Update app.py

app.py

@@ -1,91 +1,112 @@
 import gradio as gr
 from transformers import pipeline
 from PIL import Image
+import fitz  # PyMuPDF for PDF
+import docx
+import pptx
+import openpyxl
+import easyocr
 from fastapi import FastAPI
 from starlette.responses import RedirectResponse
 
-# 🔥 Fix for Pydantic v2 compatibility with Gradio
-import gradio.context
-from pydantic import BaseModel
-if not hasattr(BaseModel, "model_fields"):  # model_fields was renamed from __fields__ in Pydantic v1 → v2
-    BaseModel.model_fields = BaseModel.__fields__
-
-# 🔁 Load Hugging Face Pipelines
+# Initialize models
 summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
 image_captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
+reader = easyocr.Reader(['en', 'fr'])
 
-# 🚀 Create FastAPI App
+# FastAPI app
 app = FastAPI()
 
-def analyze_input(file, question=None):
+# Text extraction functions
+def extract_text_from_pdf(file_path):
+    try:
+        doc = fitz.open(file_path)
+        return "\n".join([page.get_text() for page in doc])
+    except Exception as e:
+        return f"❌ Error reading PDF: {e}"
+
+def extract_text_from_docx(file):
+    try:
+        doc = docx.Document(file)
+        return "\n".join([p.text for p in doc.paragraphs if p.text.strip()])
+    except Exception as e:
+        return f"❌ Error reading DOCX: {e}"
+
+def extract_text_from_pptx(file):
+    try:
+        text = []
+        prs = pptx.Presentation(file)
+        for slide in prs.slides:
+            for shape in slide.shapes:
+                if hasattr(shape, "text"):
+                    text.append(shape.text)
+        return "\n".join(text)
+    except Exception as e:
+        return f"❌ Error reading PPTX: {e}"
+
+def extract_text_from_xlsx(file):
+    try:
+        wb = openpyxl.load_workbook(file)
+        text = []
+        for sheet in wb.sheetnames:
+            ws = wb[sheet]
+            for row in ws.iter_rows(values_only=True):
+                text.append(" ".join(str(cell) for cell in row if cell))
+        return "\n".join(text)
+    except Exception as e:
+        return f"❌ Error reading XLSX: {e}"
+
+def extract_text_from_image(file):
+    try:
+        image = Image.open(file).convert("RGB")
+        return "\n".join([text[1] for text in reader.readtext(np.array(image))])
+    except Exception as e:
+        return f"❌ Error reading image with OCR: {e}"
+
+# Main processing function
+def analyze_input(file):
     if file is None:
         return "Please upload a document or image."
 
     filename = file.name.lower()
+    ext = filename.split('.')[-1]
+
+    if ext in ["jpg", "jpeg", "png"]:
+        caption = image_captioner(Image.open(file))[0]['generated_text']
+        ocr_text = extract_text_from_image(file)
+        return f"📷 Image Caption:\n{caption}\n\n🔍 OCR Text:\n{ocr_text}"
+
+    elif ext == "pdf":
+        text = extract_text_from_pdf(file.name)
+    elif ext == "docx":
+        text = extract_text_from_docx(file)
+    elif ext == "pptx":
+        text = extract_text_from_pptx(file)
+    elif ext == "xlsx":
+        text = extract_text_from_xlsx(file)
+    else:
+        return "Unsupported file type. Please upload PDF, DOCX, PPTX, XLSX, or an image."
 
-    # 🖼️ Image
-    if filename.endswith((".png", ".jpg", ".jpeg")):
-        image = Image.open(file)
-        caption = image_captioner(image)[0]['generated_text']
-        return f"📷 Image Interpretation:\n{caption}"
-
-    # 📄 Document
-    elif filename.endswith((".pdf", ".docx", ".pptx", ".xlsx")):
-        import pdfplumber
-        import docx
-        import pptx
-        import pandas as pd
-
-        try:
-            text = ""
-
-            if filename.endswith(".pdf"):
-                with pdfplumber.open(file) as pdf:
-                    text = "\n".join([page.extract_text() for page in pdf.pages if page.extract_text()])
-
-            elif filename.endswith(".docx"):
-                doc = docx.Document(file)
-                text = "\n".join([p.text for p in doc.paragraphs if p.text.strip()])
-
-            elif filename.endswith(".pptx"):
-                prs = pptx.Presentation(file)
-                for slide in prs.slides:
-                    for shape in slide.shapes:
-                        if hasattr(shape, "text"):
-                            text += shape.text + "\n"
-
-            elif filename.endswith(".xlsx"):
-                df = pd.read_excel(file, sheet_name=None)
-                text = "\n".join([df[sheet].to_string() for sheet in df])
-
-            if not text.strip():
-                return "❌ Could not extract meaningful text from the document."
-
-            summary = summarizer(text[:3000], max_length=200, min_length=30, do_sample=False)
-            return f"📄 Document Summary:\n{summary[0]['summary_text']}"
-
-        except Exception as e:
-            return f"❌ Error processing document: {str(e)}"
+    if not text.strip():
+        return "❌ No text could be extracted from the document."
 
-    else:
-        return "❌ Unsupported file type. Please upload a valid image or document."
+    summary = summarizer(text[:3000], max_length=200, min_length=30, do_sample=False)
+    return f"📄 Document Summary:\n{summary[0]['summary_text']}"
 
-# 🎛️ Gradio UI
+# Gradio Interface
 iface = gr.Interface(
     fn=analyze_input,
     inputs=gr.File(label="Upload Document or Image"),
     outputs=gr.Textbox(label="Result", lines=10),
     title="Document & Image Analysis Web Service",
-    description="Upload a document (PDF, DOCX, PPTX, XLSX) or image to get a summary or caption. CPU-friendly."
+    description="Upload a document (PDF, DOCX, PPTX, XLSX) to get a summary or an image to get a caption. OCR and AI-powered."
 )
 
-# ⌨️ Wrap in Tabbed UI
 demo = gr.TabbedInterface([iface], ["Docs and Images"])
 
-# 🔗 Mount Gradio to FastAPI
+# Mount to FastAPI
 app = gr.mount_gradio_app(app, demo, path="/")
 
-# 🏠 Base redirect
 @app.get("/")
-def home():
+def root():
     return RedirectResponse(url="/")