diff --git a/litellm/proxy/_new_secret_config.yaml b/litellm/proxy/_new_secret_config.yaml index 98a59a0af..a8101181c 100644 --- a/litellm/proxy/_new_secret_config.yaml +++ b/litellm/proxy/_new_secret_config.yaml @@ -6,7 +6,6 @@ model_list: api_base: https://openai-function-calling-workers.tasslexyz.workers.dev/ # api_base: http://0.0.0.0:8080 stream_timeout: 0.001 - rpm: 10 - model_name: fake-openai-endpoint litellm_params: model: openai/my-fake-model-2 @@ -14,7 +13,6 @@ model_list: api_base: https://openai-function-calling-workers.tasslexyz.workers.dev/ # api_base: http://0.0.0.0:8080 stream_timeout: 0.001 - rpm: 10 - litellm_params: model: azure/chatgpt-v-2 api_base: os.environ/AZURE_API_BASE @@ -32,28 +30,26 @@ model_list: # api_key: my-fake-key # api_base: https://exampleopenaiendpoint-production.up.railway.app/ -litellm_settings: - success_callback: ["prometheus"] - failure_callback: ["prometheus"] - service_callback: ["prometheus_system"] - upperbound_key_generate_params: - max_budget: os.environ/LITELLM_UPPERBOUND_KEYS_MAX_BUDGET +# litellm_settings: +# success_callback: ["prometheus"] +# failure_callback: ["prometheus"] +# service_callback: ["prometheus_system"] +# upperbound_key_generate_params: +# max_budget: os.environ/LITELLM_UPPERBOUND_KEYS_MAX_BUDGET router_settings: routing_strategy: usage-based-routing-v2 - redis_url: "rediss://:073f655645b843c4839329aea8384e68@us1-great-lizard-40486.upstash.io:40486/0" + # redis_url: "os.environ/REDIS_URL" + redis_host: os.environ/REDIS_HOST + redis_port: os.environ/REDIS_PORT + redis_password: os.environ/REDIS_PASSWORD enable_pre_call_checks: True +litellm_settings: + num_retries: 3 # retry call 3 times on each model_name + allowed_fails: 3 # cooldown model if it fails > 1 call in a minute. + general_settings: - master_key: sk-1234 - allow_user_auth: true alerting: ["slack"] - store_model_in_db: True // set via environment variable - os.environ["STORE_MODEL_IN_DB"] = "True" - proxy_batch_write_at: 5 # 👈 Frequency of batch writing logs to server (in seconds) - enable_jwt_auth: True - alerting: ["slack"] - litellm_jwtauth: - admin_jwt_scope: "litellm_proxy_admin" - public_key_ttl: os.environ/LITELLM_PUBLIC_KEY_TTL - user_id_jwt_field: "sub" - org_id_jwt_field: "azp" \ No newline at end of file + alerting_threshold: 300 # sends alerts if requests hang for 5min+ and responses take 5min+ + proxy_batch_write_at: 60 # Frequency of batch writing logs to server (in seconds) \ No newline at end of file diff --git a/litellm/tests/example_config_yaml/cache_with_params.yaml b/litellm/tests/example_config_yaml/cache_with_params.yaml index d43c1d033..068e2cc4a 100644 --- a/litellm/tests/example_config_yaml/cache_with_params.yaml +++ b/litellm/tests/example_config_yaml/cache_with_params.yaml @@ -8,4 +8,4 @@ litellm_settings: cache_params: type: "redis" supported_call_types: ["embedding", "aembedding"] - host: "localhost" \ No newline at end of file + host: "os.environ/REDIS_HOST" \ No newline at end of file diff --git a/litellm/tests/test_proxy_server.py b/litellm/tests/test_proxy_server.py index d58cf7c2f..052646db8 100644 --- a/litellm/tests/test_proxy_server.py +++ b/litellm/tests/test_proxy_server.py @@ -362,7 +362,9 @@ def test_load_router_config(): ] # init with all call types except Exception as e: - pytest.fail("Proxy: Got exception reading config", e) + pytest.fail( + f"Proxy: Got exception reading config: {str(e)}\n{traceback.format_exc()}" + ) # test_load_router_config()