Update app.py

app.py

@@ -18,7 +18,7 @@ app = FastAPI()
 # -------------------------
 # Extraction Functions
 # -------------------------
-def extract_text_from_pdf(file_bytes):
+"""def extract_text_from_pdf(file_bytes):
     try:
         with fitz.open(stream=file_bytes, filetype="pdf") as doc:
             return "\n".join([page.get_text() for page in doc])
@@ -56,7 +56,44 @@ def extract_text_from_xlsx(file_bytes):
         return "\n".join(text)
     except Exception as e:
         return f"❌ XLSX extraction error: {e}"
+"""
+def extract_text_from_pdf(pdf_file):
+    text = []
+    try:
+        with fitz.open(pdf_file) as doc:
+            for page in doc:
+                text.append(page.get_text("text"))
+    except Exception as e:
+        return f"Error reading PDF: {e}"
+    return "\n".join(text)
+
+def extract_text_from_docx(docx_file):
+    doc = docx.Document(docx_file)
+    return "\n".join([p.text for p in doc.paragraphs if p.text.strip()])
+
+def extract_text_from_pptx(pptx_file):
+    text = []
+    try:
+        presentation = pptx.Presentation(pptx_file)
+        for slide in presentation.slides:
+            for shape in slide.shapes:
+                if hasattr(shape, "text"):
+                    text.append(shape.text)
+    except Exception as e:
+        return f"Error reading PPTX: {e}"
+    return "\n".join(text)
 
+def extract_text_from_xlsx(xlsx_file):
+    text = []
+    try:
+        wb = openpyxl.load_workbook(xlsx_file)
+        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))
+    except Exception as e:
+        return f"Error reading XLSX: {e}"
+    return "\n".join(text)
 # -------------------------
 # Main Logic
 # -------------------------