Spaces:
Runtime error
Runtime error
File size: 6,520 Bytes
ec8f374 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 |
"""
Tool Use Generator Module
Generates training data for teaching LLMs to use tools and functions.
"""
import json
from typing import List, Dict, Any, Optional
class ToolUseGenerator:
"""Generate tool use training data for function calling."""
def __init__(self, tools: Optional[List[Dict]] = None):
"""
Initialize tool use generator.
Args:
tools: List of tool definitions
"""
self.tools = tools or self._get_default_financial_tools()
def _get_default_financial_tools(self) -> List[Dict]:
"""Get default financial tools."""
return [
{
"name": "get_market_data",
"description": "Get current market data for a stock",
"parameters": {
"symbol": "string",
"data_type": "string (price, volume, market_cap)"
},
"returns": "dict"
},
{
"name": "calculate_compound_interest",
"description": "Calculate compound interest",
"parameters": {
"principal": "float",
"rate": "float",
"time": "float",
"frequency": "int"
},
"returns": "float"
},
{
"name": "get_portfolio_allocation",
"description": "Get current portfolio allocation",
"parameters": {
"user_id": "string"
},
"returns": "dict"
},
{
"name": "calculate_retirement_needs",
"description": "Calculate retirement savings needs",
"parameters": {
"current_age": "int",
"retirement_age": "int",
"current_savings": "float",
"annual_contribution": "float"
},
"returns": "dict"
}
]
def generate_tool_use_examples(
self,
num_examples: int = 10,
complexity: str = "single"
) -> List[Dict[str, Any]]:
"""
Generate tool use training examples.
Args:
num_examples: Number of examples to generate
complexity: "single" or "multi" (multi-step tool chains)
Returns:
List of tool use examples
"""
examples = []
for _ in range(num_examples):
if complexity == "single":
example = self._generate_single_tool_example()
else:
example = self._generate_multi_tool_example()
if example:
examples.append(example)
return examples
def _generate_single_tool_example(self) -> Dict[str, Any]:
"""Generate example with single tool call."""
import random
tool = random.choice(self.tools)
# Create example based on tool
if tool["name"] == "get_market_data":
return {
"instruction": "What is the current price of Apple stock?",
"input": "",
"output": "I'll check the current market data for Apple stock.",
"tool_calls": [
{
"tool": "get_market_data",
"parameters": {
"symbol": "AAPL",
"data_type": "price"
}
}
]
}
elif tool["name"] == "calculate_compound_interest":
return {
"instruction": "If I invest $10,000 at 5% interest compounded quarterly, how much will I have in 10 years?",
"input": "",
"output": "I'll calculate that for you using compound interest formula.",
"tool_calls": [
{
"tool": "calculate_compound_interest",
"parameters": {
"principal": 10000,
"rate": 0.05,
"time": 10,
"frequency": 4
}
}
]
}
# Generic example
return {
"instruction": f"Use the {tool['name']} tool",
"input": "",
"output": f"I'll use {tool['name']} to help with that.",
"tool_calls": [{"tool": tool["name"], "parameters": {}}]
}
def _generate_multi_tool_example(self) -> Dict[str, Any]:
"""Generate example with multiple tool calls (chain)."""
return {
"instruction": "Should I rebalance my portfolio given current market conditions?",
"input": "",
"output": "Let me check your portfolio and current market data to provide a recommendation.",
"tool_calls": [
{
"tool": "get_portfolio_allocation",
"parameters": {"user_id": "user123"}
},
{
"tool": "get_market_data",
"parameters": {"symbol": "SPY", "data_type": "price"}
}
],
"reasoning": "First get the user's current portfolio allocation, then check market conditions, and finally provide rebalancing advice."
}
def add_custom_tool(self, tool: Dict[str, Any]) -> None:
"""
Add a custom tool definition.
Args:
tool: Tool definition dict
"""
required_keys = ["name", "description", "parameters", "returns"]
if not all(key in tool for key in required_keys):
raise ValueError(f"Tool must have keys: {required_keys}")
self.tools.append(tool)
def get_tools_schema(self) -> List[Dict]:
"""Get OpenAI-compatible tools schema."""
schema = []
for tool in self.tools:
schema.append({
"type": "function",
"function": {
"name": tool["name"],
"description": tool["description"],
"parameters": {
"type": "object",
"properties": tool["parameters"],
"required": list(tool["parameters"].keys())
}
}
})
return schema
|