Update app.py

app.py

@@ -7,28 +7,30 @@ from reranker import rerank
 def clean_df(df):
     df = df.copy()
     
-    # Extract the assessment name from the URL
-    df["assessment_name"] = df["Pre-packaged Job Solutions"].str.split('/').str[-2].str.replace('-', ' ').str.title()
+    # 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)
     
-    # Create proper URLs
-    df["url"] = "https://www.shl.com" + df["Pre-packaged Job Solutions"]
+    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")
     
-    # Convert T/F to Yes/No
-    df["remote_support"] = df["Remote Testing"].map(lambda x: "Yes" if x == "T" else "No")
-    df["adaptive_support"] = df["Adaptive/IRT"].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")
     
-    # Handle test_type properly - it's already in list format as a string
-    df["test_type"] = df["Test Type"]
+    df["description"] = df.iloc[:, 5]
     
-    # Keep the description as is
-    df["description"] = df["Description"]
+    # Extract duration with error handling
+    df["duration"] = pd.to_numeric(
+        df.iloc[:, 8].astype(str).str.extract(r'(\d+)')[0], 
+        errors='coerce'
+    )
     
-    # Extract duration with proper handling
-    df["duration"] = df["Assessment_Length"].str.extract(r'(\d+)').fillna("N/A")
-    
-    # Select only the columns we need
-    return df[["assessment_name", "url", "remote_support", "adaptive_support", 
-               "description", "duration", "test_type"]]
+    return df[["url", "adaptive_support", "remote_support", "description", "duration", "test_type"]]
 
 try:
     df = pd.read_csv("assesments.csv")
@@ -67,19 +69,10 @@ def recommend(query):
     try:
         # Print some debug info
         print(f"Processing query: {query[:50]}...")
-        print(f"DataFrame shape: {df_clean.shape}")
-        print(f"DataFrame columns: {df_clean.columns.tolist()}")
-        
-        if df_clean.empty:
-            return {"error": "No assessment data available"}
-        
-        # Print a sample row for debugging
-        print("Sample row:")
-        print(df_clean.iloc[0].to_dict())
         
         top_k_df = get_relevant_passages(query, df_clean, top_k=20)
         
-        # Debug: Check retrieved data
+        # Debug: Check URLs in retrieved data
         print(f"Retrieved {len(top_k_df)} assessments")
         if not top_k_df.empty:
             print(f"Sample URLs from retrieval: {top_k_df['url'].iloc[:3].tolist()}")
@@ -105,7 +98,6 @@ def recommend(query):
         print(f"Error: {str(e)}\n{error_details}")
         return {"error": f"Error processing request: {str(e)}"}
 
-
 iface = gr.Interface(
     fn=recommend,
     inputs=gr.Textbox(label="Enter Job Description", lines=4),