Update app.py

app.py

@@ -4,38 +4,77 @@ import os
 import pandas as pd
 from sentence_transformers import SentenceTransformer
 
+# Load model from HF
 model = SentenceTransformer("csAhmad/zoraiz-model")
 
-os.makedirs("temp/extracted", exist_ok=True)
+# Ensure temp directory exists
+EXTRACT_PATH = "temp/extracted"
+os.makedirs(EXTRACT_PATH, exist_ok=True)
 
-def process_zip(zip_file):
-    extract_path = "temp/extracted"
-    os.makedirs(extract_path, exist_ok=True)
 
-    zip_path = zip_file.name  # always works in Spaces
+def process_zip(zip_file):
+    # ---------------------------
+    # 1. Validate input
+    # ---------------------------
+    if zip_file is None:
+        raise gr.Error("Please upload a ZIP file.")
+
+    # reset extraction folder
+    if os.path.exists(EXTRACT_PATH):
+        for f in os.listdir(EXTRACT_PATH):
+            try:
+                os.remove(os.path.join(EXTRACT_PATH, f))
+            except:
+                pass
+
+    os.makedirs(EXTRACT_PATH, exist_ok=True)
+
+    zip_path = zip_file.name
+
+    # ---------------------------
+    # 2. Extract ZIP safely
+    # ---------------------------
+    try:
+        with zipfile.ZipFile(zip_path, "r") as zip_ref:
+            zip_ref.extractall(EXTRACT_PATH)
+    except zipfile.BadZipFile:
+        raise gr.Error("Invalid ZIP file uploaded.")
+
+    # ---------------------------
+    # 3. Process files
+    # ---------------------------
+    results = []
 
-    # Extract ZIP
-    with zipfile.ZipFile(zip_path, 'r') as zip_ref:
-        zip_ref.extractall(extract_path)
+    for root, dirs, files in os.walk(EXTRACT_PATH):
+        for file in files:
+            file_path = os.path.join(root, file)
 
-    results = []
+            # only process text files
+            if file.lower().endswith(".txt"):
+                with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
+                    text = f.read()
 
-    # Example: process txt files
-    for file in os.listdir(extract_path):
-        if file.endswith(".txt"):
-            file_path = os.path.join(extract_path, file)
+                if not text.strip():
+                    continue
 
-            with open(file_path, "r", encoding="utf-8") as f:
-                text = f.read()
+                emb = model.encode(text)
 
-            emb = model.encode(text)
+                results.append({
+                    "file": file,
+                    "text_length": len(text),
+                    "embedding_dim": len(emb),
+                    "preview_embedding": str(emb[:10])
+                })
 
-            results.append({
-                "file": file,
-                "embedding_dim": len(emb),
-                "first_10_values": str(emb[:10])
-            })
+    # ---------------------------
+    # 4. Handle empty results
+    # ---------------------------
+    if len(results) == 0:
+        raise gr.Error("No valid .txt files found inside ZIP.")
 
+    # ---------------------------
+    # 5. Create Excel file
+    # ---------------------------
     df = pd.DataFrame(results)
 
     output_file = "output.xlsx"
@@ -44,12 +83,15 @@ def process_zip(zip_file):
     return output_file
 
 
+# ---------------------------
+# 6. Gradio UI
+# ---------------------------
 demo = gr.Interface(
     fn=process_zip,
     inputs=gr.File(file_types=[".zip"]),
     outputs=gr.File(label="Download Excel"),
-    title="ZIP to Excel Processor",
-    description="Upload ZIP → Extract files → Generate embeddings → Export Excel"
+    title="ZIP → Embeddings → Excel Generator",
+    description="Upload a ZIP containing .txt files. It will generate embeddings using SentenceTransformer and export to Excel."
 )
 
 demo.launch()