Update app.py

app.py

@@ -5,11 +5,10 @@ from sklearn.cluster import KMeans
 from sentence_transformers import SentenceTransformer
 import requests
 import os
-
-HF_API_TOKEN = os.getenv("HF_API_TOKEN")  # ✅ GOOD: Read from environment
+import io
 
 # === CONFIGURATION ===
-#HF_API_TOKEN = ""
+HF_API_TOKEN = os.getenv("HF_API_TOKEN")  # Set in Hugging Face Secrets
 FALCON_MODEL = "tiiuae/falcon-7b-instruct"
 
 # === STEP 1: CLUSTERING MODEL ===
@@ -26,6 +25,9 @@ def cluster_texts(texts, n_clusters=10):
 
 # === STEP 2: FALCON-BASED LABELING ===
 def query_falcon(prompt):
+    if not HF_API_TOKEN:
+        return "API Token missing"
+        
     headers = {"Authorization": f"Bearer {HF_API_TOKEN}"}
     API_URL = f"https://api-inference.huggingface.co/models/{FALCON_MODEL}"
 
@@ -38,12 +40,11 @@ def query_falcon(prompt):
         }
     }
 
-    response = requests.post(API_URL, headers=headers, json=payload)
     try:
+        response = requests.post(API_URL, headers=headers, json=payload)
         return response.json()[0]['generated_text'].strip()
     except Exception as e:
-        print(f"Error calling Falcon: {e}")
-        return ""
+        return f"Error calling Falcon: {str(e)}"
 
 def generate_topic_labels(texts, clusters, n_clusters=10):
     cluster_samples = {}
@@ -76,9 +77,17 @@ session = {
     "topic_labels": {}
 }
 
+def read_csv_file(file_obj):
+    """Robust CSV reader that handles both string paths and file-like objects"""
+    if isinstance(file_obj, str):
+        return pd.read_csv(file_obj)
+    else:
+        content = file_obj.read().decode("utf-8")
+        return pd.read_csv(io.StringIO(content))
+
 def run_initial_analysis(csv_file, context_input, n_clusters=10):
     try:
-        df = pd.read_csv(csv_file)
+        df = read_csv_file(csv_file)
     except Exception as e:
         return f"Error reading CSV: {str(e)}", "", ""
 
@@ -96,9 +105,7 @@ def run_initial_analysis(csv_file, context_input, n_clusters=10):
     df['label'] = df['cluster'].map(topic_labels)
 
     session['current_df'] = df
-    session['topic_labels'] = topic_labels
 
-    # Save CSV
     output = io.StringIO()
     df.to_csv(output, index=False)
     csv_str = output.getvalue()