phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(openai.py): creat MistralConfig with response_format mapping for mistral api

Browse source
This commit is contained in:
Krrish Dholakia 2024-05-13 13:29:43 -07:00
parent 20fe4ffd6b
commit 20456968e9
5 changed files with 129 additions and 46 deletions
Download patch file Download diff file Expand all files Collapse all files

19
litellm/tests/test_function_calling.py
View file

@ -37,14 +37,19 @@ def get_current_weather(location, unit="fahrenheit"):
# Example dummy function hard coded to return the same weather
# In production, this could be your backend API or an external API
def test_parallel_function_call():
@pytest.mark.parametrize(
"model", ["gpt-3.5-turbo-1106", "mistral/mistral-large-latest"]
)
def test_parallel_function_call(model):
try:
# Step 1: send the conversation and available functions to the model
messages = [
{
"role": "user",
"content": "What's the weather like in San Francisco, Tokyo, and Paris?",
"content": "What's the weather like in San Francisco, Tokyo, and Paris? - give me 3 responses",
}
]
tools = [
@ -58,7 +63,7 @@ def test_parallel_function_call():
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
"description": "The city and state",
},
"unit": {
"type": "string",
@ -71,7 +76,7 @@ def test_parallel_function_call():
}
]
response = litellm.completion(
model="gpt-3.5-turbo-1106",
model=model,
messages=messages,
tools=tools,
tool_choice="auto", # auto is default, but we'll be explicit
@ -83,8 +88,8 @@ def test_parallel_function_call():
print("length of tool calls", len(tool_calls))
print("Expecting there to be 3 tool calls")
assert (
len(tool_calls) > 1
) # this has to call the function for SF, Tokyo and parise
len(tool_calls) > 0
) # this has to call the function for SF, Tokyo and paris
# Step 2: check if the model wanted to call a function
if tool_calls:
@ -116,7 +121,7 @@ def test_parallel_function_call():
) # extend conversation with function response
print(f"messages: {messages}")
second_response = litellm.completion(
model="gpt-3.5-turbo-1106", messages=messages, temperature=0.2, seed=22
model=model, messages=messages, temperature=0.2, seed=22
) # get a new response from the model where it can see the function response
print("second response\n", second_response)
return second_response