Update app.py

app.py

@@ -1,43 +1,49 @@
 from fastapi import FastAPI
 from fastapi.responses import RedirectResponse
+from transformers import pipeline
+from PIL import Image
 import fitz  # PyMuPDF
 import docx
-import openpyxl
 import pptx
+import openpyxl
 import io
-from PIL import Image
+
 import gradio as gr
-from transformers import pipeline
 
-# Load models
+# Initialize models
 summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
 image_captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
 
+# FastAPI app
 app = FastAPI()
 
 # -------------------------
-# File Extraction Helpers
+# Helper Functions
 # -------------------------
-def extract_text_from_pdf(file_obj):
+
+def extract_text_from_pdf(upload):
     try:
-        file_obj.seek(0)
-        with fitz.open(stream=file_obj.read(), filetype="pdf") as doc:
+        file_bytes = upload.read()
+        stream = io.BytesIO(file_bytes)
+        with fitz.open(stream=stream, filetype="pdf") as doc:
             return "\n".join([page.get_text() for page in doc])
     except Exception as e:
         return f"❌ PDF extraction error: {e}"
 
-def extract_text_from_docx(file_obj):
+def extract_text_from_docx(upload):
     try:
-        file_obj.seek(0)
-        doc = docx.Document(io.BytesIO(file_obj.read()))
+        file_bytes = upload.read()
+        stream = io.BytesIO(file_bytes)
+        doc = docx.Document(stream)
         return "\n".join(p.text for p in doc.paragraphs if p.text.strip())
     except Exception as e:
         return f"❌ DOCX extraction error: {e}"
 
-def extract_text_from_pptx(file_obj):
+def extract_text_from_pptx(upload):
     try:
-        file_obj.seek(0)
-        prs = pptx.Presentation(io.BytesIO(file_obj.read()))
+        file_bytes = upload.read()
+        stream = io.BytesIO(file_bytes)
+        prs = pptx.Presentation(stream)
         text = []
         for slide in prs.slides:
             for shape in slide.shapes:
@@ -47,10 +53,11 @@ def extract_text_from_pptx(file_obj):
     except Exception as e:
         return f"❌ PPTX extraction error: {e}"
 
-def extract_text_from_xlsx(file_obj):
+def extract_text_from_xlsx(upload):
     try:
-        file_obj.seek(0)
-        wb = openpyxl.load_workbook(io.BytesIO(file_obj.read()))
+        file_bytes = upload.read()
+        stream = io.BytesIO(file_bytes)
+        wb = openpyxl.load_workbook(stream)
         text = []
         for sheet in wb.sheetnames:
             ws = wb[sheet]
@@ -61,23 +68,29 @@ def extract_text_from_xlsx(file_obj):
         return f"❌ XLSX extraction error: {e}"
 
 # -------------------------
-# Main Logic
+# Core Functions
 # -------------------------
-def summarize_document(file):
-    name = getattr(file, "name", "").lower()
-    if name.endswith(".pdf"):
-        text = extract_text_from_pdf(file)
-    elif name.endswith(".docx"):
-        text = extract_text_from_docx(file)
-    elif name.endswith(".pptx"):
-        text = extract_text_from_pptx(file)
-    elif name.endswith(".xlsx"):
-        text = extract_text_from_xlsx(file)
+
+def summarize_document(upload):
+    if not upload:
+        return "⚠️ No file uploaded."
+
+    ext = upload.name.lower()
+    upload.seek(0)
+
+    if ext.endswith(".pdf"):
+        text = extract_text_from_pdf(upload)
+    elif ext.endswith(".docx"):
+        text = extract_text_from_docx(upload)
+    elif ext.endswith(".pptx"):
+        text = extract_text_from_pptx(upload)
+    elif ext.endswith(".xlsx"):
+        text = extract_text_from_xlsx(upload)
     else:
-        return "❌ Unsupported file format."
+        return "❌ Unsupported file type."
 
-    if not text or not isinstance(text, str) or not text.strip():
-        return "❗ No extractable text found."
+    if not text or not text.strip() or text.startswith("❌"):
+        return text if text.startswith("❌") else "❗ No extractable text found."
 
     try:
         summary = summarizer(text[:3000], max_length=150, min_length=30, do_sample=False)
@@ -86,34 +99,34 @@ def summarize_document(file):
         return f"⚠️ Summarization error: {e}"
 
 def interpret_image(image):
+    if not image:
+        return "⚠️ No image uploaded."
     try:
         return f"🖼️ Caption:\n{image_captioner(image)[0]['generated_text']}"
     except Exception as e:
         return f"⚠️ Image captioning error: {e}"
 
 # -------------------------
-# Gradio Interfaces
+# Gradio Interface
 # -------------------------
-doc_summary = gr.Interface(
+
+doc_ui = gr.Interface(
     fn=summarize_document,
-    inputs=gr.File(label="Upload a Document"),
-    outputs="text",
+    inputs=gr.File(label="Upload a Document (PDF, DOCX, PPTX, XLSX)"),
+    outputs=gr.Textbox(label="Summary"),
     title="📄 Document Summarizer"
 )
 
-img_caption = gr.Interface(
+img_ui = gr.Interface(
     fn=interpret_image,
     inputs=gr.Image(type="pil", label="Upload an Image"),
-    outputs="text",
+    outputs=gr.Textbox(label="Caption"),
     title="🖼️ Image Interpreter"
 )
 
-# -------------------------
-# Launch with FastAPI
-# -------------------------
-demo = gr.TabbedInterface([doc_summary, img_caption], ["Document Summary", "Image Captioning"])
+demo = gr.TabbedInterface([doc_ui, img_ui], ["Document Summarization", "Image Captioning"])
 app = gr.mount_gradio_app(app, demo, path="/")
 
 @app.get("/")
-def home():
+def redirect_to_ui():
     return RedirectResponse(url="/")