pip install groq

1from groq import Groq
2import json
3
4# Initialize the Groq client
5client = Groq()
6# Specify the model to be used (we recommend our fine-tuned models or the Llama 3.1 models)
7MODEL = 'llama3-groq-70b-8192-tool-use-preview'
8
9def calculate(expression):
10    """Evaluate a mathematical expression"""
11    try:
12        # Attempt to evaluate the math expression
13        result = eval(expression)
14        return json.dumps({"result": result})
15    except:
16        # Return an error message if the math expression is invalid
17        return json.dumps({"error": "Invalid expression"})

1# imports calculate function from step 1
2def run_conversation(user_prompt):
3    # Initialize the conversation with system and user messages
4    messages=[
5        {
6            "role": "system",
7            "content": "You are a calculator assistant. Use the calculate function to perform mathematical operations and provide the results."
8        },
9        {
10            "role": "user",
11            "content": user_prompt,
12        }
13    ]
14    # Define the available tools (i.e. functions) for our model to use
15    tools = [
16        {
17            "type": "function",
18            "function": {
19                "name": "calculate",
20                "description": "Evaluate a mathematical expression",
21                "parameters": {
22                    "type": "object",
23                    "properties": {
24                        "expression": {
25                            "type": "string",
26                            "description": "The mathematical expression to evaluate",
27                        }
28                    },
29                    "required": ["expression"],
30                },
31            },
32        }
33    ]
34    # Make the initial API call to Groq
35    response = client.chat.completions.create(
36        model=MODEL, # LLM to use
37        messages=messages, # Conversation history
38        stream=False
39        tools=tools, # Available tools (i.e. functions) for our LLM to use
40        tool_choice="auto", # Let our LLM decide when to use tools
41        max_tokens=4096 # Maximum number of tokens to allow in our response
42    )
43    # Extract the response and any tool call responses
44    response_message = response.choices[0].message
45    tool_calls = response_message.tool_calls
46    if tool_calls:
47        # Define the available tools that can be called by the LLM
48        available_functions = {
49            "calculate": calculate,
50        }
51        # Add the LLM's response to the conversation
52        messages.append(response_message)
53
54        # Process each tool call
55        for tool_call in tool_calls:
56            function_name = tool_call.function.name
57            function_to_call = available_functions[function_name]
58            function_args = json.loads(tool_call.function.arguments)
59            # Call the tool and get the response
60            function_response = function_to_call(
61                expression=function_args.get("expression")
62            )
63            # Add the tool response to the conversation
64            messages.append(
65                {
66                    "tool_call_id": tool_call.id, 
67                    "role": "tool", # Indicates this message is from tool use
68                    "name": function_name,
69                    "content": function_response,
70                }
71            )
72        # Make a second API call with the updated conversation
73        second_response = client.chat.completions.create(
74            model=MODEL,
75            messages=messages
76        )
77        # Return the final response
78        return second_response.choices[0].message.content
79# Example usage
80user_prompt = "What is 25 * 4 + 10?"
81print(run_conversation(user_prompt))

