feat: add logging

app.py

@@ -4,11 +4,16 @@ import sys
 # Add src directory to Python path for Hugging Face Spaces compatibility
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), "src"))
 
+import logging
+
 import gradio as gr
 
 from unpredictable_lord.chat import chat_with_llm_stream
 
-print("ZERO_GPU:", os.environ.get("ZERO_GPU"))
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
+logger = logging.getLogger(__name__)
+
+logger.info(f"ZERO_GPU: {os.environ.get('ZERO_GPU')}")
 
 # Gradio UI
 with gr.Blocks(title="Unpredictable Lord") as demo:

src/unpredictable_lord/chat.py

@@ -4,8 +4,12 @@ AI chat functionality implementation
 Provides chat functionality by calling the LLM endpoint on Modal or using ZeroGPU.
 """
 
+import logging
+
 import openai_harmony as oh
 
+logger = logging.getLogger(__name__)
+
 USE_MODAL = False
 
 
@@ -115,11 +119,13 @@ def chat_with_llm_stream(
                     partial_history[-1]["content"] = response_text
                     yield partial_history
 
-    except Exception as e:
-        error_message = f"An error occurred: {str(e)}"
-        print(error_message)
+    except Exception:
+        logger.exception("Error during chat_with_llm_stream")
         updated_history = chat_history + [
             {"role": "user", "content": user_message},
-            {"role": "assistant", "content": error_message},
+            {
+                "role": "assistant",
+                "content": "[Error occurred while generating response.]",
+            },
         ]
         yield updated_history

src/unpredictable_lord/modal_main.py

@@ -1,3 +1,4 @@
+import logging
 import subprocess
 from queue import Queue
 from threading import Thread
@@ -8,6 +9,8 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers.generation.streamers import BaseStreamer
 
+logger = logging.getLogger(__name__)
+
 APP_NAME = "unpredictable-lord"
 VOLUME_NAME = APP_NAME + "-volume"
 MOUNT_VOLUME = modal.Volume.from_name(VOLUME_NAME, create_if_missing=True)

src/unpredictable_lord/zerogpu.py

@@ -1,3 +1,4 @@
+import logging
 from queue import Queue
 from threading import Thread
 
@@ -7,6 +8,8 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers.generation.streamers import BaseStreamer
 
+logger = logging.getLogger(__name__)
+
 # https://huggingface.co/openai/gpt-oss-20b
 MODEL_IDENTIFIER = "openai/gpt-oss-20b"
 # https://huggingface.co/openai/gpt-oss-120b