Upload app.py

app.py

@@ -44,12 +44,12 @@ def load_llm():
         "text-generation",
         model=model,
         tokenizer=tokenizer,
-        max_new_tokens=300,
-        temperature=0.1,
-        repetition_penalty=1.1,
         return_full_text=False
     )
-    return HuggingFacePipeline(pipeline=pipe)
+    return HuggingFacePipeline(
+        pipeline=pipe, 
+        pipeline_kwargs={"max_new_tokens": 300, "temperature": 0.1, "repetition_penalty": 1.1}
+    )
 
 # 2. CODE INGESTION & VECTOR DATABASE
 
@@ -249,7 +249,7 @@ def get_initial_repo_status():
         return f"✅ **Ready!** {file_count} files indexed and loaded."
     return "❌ **Empty Database.** Provide a codebase below to begin."
 
-with gr.Blocks(title="Codebase Assistant", css=custom_css, theme=gr.themes.Soft()) as demo:
+with gr.Blocks(title="Codebase Assistant") as demo:
     with gr.Row():
         with gr.Column(scale=1):
             gr.Markdown("# 🦖 RepoRaptor\n**Your personal AI codebase expert.**")
@@ -278,7 +278,7 @@ with gr.Blocks(title="Codebase Assistant", css=custom_css, theme=gr.themes.Soft(
         
         with gr.Column(scale=3):
             gr.Markdown("### 💻 Chat Interface\nAsk architecture questions, find bugs, or request code explanations. I will **only** answer questions related to code.")
-            chatbot = gr.Chatbot(height=600, show_label=False, bubble_full_width=False)
+            chatbot = gr.Chatbot(height=600, show_label=False)
             
             with gr.Row():
                 msg = gr.Textbox(placeholder="E.g., What does the main function do? (Press Enter to send)", show_label=False, scale=4)
@@ -288,4 +288,4 @@ with gr.Blocks(title="Codebase Assistant", css=custom_css, theme=gr.themes.Soft(
             clear.click(lambda: None, None, chatbot, queue=False)
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0")
+    demo.launch(server_name="0.0.0.0", css=custom_css, theme=gr.themes.Soft())