phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix - router show better client side errors

Browse source
This commit is contained in:
Ishaan Jaff 2024-05-16 09:01:27 -07:00
parent fda3914f4c
commit 848561a8a7
1 changed files with 7 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

12
litellm/router.py
View file

@ -3251,7 +3251,7 @@ class Router:
if _rate_limit_error == True: # allow generic fallback logic to take place if _rate_limit_error == True: # allow generic fallback logic to take place
raise ValueError( raise ValueError(
f"{RouterErrors.no_deployments_available.value}, passed model={model}" f"{RouterErrors.no_deployments_available.value}, Try again in {self.cooldown_time} seconds. Passed model={model}. Try again in {self.cooldown_time} seconds."
) )
elif _context_window_error == True: elif _context_window_error == True:
raise litellm.ContextWindowExceededError( raise litellm.ContextWindowExceededError(
@ -3323,7 +3323,9 @@ class Router:
litellm.print_verbose(f"initial list of deployments: {healthy_deployments}") litellm.print_verbose(f"initial list of deployments: {healthy_deployments}")
if len(healthy_deployments) == 0: if len(healthy_deployments) == 0:
raise ValueError(f"No healthy deployment available, passed model={model}. ") raise ValueError(
f"No healthy deployment available, passed model={model}. Try again in {self.cooldown_time} seconds"
)
if litellm.model_alias_map and model in litellm.model_alias_map: if litellm.model_alias_map and model in litellm.model_alias_map:
model = litellm.model_alias_map[ model = litellm.model_alias_map[
model model
@ -3413,7 +3415,7 @@ class Router:
if _allowed_model_region is None: if _allowed_model_region is None:
_allowed_model_region = "n/a" _allowed_model_region = "n/a"
raise ValueError( raise ValueError(
f"{RouterErrors.no_deployments_available.value}, passed model={model}. Enable pre-call-checks={self.enable_pre_call_checks}, allowed_model_region={_allowed_model_region}" f"{RouterErrors.no_deployments_available.value}, Try again in {self.cooldown_time} seconds. Passed model={model}. Enable pre-call-checks={self.enable_pre_call_checks}, allowed_model_region={_allowed_model_region}"
) )
if ( if (
@ -3481,7 +3483,7 @@ class Router:
f"get_available_deployment for model: {model}, No deployment available" f"get_available_deployment for model: {model}, No deployment available"
) )
raise ValueError( raise ValueError(
f"{RouterErrors.no_deployments_available.value}, passed model={model}" f"{RouterErrors.no_deployments_available.value}, Try again in {self.cooldown_time} seconds. Passed model={model}"
) )
verbose_router_logger.info( verbose_router_logger.info(
f"get_available_deployment for model: {model}, Selected deployment: {self.print_deployment(deployment)} for model: {model}" f"get_available_deployment for model: {model}, Selected deployment: {self.print_deployment(deployment)} for model: {model}"
@ -3611,7 +3613,7 @@ class Router:
f"get_available_deployment for model: {model}, No deployment available" f"get_available_deployment for model: {model}, No deployment available"
) )
raise ValueError( raise ValueError(
f"{RouterErrors.no_deployments_available.value}, passed model={model}" f"{RouterErrors.no_deployments_available.value}, Try again in {self.cooldown_time} seconds. Passed model={model}"
) )
verbose_router_logger.info( verbose_router_logger.info(
f"get_available_deployment for model: {model}, Selected deployment: {self.print_deployment(deployment)} for model: {model}" f"get_available_deployment for model: {model}, Selected deployment: {self.print_deployment(deployment)} for model: {model}"