Update app.py

app.py

@@ -4,24 +4,54 @@ from retriever import get_relevant_passages
 from reranker import rerank
 
 # Load and clean CSV
-df = pd.read_csv("assesments.csv")
-
 def clean_df(df):
     df = df.copy()
-    df["url"] = "https://www.shl.com" + df.iloc[:, 1].astype(str)
+    
+    # Ensure clean URLs
+    # Check if the second column contains URLs or just IDs
+    second_col = df.iloc[:, 1].astype(str)
+    if second_col.str.contains('http').any() or second_col.str.contains('www').any():
+        df["url"] = second_col  # Already has full URLs
+    else:
+        # Create full URLs from IDs
+        df["url"] = "https://www.shl.com/" + second_col.str.replace(r'^[\s/]*', '', regex=True)
+    
     df["remote_support"] = df.iloc[:, 2].map(lambda x: "Yes" if x == "T" else "No")
     df["adaptive_support"] = df.iloc[:, 3].map(lambda x: "Yes" if x == "T" else "No")
+    
+    # Handle test_type with error checking
     df["test_type"] = df.iloc[:, 4].astype(str).str.split("\\n")
+    
     df["description"] = df.iloc[:, 5]
-    df["duration"] = df.iloc[:, 8].astype(str).str.extract(r'(\d+)').astype(float)
+    
+    # Extract duration with error handling
+    df["duration"] = pd.to_numeric(
+        df.iloc[:, 8].astype(str).str.extract(r'(\d+)')[0], 
+        errors='coerce'
+    )
+    
     return df[["url", "adaptive_support", "remote_support", "description", "duration", "test_type"]]
 
-df_clean = clean_df(df)
+try:
+    df = pd.read_csv("assesments.csv")
+    df_clean = clean_df(df)
+except Exception as e:
+    print(f"Error loading or cleaning data: {e}")
+    # Create an empty DataFrame with required columns as fallback
+    df_clean = pd.DataFrame(columns=["url", "adaptive_support", "remote_support", 
+                                     "description", "duration", "test_type"])
 
 def recommend(query):
-    top_k_df = get_relevant_passages(query, df_clean, top_k=20)
-    candidates = top_k_df.to_dict(orient="records")
-    return rerank(query, candidates)
+    if not query.strip():
+        return {"error": "Please enter a job description"}
+    
+    try:
+        top_k_df = get_relevant_passages(query, df_clean, top_k=20)
+        candidates = top_k_df.to_dict(orient="records")
+        result = rerank(query, candidates)
+        return result
+    except Exception as e:
+        return {"error": f"Error processing request: {str(e)}"}
 
 iface = gr.Interface(
     fn=recommend,
@@ -32,4 +62,4 @@ iface = gr.Interface(
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch()