phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(health_check.py): return 'missing mode' error message, if error with health check, and mode is missing

Browse source
This commit is contained in:
Krrish Dholakia 2024-08-16 17:23:30 -07:00
parent 51da6ab64e
commit 7fce6b0163
6 changed files with 17 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

12
litellm/main.py
View file

@ -4779,7 +4779,9 @@ async def ahealth_check(
For azure/openai -> completion.with_raw_response For azure/openai -> completion.with_raw_response
For rest -> litellm.acompletion() For rest -> litellm.acompletion()
""" """
passed_in_mode: Optional[str] = None
try: try:
model: Optional[str] = model_params.get("model", None) model: Optional[str] = model_params.get("model", None)
if model is None: if model is None:
@ -4793,7 +4795,10 @@ async def ahealth_check(
if model in litellm.model_cost and mode is None: if model in litellm.model_cost and mode is None:
mode = litellm.model_cost[model].get("mode") mode = litellm.model_cost[model].get("mode")
mode = mode or "chat" # default to chat completion calls mode = mode
passed_in_mode = mode
if mode is None:
mode = "chat" # default to chat completion calls
if custom_llm_provider == "azure": if custom_llm_provider == "azure":
api_key = ( api_key = (
@ -4883,13 +4888,14 @@ async def ahealth_check(
response = {} # args like remaining ratelimit etc. response = {} # args like remaining ratelimit etc.
return response return response
except Exception as e: except Exception as e:
verbose_logger.error( verbose_logger.exception(
"litellm.ahealth_check(): Exception occured - {}".format(str(e)) "litellm.ahealth_check(): Exception occured - {}".format(str(e))
) )
stack_trace = traceback.format_exc() stack_trace = traceback.format_exc()
if isinstance(stack_trace, str): if isinstance(stack_trace, str):
stack_trace = stack_trace[:1000] stack_trace = stack_trace[:1000]
if model not in litellm.model_cost and mode is None:
if passed_in_mode is None:
return { return {
"error": "Missing `mode`. Set the `mode` for the model - https://docs.litellm.ai/docs/proxy/health#embedding-models" "error": "Missing `mode`. Set the `mode` for the model - https://docs.litellm.ai/docs/proxy/health#embedding-models"
} }

1
litellm/proxy/_experimental/out/404.html
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/model_hub.html
View file

File diff suppressed because one or more lines are too long

1
litellm/proxy/_experimental/out/onboarding.html
View file

File diff suppressed because one or more lines are too long

15
litellm/proxy/_new_secret_config.yaml
View file

@ -1,9 +1,6 @@
# model_list: model_list:
# - model_name: "gpt-4" - model_name: "text-embedding-ada-002"
# litellm_params: litellm_params:
# model: "gpt-4" model: "azure/azure-embedding-model"
# model_info: api_base: os.environ/AZURE_API_BASE
# my_custom_key: "my_custom_value" api_key: os.environ/AZURE_API_KEY
general_settings:
infer_model_from_keys: true

4
litellm/proxy/health_check.py
View file

@ -13,7 +13,7 @@ logger = logging.getLogger(__name__)
ILLEGAL_DISPLAY_PARAMS = ["messages", "api_key", "prompt", "input"] ILLEGAL_DISPLAY_PARAMS = ["messages", "api_key", "prompt", "input"]
MINIMAL_DISPLAY_PARAMS = ["model"] MINIMAL_DISPLAY_PARAMS = ["model", "mode_error"]
def _get_random_llm_message(): def _get_random_llm_message():
@ -31,7 +31,7 @@ def _clean_endpoint_data(endpoint_data: dict, details: Optional[bool] = True):
""" """
return ( return (
{k: v for k, v in endpoint_data.items() if k not in ILLEGAL_DISPLAY_PARAMS} {k: v for k, v in endpoint_data.items() if k not in ILLEGAL_DISPLAY_PARAMS}
if details if details is not False
else {k: v for k, v in endpoint_data.items() if k in MINIMAL_DISPLAY_PARAMS} else {k: v for k, v in endpoint_data.items() if k in MINIMAL_DISPLAY_PARAMS}
) )