cookbook/Parallel_function_calling.ipynb
This is a tutorial on using Parallel function calling with LiteLLM
!pip install litellm
This tutorial walks through the steps doing parallel function calling using
# set openai api key
import os
os.environ['OPENAI_API_KEY'] = "" # litellm reads OPENAI_API_KEY from .env and sends the request
import litellm
import json
# Example dummy function hard coded to return the same weather
# In production, this could be your backend API or an external API
def get_current_weather(location, unit="fahrenheit"):
"""Get the current weather in a given location"""
if "tokyo" in location.lower():
return json.dumps({"location": "Tokyo", "temperature": "10", "unit": "celsius"})
elif "san francisco" in location.lower():
return json.dumps({"location": "San Francisco", "temperature": "72", "unit": "fahrenheit"})
elif "paris" in location.lower():
return json.dumps({"location": "Paris", "temperature": "22", "unit": "celsius"})
else:
return json.dumps({"location": location, "temperature": "unknown"})
messages = [{"role": "user", "content": "What's the weather like in San Francisco, Tokyo, and Paris?"}]
tools = [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location"],
},
},
}
]
response = litellm.completion(
model="gpt-3.5-turbo-1106",
messages=messages,
tools=tools,
tool_choice="auto", # auto is default, but we'll be explicit
)
print("\nLLM Response1:\n", response)
response_message = response.choices[0].message
tool_calls = response.choices[0].message.tool_calls
print("\nTool Choice:\n", tool_calls)
# Check if the model wants to call a function
if tool_calls:
# Execute the functions and prepare responses
available_functions = {
"get_current_weather": get_current_weather,
}
messages.append(response_message) # Extend conversation with assistant's reply
for tool_call in tool_calls:
print(f"\nExecuting tool call\n{tool_call}")
function_name = tool_call.function.name
function_to_call = available_functions[function_name]
function_args = json.loads(tool_call.function.arguments)
# calling the get_current_weather() function
function_response = function_to_call(
location=function_args.get("location"),
unit=function_args.get("unit"),
)
print(f"Result from tool call\n{function_response}\n")
# Extend conversation with function response
messages.append(
{
"tool_call_id": tool_call.id,
"role": "tool",
"name": function_name,
"content": function_response,
}
)
second_response = litellm.completion(
model="gpt-3.5-turbo-1106",
messages=messages,
)
print("Second Response\n", second_response)
print("Second Response Message\n", second_response.choices[0].message.content)
# set Azure env variables
import os
os.environ['AZURE_API_KEY'] = "" # litellm reads AZURE_API_KEY from .env and sends the request
os.environ['AZURE_API_BASE'] = "https://openai-gpt-4-test-v-1.openai.azure.com/"
os.environ['AZURE_API_VERSION'] = "2023-07-01-preview"
import litellm
import json
# Example dummy function hard coded to return the same weather
# In production, this could be your backend API or an external API
def get_current_weather(location, unit="fahrenheit"):
"""Get the current weather in a given location"""
if "tokyo" in location.lower():
return json.dumps({"location": "Tokyo", "temperature": "10", "unit": "celsius"})
elif "san francisco" in location.lower():
return json.dumps({"location": "San Francisco", "temperature": "72", "unit": "fahrenheit"})
elif "paris" in location.lower():
return json.dumps({"location": "Paris", "temperature": "22", "unit": "celsius"})
else:
return json.dumps({"location": location, "temperature": "unknown"})
messages = [{"role": "user", "content": "What's the weather like in San Francisco, Tokyo, and Paris?"}]
tools = [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location"],
},
},
}
]
response = litellm.completion(
model="azure/chatgpt-functioncalling", # model = azure/<your-azure-deployment-name>
messages=messages,
tools=tools,
tool_choice="auto", # auto is default, but we'll be explicit
)
print("\nLLM Response1:\n", response)
response_message = response.choices[0].message
tool_calls = response.choices[0].message.tool_calls
print("\nTool Choice:\n", tool_calls)
# Check if the model wants to call a function
if tool_calls:
# Execute the functions and prepare responses
available_functions = {
"get_current_weather": get_current_weather,
}
messages.append(response_message) # Extend conversation with assistant's reply
for tool_call in tool_calls:
print(f"\nExecuting tool call\n{tool_call}")
function_name = tool_call.function.name
function_to_call = available_functions[function_name]
function_args = json.loads(tool_call.function.arguments)
# calling the get_current_weather() function
function_response = function_to_call(
location=function_args.get("location"),
unit=function_args.get("unit"),
)
print(f"Result from tool call\n{function_response}\n")
# Extend conversation with function response
messages.append(
{
"tool_call_id": tool_call.id,
"role": "tool",
"name": function_name,
"content": function_response,
}
)
second_response = litellm.completion(
model="azure/chatgpt-functioncalling",
messages=messages,
)
print("Second Response\n", second_response)
print("Second Response Message\n", second_response.choices[0].message.content)