Update app.py

app.py

@@ -1,83 +1,57 @@
-import gradio as gr
-from transformers import pipeline
-from PIL import Image
-import fitz  # PyMuPDF for PDF
+from fastapi import FastAPI, UploadFile, File
+import fitz  # PyMuPDF
 import docx
-import pptx
 import openpyxl
-import easyocr
-from fastapi import FastAPI
-from starlette.responses import RedirectResponse
+import pptx
+from PIL import Image
+import io
+
+import gradio as gr
+from transformers import pipeline
 
-# Initialize models
+# 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'])
 
-# FastAPI app
 app = FastAPI()
 
-# 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}"
+# -------------------------
+# Document Extraction Utils
+# -------------------------
+def extract_text_from_pdf(file):
+    text = ""
+    with fitz.open(stream=file.read(), filetype="pdf") as doc:
+        for page in doc:
+            text += page.get_text()
+    return text
 
 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}"
+    doc = docx.Document(io.BytesIO(file.read()))
+    return "\n".join([para.text for para in doc.paragraphs if para.text.strip()])
 
 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}"
+    text = []
+    prs = pptx.Presentation(io.BytesIO(file.read()))
+    for slide in prs.slides:
+        for shape in slide.shapes:
+            if hasattr(shape, "text"):
+                text.append(shape.text)
+    return "\n".join(text)
 
 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)
+    wb = openpyxl.load_workbook(io.BytesIO(file.read()))
+    text = []
+    for sheet in wb.sheetnames:
+        ws = wb[sheet]
+        for row in ws.iter_rows(values_only=True):
+            line = " ".join(str(cell) for cell in row if cell)
+            text.append(line)
+    return "\n".join(text)
+
+def summarize_document(file: UploadFile):
+    ext = file.filename.split(".")[-1].lower()
+    if ext == "pdf":
+        text = extract_text_from_pdf(file)
     elif ext == "docx":
         text = extract_text_from_docx(file)
     elif ext == "pptx":
@@ -85,28 +59,53 @@ def analyze_input(file):
     elif ext == "xlsx":
         text = extract_text_from_xlsx(file)
     else:
-        return "Unsupported file type. Please upload PDF, DOCX, PPTX, XLSX, or an image."
+        return "Unsupported file format."
 
     if not text.strip():
-        return "❌ No text could be extracted from the document."
+        return "No extractable text."
 
-    summary = summarizer(text[:3000], max_length=200, min_length=30, do_sample=False)
-    return f"📄 Document Summary:\n{summary[0]['summary_text']}"
-
-# 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) to get a summary or an image to get a caption. OCR and AI-powered."
-)
-
-demo = gr.TabbedInterface([iface], ["Docs and Images"])
-
-# Mount to FastAPI
-app = gr.mount_gradio_app(app, demo, path="/")
+    # Trim large docs
+    text = text[:3000]
+    try:
+        summary = summarizer(text, max_length=150, min_length=30, do_sample=False)
+        return summary[0]["summary_text"]
+    except Exception as e:
+        return f"Summarization error: {e}"
 
+def interpret_image(image):
+    if image is None:
+        return "No image uploaded."
+    try:
+        return image_captioner(image)[0]["generated_text"]
+    except Exception as e:
+        return f"Image captioning error: {e}"
+
+# -------------------------
+# Gradio UI
+# -------------------------
+def run_interface():
+    doc_summary = gr.Interface(
+        fn=summarize_document,
+        inputs=gr.File(label="Upload a Document"),
+        outputs="text",
+        title="📄 Document Summarizer"
+    )
+
+    img_caption = gr.Interface(
+        fn=interpret_image,
+        inputs=gr.Image(type="pil", label="Upload an Image"),
+        outputs="text",
+        title="🖼️ Image Interpreter"
+    )
+
+    gr.TabbedInterface([doc_summary, img_caption], ["Summarize Document", "Caption Image"]).launch()
+
+# -------------------------
+# Run from CLI or FastAPI
+# -------------------------
 @app.get("/")
-def root():
-    return RedirectResponse(url="/")
+def read_root():
+    return {"message": "Gradio running at /docs or use CLI"}
+
+if __name__ == "__main__":
+    run_interface()