Update app.py

app.py

@@ -1,78 +1,86 @@
 import os
 import threading
 import asyncio
+import time
 import discord
 from dotenv import load_dotenv
 from huggingface_hub import hf_hub_download
 from llama_cpp import Llama
 
-# Load environment variables (from Hugging Face Secrets and .env if available)
+# Load environment variables from Hugging Face Secrets (.env file is optional)
 load_dotenv()
 DISCORD_TOKEN = os.getenv("DISCORD_TOKEN")
 
 if not DISCORD_TOKEN:
     raise ValueError("Discord bot token is missing. Set DISCORD_TOKEN in the environment variables.")
 
-# Set model details
+# Model details: using the quantized Q8 version from bartowski's repository.
 MODEL_REPO = "bartowski/agentica-org_DeepScaleR-1.5B-Preview-GGUF"
 MODEL_FILENAME = "agentica-org_DeepScaleR-1.5B-Preview-Q8_0.gguf"
 MODEL_PATH = f"./{MODEL_FILENAME}"
 
-# If the model file doesn't exist locally, download it.
+# Download the model file if it does not exist locally.
 if not os.path.exists(MODEL_PATH):
-    print("Model file not found, downloading...")
+    print("Model file not found locally. Downloading now...")
     MODEL_PATH = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILENAME)
     print(f"Model downloaded to {MODEL_PATH}")
+else:
+    print(f"Model found locally at {MODEL_PATH}")
 
 # Initialize the model using llama-cpp-python.
-# Adjust n_threads if needed.
+# Adjust n_threads based on available CPU cores.
+print("Initializing model...")
 llm = Llama(model_path=MODEL_PATH, n_threads=4)
+print("Model initialization complete.")
 
 # Define a function to generate a response.
 def generate_response(prompt):
-    output = llm(prompt=prompt, max_tokens=200, temperature=0.7, top_p=0.9, echo=False)
-    response = output["text"]
-    # Replace the internal model name with your bot's identity.
-    response = response.replace("DeepScaleR", "Shiv Yantra AI")
-    return response
+    try:
+        # Generate response using the quantized model.
+        output = llm(prompt=prompt, max_tokens=200, temperature=0.7, top_p=0.9, echo=False)
+        response = output["text"]
+        # Enforce your bot identity.
+        response = response.replace("DeepScaleR", "Shiv Yantra AI")
+        return response
+    except Exception as e:
+        print(f"Error in generate_response: {e}")
+        return "Error processing your request."
 
-# ---------------------------
+# ----------------------------
 # Discord Bot Setup
-# ---------------------------
+# ----------------------------
 intents = discord.Intents.default()
-intents.message_content = True  # Enable access to message content
+intents.message_content = True  # Ensure we can read message contents
 client = discord.Client(intents=intents)
 
 @client.event
 async def on_ready():
-    print(f"Logged in as {client.user}")
+    print(f"Discord bot logged in as {client.user}")
 
 @client.event
 async def on_message(message):
-    # Ignore messages from the bot itself.
+    # Skip bot's own messages.
     if message.author == client.user:
         return
-
     user_input = message.content.strip()
     if user_input:
         try:
-            # Run generate_response in a separate thread so as not to block the Discord loop.
+            # Run the generate_response in a separate thread to avoid blocking.
             ai_response = await asyncio.to_thread(generate_response, user_input)
         except Exception as e:
-            print(f"Error during generation: {e}")
+            print(f"Error during generation in on_message: {e}")
             ai_response = "Error processing your request."
         await message.channel.send(ai_response)
 
 def run_discord_bot():
     client.run(DISCORD_TOKEN)
 
-# ---------------------------
-# Start the Discord Bot
-# ---------------------------
+# ----------------------------
+# Start Services Concurrently
+# ----------------------------
 if __name__ == "__main__":
-    # Run the Discord bot on a separate thread.
+    print("Starting Discord bot...")
     threading.Thread(target=run_discord_bot, daemon=True).start()
-    
-    # Keep the main thread alive.
+    print("Discord bot started. Keeping main thread alive.")
     while True:
-        pass
+        time.sleep(60)