Fix OPIK configuration: make COMET_PROJECT optional

src/second_brain_online/opik_utils.py

@@ -1,77 +1,60 @@
-import os
-
-import opik
-from loguru import logger
-from opik.configurator.configure import OpikConfigurator
-
-from second_brain_online.config import settings
+#!/usr/bin/env python3
+"""
+Hugging Face Space app for Second Brain AI Assistant.
 
+Direct implementation for HF Space deployment.
+"""
 
-def configure() -> None:
-    if settings.COMET_API_KEY and settings.COMET_PROJECT:
-        try:
-            client = OpikConfigurator(api_key=settings.COMET_API_KEY)
-            default_workspace = client._get_default_workspace()
-        except Exception:
-            logger.warning(
-                "Default workspace not found. Setting workspace to None and enabling interactive mode."
-            )
-            default_workspace = None
-
-        os.environ["OPIK_PROJECT_NAME"] = settings.COMET_PROJECT
-
-        opik.configure(
-            api_key=settings.COMET_API_KEY,
-            workspace=default_workspace,
-            use_local=False,
-            force=True,
-        )
-        logger.info(
-            f"Opik configured successfully using workspace '{default_workspace}'"
-        )
-    else:
-        logger.warning(
-            "COMET_API_KEY and COMET_PROJECT are not set. Set them to enable prompt monitoring with Opik (powered by Comet ML)."
-        )
-
-
-def get_or_create_dataset(name: str, prompts: list[str]) -> opik.Dataset | None:
-    client = opik.Opik()
+import os
+import sys
+from pathlib import Path
+
+# Add the current directory and src directory to Python path
+sys.path.append('.')
+sys.path.append('src')
+
+from second_brain_online.application.agents import get_agent
+from second_brain_online.application.ui import CustomGradioUI
+from second_brain_online import opik_utils
+
+def main():
+    """Main function for Hugging Face Space deployment."""
+    # Set default values for HF Spaces
+    retriever_config_path = os.getenv("RETRIEVER_CONFIG_PATH", "configs/compute_rag_vector_index_openai_contextual_simple.yaml")
+    
+    print("🚀 Starting Second Brain AI Assistant...")
+    print(f"📁 Using retriever config: {retriever_config_path}")
+    
+    # Debug: Check environment variables
+    print("🔍 Environment variables check:")
+    print(f"  COMET_API_KEY: {'SET' if os.getenv('COMET_API_KEY') else 'NOT SET'}")
+    print(f"  COMET_PROJECT: {os.getenv('COMET_PROJECT', 'NOT SET')}")
+    print(f"  OPENAI_API_KEY: {'SET' if os.getenv('OPENAI_API_KEY') else 'NOT SET'}")
+    print(f"  MONGODB_URI: {'SET' if os.getenv('MONGODB_URI') else 'NOT SET'}")
+    
+    # Configure OPIK (optional - will use default project if COMET_PROJECT not set)
     try:
-        dataset = client.get_dataset(name=name)
-    except Exception:
-        dataset = None
-
-    if dataset:
-        logger.warning(f"Dataset '{name}' already exists. Skipping dataset creation.")
-
-        return dataset
-
-    assert prompts, "Prompts are required to create a dataset."
-
-    dataset_items = []
-    for prompt in prompts:
-        dataset_items.append(
-            {
-                "input": prompt,
-            }
+        opik_utils.configure()
+        print("✅ OPIK configured successfully")
+    except Exception as e:
+        print(f"⚠️  OPIK configuration failed: {e}")
+    
+    try:
+        # Initialize agent
+        agent = get_agent(retriever_config_path=Path(retriever_config_path))
+        
+        # Get the actual agent from the wrapper
+        actual_agent = agent._AgentWrapper__agent
+        
+        # Launch custom UI
+        CustomGradioUI(actual_agent).launch(
+            server_name="0.0.0.0",
+            server_port=7860,
+            share=False
         )
+    except Exception as e:
+        print(f"❌ Error starting the application: {e}")
+        raise
 
-    dataset = create_dataset(
-        name=name,
-        description="Dataset for evaluating the agentic app.",
-        items=dataset_items,
-    )
-
-    return dataset
-
-
-def create_dataset(name: str, description: str, items: list[dict]) -> opik.Dataset:
-    client = opik.Opik()
-
-    dataset = client.get_or_create_dataset(name=name, description=description)
-    dataset.insert(items)
-
-    dataset = client.get_dataset(name=name)
-
-    return dataset
+if __name__ == "__main__":
+    main()