phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

test(test_amazing_vertex_completion.py): try-except api errors

Browse source
This commit is contained in:
Krrish Dholakia 2024-05-03 10:09:57 -07:00
parent 0b72904608
commit 2dd9d2f704
2 changed files with 15 additions and 42 deletions
Download patch file Download diff file Expand all files Collapse all files

36
litellm/tests/test_amazing_vertex_completion.py
View file

@ -548,42 +548,6 @@ def test_gemini_pro_vision_base64():
def test_gemini_pro_function_calling():
load_vertex_ai_credentials()
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"],
},
},
}
]
messages = [
{
"role": "user",
"content": "What's the weather like in Boston today in fahrenheit?",
}
]
completion = litellm.completion(
model="gemini-pro", messages=messages, tools=tools, tool_choice="auto"
)
print(f"completion: {completion}")
if hasattr(completion.choices[0].message, "tool_calls") and isinstance(
completion.choices[0].message.tool_calls, list
):
assert len(completion.choices[0].message.tool_calls) == 1
try:
load_vertex_ai_credentials()
tools = [

19
litellm/utils.py
View file

@ -3977,9 +3977,7 @@ def calculage_img_tokens(
def create_pretrained_tokenizer(
identifier: str,
revision="main",
auth_token: Optional[str] = None
identifier: str, revision="main", auth_token: Optional[str] = None
):
"""
Creates a tokenizer from an existing file on a HuggingFace repository to be used with `token_counter`.
@ -3993,7 +3991,9 @@ def create_pretrained_tokenizer(
dict: A dictionary with the tokenizer and its type.
"""
tokenizer = Tokenizer.from_pretrained(identifier, revision=revision, auth_token=auth_token)
tokenizer = Tokenizer.from_pretrained(
identifier, revision=revision, auth_token=auth_token
)
return {"type": "huggingface_tokenizer", "tokenizer": tokenizer}
@ -9001,7 +9001,16 @@ def exception_type(
request=original_exception.request,
)
elif custom_llm_provider == "azure":
if "This model's maximum context length is" in error_str:
if "Internal server error" in error_str:
exception_mapping_worked = True
raise APIError(
status_code=500,
message=f"AzureException - {original_exception.message}",
llm_provider="azure",
model=model,
request=httpx.Request(method="POST", url="https://openai.com/"),
)
elif "This model's maximum context length is" in error_str:
exception_mapping_worked = True
raise ContextWindowExceededError(
message=f"AzureException - {original_exception.message}",