diff --git a/docs/my-website/docs/observability/arize_integration.md b/docs/my-website/docs/observability/arize_integration.md index 652d79af5122..17be003f8ab0 100644 --- a/docs/my-website/docs/observability/arize_integration.md +++ b/docs/my-website/docs/observability/arize_integration.md @@ -62,6 +62,7 @@ litellm_settings: environment_variables: ARIZE_SPACE_KEY: "d0*****" ARIZE_API_KEY: "141a****" + ARIZE_ENDPOINT: "https://otlp.arize.com/v1" # OPTIONAL - your custom arize api endpoint ``` ## Support & Talk to Founders diff --git a/docs/my-website/docs/proxy/logging.md b/docs/my-website/docs/proxy/logging.md index 5523b95f824f..89ed0bda5268 100644 --- a/docs/my-website/docs/proxy/logging.md +++ b/docs/my-website/docs/proxy/logging.md @@ -1279,6 +1279,7 @@ litellm_settings: environment_variables: ARIZE_SPACE_KEY: "d0*****" ARIZE_API_KEY: "141a****" + ARIZE_ENDPOINT: "https://otlp.arize.com/v1" # OPTIONAL - your custom arize api endpoint ``` 2. Start Proxy diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index ca02ea3aabc4..2b5cd2187f8c 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -2175,9 +2175,12 @@ def _init_custom_logger_compatible_class( OpenTelemetryConfig, ) + arize_endpoint = ( + os.environ.get("ARIZE_ENDPOINT", None) or "https://otlp.arize.com/v1" + ) otel_config = OpenTelemetryConfig( exporter="otlp_grpc", - endpoint="https://otlp.arize.com/v1", + endpoint=arize_endpoint, ) os.environ["OTEL_EXPORTER_OTLP_TRACES_HEADERS"] = ( f"space_key={os.getenv('ARIZE_SPACE_KEY')},api_key={os.getenv('ARIZE_API_KEY')}" diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 4ddd5cb1af2b..8772c3100322 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1236,7 +1236,7 @@ }, "deepseek-chat": { "max_tokens": 4096, - "max_input_tokens": 32000, + "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_token": 0.00000014, "input_cost_per_token_cache_hit": 0.000000014,