Update app.py

app.py

@@ -1,45 +1,72 @@
 import gradio as gr
 from bertopic import BERTopic
 from sentence_transformers import SentenceTransformer
-
+import os # Import os for potential path checks, though the logic below is key
 
 def run_from_textfile(file):
     if file is None:
         return "Please upload a .txt file.", "", None
-
-    # ---- Handle file input for both HuggingFace and local environments ----
-    try:
-        # HuggingFace Spaces: file is NamedString and supports .decode()
-        text = file.decode("utf-8")
-    except:
-        # Local Gradio: file is a TemporaryFile-like object
-        text = file.read().decode("utf-8")
+    
+    # ---- Handle file input: Unify access for NamedString (Spaces) and file object (Local) ----
+    text = ""
+    
+    # 1. Check for the .decode() method, which is characteristic of the Gradio NamedString object 
+    # used in some environments (like HuggingFace Spaces).
+    if hasattr(file, 'decode'):
+        try:
+            # HuggingFace Spaces/NamedString: file supports .decode() directly
+            text = file.decode("utf-8")
+        except Exception as e:
+            return f"Error decoding NamedString: {e}", "", None
+    
+    # 2. If it does not have .decode(), it's likely a standard file object 
+    # (or a path, though gr.File usually passes an object or path string)
+    # The original TemporaryFile-like object in local Gradio will support .read()
+    elif hasattr(file, 'read'):
+        try:
+            # Local Gradio/TemporaryFile-like object: file supports .read()
+            text = file.read().decode("utf-8")
+        except Exception as e:
+            return f"Error reading/decoding file object: {e}", "", None
+    
+    # Optional: Handle the case where Gradio passed a string path instead of an object
+    elif isinstance(file, str) and os.path.exists(file):
+        try:
+            with open(file, 'r', encoding='utf-8') as f:
+                text = f.read()
+        except Exception as e:
+            return f"Error reading file from path: {e}", "", None
+
+    # Fallback check if text is still empty (e.g., if object type was unexpected)
+    if not text:
+         return "Could not read the file content. Please check the file type and content.", "", None
 
     # Split the text into documents (one per line)
     docs = [line.strip() for line in text.split("\n") if line.strip()]
 
     if len(docs) < 3:
         return "Need at least 3 documents (one per line).", "", None
-
+    
     # ---- Embedding Model ----
+    # Using 'all-MiniLM-L6-v2' as requested
     embedder = SentenceTransformer("all-MiniLM-L6-v2")
-
+    
     # ---- Topic Modeling ----
     topic_model = BERTopic(embedding_model=embedder)
     topics, probs = topic_model.fit_transform(docs)
-
+    
     # ---- Topic Summary ----
-    topic_info = topic_model.get_topic_info().to_string()
-
+    # Convert to string and remove index for clean output
+    topic_info = topic_model.get_topic_info().to_string(index=False)
+    
     # ---- Document → Topic Assignments ----
     assignments = "\n".join([f"Doc {i+1}: Topic {topics[i]}" for i in range(len(docs))])
-
+    
     # ---- Visualization ----
     fig = topic_model.visualize_barchart(top_n_topics=10)
-
+    
     return topic_info, assignments, fig
 
-
 # ---- Gradio Interface ----
 with gr.Blocks() as demo:
     gr.Markdown("# 🧠 Topic Modeling from TXT File (BERTopic)")
@@ -47,15 +74,17 @@ with gr.Blocks() as demo:
         "Upload a plain text (.txt) file. Each line should contain **one LLM response**.\n"
         "\nExample format:\n```\nResponse 1...\nResponse 2...\nResponse 3...\n```"
     )
-
-    file_input = gr.File(label="Upload .txt file")
-
+    
+    # Ensure file_input is configured to pass a file object or path.
+    # The default setting should work with the logic above.
+    file_input = gr.File(label="Upload .txt file") 
+    
     run_button = gr.Button("Run Topic Modeling")
-
+    
     topic_output = gr.Textbox(label="Topic Overview", lines=12)
     assignment_output = gr.Textbox(label="Document → Topic Assignments", lines=12)
     fig_output = gr.Plot(label="Topic Visualization")
-
+    
     run_button.click(
         fn=run_from_textfile,
         inputs=file_input,
@@ -63,4 +92,4 @@ with gr.Blocks() as demo:
     )
 
 # Launch app
-demo.launch()
+demo.launch()