interstellarninja
commited on
Commit
•
4d50786
1
Parent(s):
9e2673b
changing single quotes in json objects to double quotes
Browse files
README.md
CHANGED
@@ -108,9 +108,9 @@ Our model was trained on specific system prompts and structures for Function Cal
|
|
108 |
You should use the system role with this message, followed by a function signature json as this example shows here.
|
109 |
```
|
110 |
<|im_start|>system
|
111 |
-
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> {
|
112 |
<tool_call>
|
113 |
-
{
|
114 |
</tool_call><|im_end|>
|
115 |
```
|
116 |
|
@@ -124,7 +124,7 @@ The model will then generate a tool call, which your inference code must parse,
|
|
124 |
```
|
125 |
<|im_start|>assistant
|
126 |
<tool_call>
|
127 |
-
{
|
128 |
</tool_call><|im_end|>
|
129 |
```
|
130 |
|
|
|
108 |
You should use the system role with this message, followed by a function signature json as this example shows here.
|
109 |
```
|
110 |
<|im_start|>system
|
111 |
+
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.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
|
112 |
<tool_call>
|
113 |
+
{"arguments": <args-dict>, "name": <function-name>}
|
114 |
</tool_call><|im_end|>
|
115 |
```
|
116 |
|
|
|
124 |
```
|
125 |
<|im_start|>assistant
|
126 |
<tool_call>
|
127 |
+
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
|
128 |
</tool_call><|im_end|>
|
129 |
```
|
130 |
|