1from groq import Groq
2import json
3
4# Initialize the Groq client 
5client = Groq()
6
7# Define models
8ROUTING_MODEL = "llama3-70b-8192"
9TOOL_USE_MODEL = "llama3-groq-70b-8192-tool-use-preview"
10GENERAL_MODEL = "llama3-70b-8192"
11
12def calculate(expression):
13    """Tool to evaluate a mathematical expression"""
14    try:
15        result = eval(expression)
16        return json.dumps({"result": result})
17    except:
18        return json.dumps({"error": "Invalid expression"})
19
20def route_query(query):
21    """Routing logic to let LLM decide if tools are needed"""
22    routing_prompt = f"""
23    Given the following user query, determine if any tools are needed to answer it.
24    If a calculation tool is needed, respond with 'TOOL: CALCULATE'.
25    If no tools are needed, respond with 'NO TOOL'.
26
27    User query: {query}
28
29    Response:
30    """
31    
32    response = client.chat.completions.create(
33        model=ROUTING_MODEL,
34        messages=[
35            {"role": "system", "content": "You are a routing assistant. Determine if tools are needed based on the user query."},
36            {"role": "user", "content": routing_prompt}
37        ],
38        max_tokens=20  # We only need a short response
39    )
40    
41    routing_decision = response.choices[0].message.content.strip()
42    
43    if "TOOL: CALCULATE" in routing_decision:
44        return "calculate tool needed"
45    else:
46        return "no tool needed"
47
48def run_with_tool(query):
49    """Use the tool use model to perform the calculation"""
50    messages = [
51        {
52            "role": "system",
53            "content": "You are a calculator assistant. Use the calculate function to perform mathematical operations and provide the results.",
54        },
55        {
56            "role": "user",
57            "content": query,
58        }
59    ]
60    tools = [
61        {
62            "type": "function",
63            "function": {
64                "name": "calculate",
65                "description": "Evaluate a mathematical expression",
66                "parameters": {
67                    "type": "object",
68                    "properties": {
69                        "expression": {
70                            "type": "string",
71                            "description": "The mathematical expression to evaluate",
72                        }
73                    },
74                    "required": ["expression"],
75                },
76            },
77        }
78    ]
79    response = client.chat.completions.create(
80        model=TOOL_USE_MODEL,
81        messages=messages,
82        tools=tools,
83        tool_choice="auto",
84        max_tokens=4096
85    )
86    response_message = response.choices[0].message
87    tool_calls = response_message.tool_calls
88    if tool_calls:
89        messages.append(response_message)
90        for tool_call in tool_calls:
91            function_args = json.loads(tool_call.function.arguments)
92            function_response = calculate(function_args.get("expression"))
93            messages.append(
94                {
95                    "tool_call_id": tool_call.id,
96                    "role": "tool",
97                    "name": "calculate",
98                    "content": function_response,
99                }
100            )
101        second_response = client.chat.completions.create(
102            model=TOOL_USE_MODEL,
103            messages=messages
104        )
105        return second_response.choices[0].message.content
106    return response_message.content
107
108def run_general(query):
109    """Use the general model to answer the query since no tool is needed"""
110    response = client.chat.completions.create(
111        model=GENERAL_MODEL,
112        messages=[
113            {"role": "system", "content": "You are a helpful assistant."},
114            {"role": "user", "content": query}
115        ]
116    )
117    return response.choices[0].message.content
118
119def process_query(query):
120    """Process the query and route it to the appropriate model"""
121    route = route_query(query)
122    if route == "calculate":
123        response = run_with_tool(query)
124    else:
125        response = run_general(query)
126    
127    return {
128        "query": query,
129        "route": route,
130        "response": response
131    }
132
133# Example usage
134if __name__ == "__main__":
135    queries = [
136        "What is the capital of the Netherlands?",
137        "Calculate 25 * 4 + 10"
138    ]
139    
140    for query in queries:
141        result = process_query(query)
142        print(f"Query: {result['query']}")
143        print(f"Route: {result['route']}")
144        print(f"Response: {result['response']}\n")

1import json
2from groq import Groq
3import os
4
5# Initialize Groq client
6client = Groq()
7model = "llama3-groq-70b-8192-tool-use-preview"
8
9# Define weather tools
10def get_temperature(location: str):
11    # This is a mock tool/function. In a real scenario, you would call a weather API.
12    temperatures = {"New York": 22, "London": 18, "Tokyo": 26, "Sydney": 20}
13    return temperatures.get(location, "Temperature data not available")
14
15def get_weather_condition(location: str):
16    # This is a mock tool/function. In a real scenario, you would call a weather API.
17    conditions = {"New York": "Sunny", "London": "Rainy", "Tokyo": "Cloudy", "Sydney": "Clear"}
18    return conditions.get(location, "Weather condition data not available")
19
20# Define system messages and tools
21messages = [
22    {"role": "system", "content": "You are a helpful weather assistant."},
23    {"role": "user", "content": "What's the weather like in New York and London?"},
24]
25
26tools = [
27    {
28        "type": "function",
29        "function": {
30            "name": "get_temperature",
31            "description": "Get the temperature for a given location",
32            "parameters": {
33                "type": "object",
34                "properties": {
35                    "location": {
36                        "type": "string",
37                        "description": "The name of the city",
38                    }
39                },
40                "required": ["location"],
41            },
42        },
43    },
44    {
45        "type": "function",
46        "function": {
47            "name": "get_weather_condition",
48            "description": "Get the weather condition for a given location",
49            "parameters": {
50                "type": "object",
51                "properties": {
52                    "location": {
53                        "type": "string",
54                        "description": "The name of the city",
55                    }
56                },
57                "required": ["location"],
58            },
59        },
60    }
61]
62
63# Make the initial request
64response = client.chat.completions.create(
65    model=model, messages=messages, tools=tools, tool_choice="auto", max_tokens=4096
66)
67
68response_message = response.choices[0].message
69tool_calls = response_message.tool_calls
70
71# Process tool calls
72messages.append(response_message)
73
74available_functions = {
75    "get_temperature": get_temperature,
76    "get_weather_condition": get_weather_condition,
77}
78
79for tool_call in tool_calls:
80    function_name = tool_call.function.name
81    function_to_call = available_functions[function_name]
82    function_args = json.loads(tool_call.function.arguments)
83    function_response = function_to_call(**function_args)
84
85    messages.append(
86        {
87            "role": "tool",
88            "content": str(function_response),
89            "tool_call_id": tool_call.id,
90        }
91    )
92
93# Make the final request with tool call results
94final_response = client.chat.completions.create(
95    model=model, messages=messages, tools=tools, tool_choice="auto", max_tokens=4096
96)
97
98print(final_response.choices[0].message.content)