Updated Dataset_Creator_Function

This updated function:

Checks for API keys in both environment variable formats (HF_API_KEY and HUGGINGFACE_API_KEY)
Sets the default username to "Misfits-and-Machines" if authentication fails
Explicitly creates the repository before pushing data
Sets create_repo=True and repo_type="dataset" in push_to_hub
Adds more debug printing to help track issues
Properly sanitizes the dataset name (replacing spaces with dashes)
Adds a commit message for better tracking

app.py

@@ -62,15 +62,26 @@ def Dataset_Creator_Function(dataset_name: str, conversation_data: str) -> str:
         URL of the created dataset or error message
     """
     try:
+        # Get API key from environment variables - try both possible names
+        api_key = os.getenv("HF_API_KEY") or os.getenv("HUGGINGFACE_API_KEY", "")
+        if not api_key:
+            return "Error: No Hugging Face API key found in environment variables"
+            
         # Initialize Hugging Face API
-        hf_api = HfApi(token=os.getenv("HUGGINGFACE_API_KEY", ""))
+        hf_api = HfApi(token=api_key)
         
         # Get username for the repository name
-        user_info = hf_api.whoami()
-        username = user_info.get("name", "anonymous")
+        try:
+            user_info = hf_api.whoami()
+            username = user_info.get("name", "Misfits-and-Machines")  # Use the provided username as default
+        except Exception as e:
+            return f"Error authenticating with Hugging Face: {str(e)}"
         
-        # Format the full repo name
-        repo_id = f"{username}/{dataset_name}"
+        # Format the full repo name with sanitized dataset name
+        safe_dataset_name = dataset_name.replace(" ", "-").lower()
+        repo_id = f"{username}/{safe_dataset_name}"
+        
+        print(f"Creating dataset repository: {repo_id}")
         
         # Create a conversation object
         conversation = {
@@ -82,11 +93,27 @@ def Dataset_Creator_Function(dataset_name: str, conversation_data: str) -> str:
         # Create a Hugging Face dataset
         dataset = Dataset.from_dict({"conversations": [conversation]})
         
-        # Push to the Hugging Face Hub
-        dataset.push_to_hub(repo_id, token=os.getenv("HUGGINGFACE_API_KEY", ""))
+        # First try to create the repository explicitly
+        try:
+            hf_api.create_repo(repo_id=repo_id, repo_type="dataset", exist_ok=True)
+            print(f"Repository {repo_id} created or already exists")
+        except Exception as repo_error:
+            print(f"Note: Repository creation returned: {str(repo_error)}")
+        
+        # Push to the Hugging Face Hub with explicit parameters
+        dataset.push_to_hub(
+            repo_id=repo_id,
+            token=api_key,
+            create_repo=True,  # Create the repo if it doesn't exist
+            repo_type="dataset",  # Explicitly specify this is a dataset
+            commit_message="Add conversation dataset"
+        )
         
         return f"Successfully created dataset at https://huggingface.co/datasets/{repo_id}"
     except Exception as e:
+        import traceback
+        error_trace = traceback.format_exc()
+        print(f"Dataset creation error: {str(e)}\n{error_trace}")
         return f"Error creating dataset: {str(e)}"
 
 @tool