Added Hugging Face Dataset Upload Tool

app.py

@@ -4,6 +4,10 @@ import requests
 import pytz
 import yaml
 import os
+import json
+import uuid
+from datasets import Dataset
+from huggingface_hub import HfApi
 from openai import OpenAI
 from tools.final_answer import FinalAnswerTool
 
@@ -45,6 +49,66 @@ def Sonar_Web_Search_Tool(arg1: str, arg2: str) -> str:
         return sonar_response
     except Exception as e:
         return f"Error using Sonar Websearch tool '{arg1} {arg2}': {str(e)}"
+    
+
+def Dataset_Creator_Function(dataset_name: str, conversation_data: str) -> str:
+    """Creates and pushes a dataset to Hugging Face with the conversation history.
+    
+    Args:
+        dataset_name: Name for the dataset (will be prefixed with username)
+        conversation_data: JSON string or formatted text of conversation to save
+    
+    Returns:
+        URL of the created dataset or error message
+    """
+    try:
+        # Initialize Hugging Face API
+        hf_api = HfApi(token=os.getenv("HUGGINGFACE_API_KEY", ""))
+        
+        # Get username for the repository name
+        user_info = hf_api.whoami()
+        username = user_info.get("name", "anonymous")
+        
+        # Format the full repo name
+        repo_id = f"{username}/{dataset_name}"
+        
+        # If conversation_data is a string, try to parse it as JSON
+        if isinstance(conversation_data, str):
+            try:
+                conversation = json.loads(conversation_data)
+            except json.JSONDecodeError:
+                # If not valid JSON, treat as raw text
+                conversation = {"text": conversation_data}
+        else:
+            conversation = conversation_data
+            
+        # Add metadata
+        conversation["timestamp"] = datetime.datetime.now().isoformat()
+        conversation["dataset_id"] = str(uuid.uuid4())
+        
+        # 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("HF_API_KEY", ""))
+        
+        return f"Successfully created dataset at https://huggingface.co/datasets/{repo_id}"
+    except Exception as e:
+        return f"Error creating dataset: {str(e)}"
+
+@tool
+def Dataset_Creator_Tool(dataset_name: str, conversation_data: str) -> str:
+    """A tool that posts a new dataset of the current conversation to Hugging Face.
+    
+    Args:
+        dataset_name: Name for the dataset (will be prefixed with username)
+        conversation_data: Conversation history as JSON string or formatted text
+    """
+    try:
+        dataset_creator_response = Dataset_Creator_Function(dataset_name, conversation_data)
+        return dataset_creator_response
+    except Exception as e:
+        return f"Error using Dataset Creator tool: {str(e)}"
 
 
 @tool
@@ -81,7 +145,13 @@ with open("prompts.yaml", 'r') as stream:
     
 agent = CodeAgent(
     model=model,
-    tools=[final_answer, Sonar_Web_Search_Tool, get_current_time_in_timezone, image_generation_tool],  # Added the image tool
+    tools=[
+        final_answer, 
+        Sonar_Web_Search_Tool, 
+        get_current_time_in_timezone, 
+        image_generation_tool,
+        Dataset_Creator_Tool
+    ],  
     max_steps=6,
     verbosity_level=1,
     grammar=None,