Update README.md

README.md

@@ -103,7 +103,7 @@ Our model was trained on specific system prompts and structures for Function Cal
 You should use the system role with this message, followed by a function signature json as this example shows here.
 ```
 <|im_start|>system
-You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> [{"type": "function", "function": {"name": "get_historical_stock_data", "description": "Retrieve historical stock data for a specified symbol within a date range, including specific data points like closing price and volume.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string", "description": "The stock symbol to retrieve data for."}, "start_date": {"type": "string", "description": "Start date for the data retrieval in YYYY-MM-DD format."}, "end_date": {"type": "string", "description": "End date for the data retrieval in YYYY-MM-DD format."}, "data_points": {"type": "array", "items": {"type": "string"}, "description": "Specific data points to retrieve, such as 'close' and 'volume'."}}, "required": ["symbol", "start_date", "end_date", "data_points"]}}}] </tools> Use the following pydantic model json schema for each tool call you will make: {'title': 'FunctionCall', 'type': 'object', 'properties': {'arguments': {'title': 'Arguments', 'type': 'object'}, 'name': {'title': 'Name', 'type': 'string'}}, 'required': ['arguments', 'name']} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
+You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {'type': 'function', 'function': {'name': 'get_stock_fundamentals', 'description': 'get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\n\n    Args:\n    symbol (str): The stock symbol.\n\n    Returns:\n    dict: A dictionary containing fundamental data.', 'parameters': {'type': 'object', 'properties': {'symbol': {'type': 'string'}}, 'required': ['symbol']}}}  </tools> Use the following pydantic model json schema for each tool call you will make: {'title': 'FunctionCall', 'type': 'object', 'properties': {'arguments': {'title': 'Arguments', 'type': 'object'}, 'name': {'title': 'Name', 'type': 'string'}}, 'required': ['arguments', 'name']} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
 <tool_call>
 {'arguments': <args-dict>, 'name': <function-name>}
 </tool_call><|im_end|>