+        return None
+    return "❌ Invalid file format!"
+
+# ✅ Extract Text from PDF
+def extract_text_from_pdf(file):
+    try:
+        doc = fitz.open(stream=file, filetype="pdf")
+        return "\n".join([page.get_text() for page in doc])
+    except Exception:
+        return None
+
+# ✅ Extract Text from DOCX & PPTX using Tika
+def extract_text_with_tika(file):
+    try:
+        return parser.from_buffer(file)["content"]
+    except Exception:
+        return None
+
+# ✅ Extract Text from Excel
+def extract_text_from_excel(file):
+    try:
+        wb = load_workbook(BytesIO(file), data_only=True)
+        text = []
+        for sheet in wb.worksheets:
+            for row in sheet.iter_rows(values_only=True):
+                text.append(" ".join(str(cell) for cell in row if cell))
+        return "\n".join(text)
+    except Exception:
+        return None
+
+# ✅ Truncate Long Text for Model
+def truncate_text(text, max_length=2048):
+    return text[:max_length] if len(text) > max_length else text
+
+# ✅ Answer Questions from Image or Document
+def answer_question(file, question: str):
+    # Image Processing (Gradio sends images as NumPy arrays)
+    if isinstance(file, np.ndarray):  
+        image = Image.fromarray(file)
+        caption = image_captioning_pipeline(image)[0]['generated_text']
+        response = qa_pipeline(f"Question: {question}\nContext: {caption}")
+        return response[0]["generated_text"]
+
+    # Validate File
+    validation_error = validate_file_type(file)
+    if validation_error:
+        return validation_error
+
+    # ✅ Read File Bytes Properly
+    file_ext = file.name.split(".")[-1].lower() if hasattr(file, "name") else None
+    file_bytes = file.read() if hasattr(file, "read") else None
+    if not file_bytes:
+        return "❌ Could not read file content!"
+
+    # Extract Text from Supported Documents
+    text = None
+    if file_ext == "pdf":
+        text = extract_text_from_pdf(file_bytes)
+    elif file_ext in ["docx", "pptx"]:
+        text = extract_text_with_tika(file_bytes)
+    elif file_ext == "xlsx":
+        text = extract_text_from_excel(file_bytes)
+
+    if not text:
+        return "⚠️ No text extracted from the document."
+
+    truncated_text = truncate_text(text)
+    response = qa_pipeline(f"Question: {question}\nContext: {truncated_text}")
+
+    return response[0]["generated_text"]
+
+# ✅ Gradio Interface (Unified for Images & Documents)
+with gr.Blocks() as demo:
+    gr.Markdown("## 📄 AI-Powered Document & Image QA")
+
+    with gr.Row():
+        file_input = gr.File(label="Upload Document / Image")
+        question_input = gr.Textbox(label="Ask a Question", placeholder="What is this document about?")
+    
+    answer_output = gr.Textbox(label="Answer")
+    
+    submit_btn = gr.Button("Get Answer")
+    submit_btn.click(answer_question, inputs=[file_input, question_input], outputs=answer_output)
+
+# ✅ Mount Gradio with FastAPI
+app = gr.mount_gradio_app(app, demo, path="/")
+
 @app.get("/")
 def home():
     return RedirectResponse(url="/")