Update app.py

app.py

@@ -1,64 +1,116 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+import logging
+import json
+from together import Together
+
+# ----------------------------------------------------------------------------
+# Configuration & Constants
+# ----------------------------------------------------------------------------
+MODEL_NAME = "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
+SYSTEM_PROMPT = (
+    "You are CyberGuard, a senior-level cybersecurity expert assistant. "
+    "You autonomously enforce security best practices, making informed decisions when rule-based policies fail."
+)
+HISTORY_FILE = "conversation_history.json"
+
+# ----------------------------------------------------------------------------
+# Setup Logging
+# ----------------------------------------------------------------------------
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s'
 )
+logger = logging.getLogger(__name__)
+
+# ----------------------------------------------------------------------------
+# Conversation Persistence Utilities
+# ----------------------------------------------------------------------------
+def load_history(filepath: str) -> list:
+    """Load conversation history from a JSON file."""
+    try:
+        with open(filepath, 'r') as f:
+            history = json.load(f)
+        logger.info("Loaded existing conversation history.")
+        return history
+    except FileNotFoundError:
+        logger.info("No existing history found, starting fresh.")
+        return []
+
+
+def save_history(history: list, filepath: str) -> None:
+    """Persist conversation history to disk."""
+    with open(filepath, 'w') as f:
+        json.dump(history, f, indent=2)
+    logger.info("Conversation history saved.")
+
+# ----------------------------------------------------------------------------
+# Together Client Initialization
+# ----------------------------------------------------------------------------
+together_client = Together()
+
+# ----------------------------------------------------------------------------
+# Core Chat Functionality
+# ----------------------------------------------------------------------------
+def append_and_stream(user_input: str, history: list):
+    """
+    Append user input to history, call the LLM streaming API, and yield token-by-token.
+    """
+    # Frame as cybersecurity expert if not already
+    if not user_input.lower().startswith("as a cybersecurity expert"):
+        user_input = f"(As a cybersecurity expert) {user_input}"
+
+    # Append system prompt at start if missing
+    if not history or history[0]['role'] != 'system':
+        history.insert(0, {'role': 'system', 'content': SYSTEM_PROMPT})
+
+    # Append user message and prepare assistant placeholder
+    history.append({'role': 'user', 'content': user_input})
+    history.append({'role': 'assistant', 'content': ''})
+    save_history(history, HISTORY_FILE)
+
+    # Stream tokens from the model
+    stream = together_client.chat.completions.create(
+        model=MODEL_NAME,
+        messages=history,
+        stream=True
+    )
+
+    # Incrementally build assistant reply
+    for token in stream:
+        if hasattr(token, 'choices'):
+            delta = token.choices[0].delta.content
+            history[-1]['content'] += delta
+            save_history(history, HISTORY_FILE)
+            yield history
+
+# ----------------------------------------------------------------------------
+# Gradio Interface Definition
+# ----------------------------------------------------------------------------
+def launch_interface():
+    # Load previous history or start a new one
+    history = load_history(HISTORY_FILE)
+
+    with gr.Blocks() as demo:
+        gr.Markdown("## CyberGuard – Autonomous Cybersecurity Chat")
+        chatbot = gr.Chatbot(value=[(msg['role'], msg['content']) for msg in history if msg['role'] != 'system'])
+        state = gr.State(history)
+
+        txt = gr.Textbox(show_label=False, placeholder="Enter your security query...")
+
+        # Handle user submission
+        def on_submit(user_msg, hist):
+            return hist, hist + []  # trigger state change
+
+        txt.submit(lambda *_: None, None, txt)  # Clear input box
+        txt.submit(on_submit, [txt, state], [state, chatbot], queue=False)
+
+        # Stream assistant response when history updates
+        state.change(fn=append_and_stream, inputs=state, outputs=chatbot)
 
+        demo.launch(share=True, server_name='0.0.0.0', server_port=7860)
 
 if __name__ == "__main__":
-    demo.launch()
+    try:
+        launch_interface()
+    except Exception as e:
+        logger.exception("Failed to launch CyberGuard chat interface.")