Update app.py

app.py

@@ -62,7 +62,7 @@ Respond only 'Yes' if suitable, otherwise 'No'.
         return "No"
 
 # ----------------------------
-# Filter by roles (step 1)
+# Step 1: Filter by roles
 # ----------------------------
 def filter_by_roles(category_name):
     job_titles = CATEGORIES[category_name]
@@ -95,16 +95,23 @@ def filter_by_roles(category_name):
     return df, FILTERED_CSV
 
 # ----------------------------
-# LLM-based recommendations (step 2)
+# Step 2: LLM recommendations
 # ----------------------------
 def llm_recommendations(category_name):
     job_titles = CATEGORIES[category_name]
+
+    # Read filtered candidates from CSV
     if not os.path.exists(FILTERED_CSV):
         return pd.DataFrame(), None
 
-    df = pd.read_csv(FILTERED_CSV)
-    filtered_candidates = df.to_dict(orient="records")
+    df_filtered = pd.read_csv(FILTERED_CSV)
+    df_filtered = df_filtered[df_filtered["Category"] == category_name]
+
+    if df_filtered.empty:
+        return pd.DataFrame(), None
+
     recommended = []
+    filtered_candidates = df_filtered.to_dict(orient="records")
 
     for i in range(0, len(filtered_candidates), BATCH_SIZE):
         batch = filtered_candidates[i:i+BATCH_SIZE]
@@ -118,11 +125,18 @@ def llm_recommendations(category_name):
         return pd.DataFrame(), None
 
     df_rec = pd.DataFrame(recommended)
-    df_rec["Salary_sort"] = df_rec["Salary"].apply(lambda s: float(s.replace("$","").replace(",","")) if isinstance(s,str) and s.startswith("$") else float('inf'))
+    # Sort by Salary (numeric)
+    def parse_salary(s):
+        try:
+            return float(s.replace("$","").replace(",",""))
+        except:
+            return float('inf')
+    df_rec["Salary_sort"] = df_rec["Salary"].apply(parse_salary)
     df_rec = df_rec.sort_values("Salary_sort").drop(columns=["Salary_sort"])
-    df_rec = df_rec.head(5)
-    df_rec.to_csv(OUTPUT_FILE, index=False)
-    return df_rec, OUTPUT_FILE
+    df_top5 = df_rec.head(5)
+    df_top5.to_csv(OUTPUT_FILE, index=False)
+
+    return df_top5, OUTPUT_FILE
 
 # ----------------------------
 # Show first 5 raw JSON candidates