diff --git a/litellm/main.py b/litellm/main.py index cf7a4a5e7e..eb975ca6c4 100644 --- a/litellm/main.py +++ b/litellm/main.py @@ -4779,7 +4779,9 @@ async def ahealth_check( For azure/openai -> completion.with_raw_response For rest -> litellm.acompletion() """ + passed_in_mode: Optional[str] = None try: + model: Optional[str] = model_params.get("model", None) if model is None: @@ -4793,7 +4795,10 @@ async def ahealth_check( if model in litellm.model_cost and mode is None: 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": api_key = ( @@ -4883,13 +4888,14 @@ async def ahealth_check( response = {} # args like remaining ratelimit etc. return response except Exception as e: - verbose_logger.error( + verbose_logger.exception( "litellm.ahealth_check(): Exception occured - {}".format(str(e)) ) stack_trace = traceback.format_exc() if isinstance(stack_trace, str): stack_trace = stack_trace[:1000] - if model not in litellm.model_cost and mode is None: + + if passed_in_mode is None: return { "error": "Missing `mode`. Set the `mode` for the model - https://docs.litellm.ai/docs/proxy/health#embedding-models" } diff --git a/litellm/proxy/_experimental/out/404.html b/litellm/proxy/_experimental/out/404.html deleted file mode 100644 index eeffbc7ccd..0000000000 --- a/litellm/proxy/_experimental/out/404.html +++ /dev/null @@ -1 +0,0 @@ -404: This page could not be found.LiteLLM Dashboard

404

This page could not be found.

\ No newline at end of file diff --git a/litellm/proxy/_experimental/out/model_hub.html b/litellm/proxy/_experimental/out/model_hub.html deleted file mode 100644 index 333dae1386..0000000000 --- a/litellm/proxy/_experimental/out/model_hub.html +++ /dev/null @@ -1 +0,0 @@ -LiteLLM Dashboard \ No newline at end of file diff --git a/litellm/proxy/_experimental/out/onboarding.html b/litellm/proxy/_experimental/out/onboarding.html deleted file mode 100644 index 3187145b15..0000000000 --- a/litellm/proxy/_experimental/out/onboarding.html +++ /dev/null @@ -1 +0,0 @@ -LiteLLM Dashboard \ No newline at end of file diff --git a/litellm/proxy/_new_secret_config.yaml b/litellm/proxy/_new_secret_config.yaml index f224253a79..fcbc4a1700 100644 --- a/litellm/proxy/_new_secret_config.yaml +++ b/litellm/proxy/_new_secret_config.yaml @@ -1,9 +1,6 @@ -# model_list: -# - model_name: "gpt-4" -# litellm_params: -# model: "gpt-4" -# model_info: -# my_custom_key: "my_custom_value" - -general_settings: - infer_model_from_keys: true \ No newline at end of file +model_list: + - model_name: "text-embedding-ada-002" + litellm_params: + model: "azure/azure-embedding-model" + api_base: os.environ/AZURE_API_BASE + api_key: os.environ/AZURE_API_KEY \ No newline at end of file diff --git a/litellm/proxy/health_check.py b/litellm/proxy/health_check.py index 5713fa782b..ff5ed7bfb7 100644 --- a/litellm/proxy/health_check.py +++ b/litellm/proxy/health_check.py @@ -13,7 +13,7 @@ logger = logging.getLogger(__name__) ILLEGAL_DISPLAY_PARAMS = ["messages", "api_key", "prompt", "input"] -MINIMAL_DISPLAY_PARAMS = ["model"] +MINIMAL_DISPLAY_PARAMS = ["model", "mode_error"] def _get_random_llm_message(): @@ -31,7 +31,7 @@ def _clean_endpoint_data(endpoint_data: dict, details: Optional[bool] = True): """ return ( {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} )