From c72c8c0383a1d950e7e6e52cb6fe643ad61d3e02 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Wed, 11 Sep 2024 14:24:04 -0700 Subject: [PATCH] fix otel use sensible defaults --- litellm/integrations/opentelemetry.py | 4 --- ...odel_prices_and_context_window_backup.json | 33 ++++++++++++++++++- litellm/proxy/proxy_config.yaml | 3 ++ 3 files changed, 35 insertions(+), 5 deletions(-) diff --git a/litellm/integrations/opentelemetry.py b/litellm/integrations/opentelemetry.py index 84e45e16b1..d432372db5 100644 --- a/litellm/integrations/opentelemetry.py +++ b/litellm/integrations/opentelemetry.py @@ -650,8 +650,6 @@ class OpenTelemetry(CustomLogger): OTLPSpanExporterHTTP( endpoint=self.OTEL_ENDPOINT, headers=_split_otel_headers ), - max_queue_size=100, - max_export_batch_size=100, ) elif self.OTEL_EXPORTER == "otlp_grpc": verbose_logger.debug( @@ -662,8 +660,6 @@ class OpenTelemetry(CustomLogger): OTLPSpanExporterGRPC( endpoint=self.OTEL_ENDPOINT, headers=_split_otel_headers ), - max_queue_size=100, - max_export_batch_size=100, ) else: verbose_logger.debug( diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 61aa5183e6..37ac239664 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -2015,6 +2015,37 @@ "supports_vision": true, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, + "gemini-1.5-flash-exp-0827": { + "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_images_per_prompt": 3000, + "max_videos_per_prompt": 10, + "max_video_length": 1, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_pdf_size_mb": 30, + "input_cost_per_image": 0.0001315, + "input_cost_per_video_per_second": 0.0001315, + "input_cost_per_audio_per_second": 0.000125, + "input_cost_per_token": 0.0000005, + "input_cost_per_character": 0.000000125, + "input_cost_per_token_above_128k_tokens": 0.000001, + "input_cost_per_character_above_128k_tokens": 0.00000025, + "output_cost_per_token": 0.0000015, + "output_cost_per_character": 0.000000375, + "output_cost_per_token_above_128k_tokens": 0.000003, + "output_cost_per_character_above_128k_tokens": 0.00000075, + "output_cost_per_image": 0.000263, + "output_cost_per_video_per_second": 0.000263, + "output_cost_per_audio_per_second": 0.00025, + "litellm_provider": "vertex_ai-language-models", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": true, + "supports_vision": true, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, "gemini-1.5-flash-001": { "max_tokens": 8192, "max_input_tokens": 1000000, @@ -5586,4 +5617,4 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "metadata": {"notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."} } -} \ No newline at end of file +} diff --git a/litellm/proxy/proxy_config.yaml b/litellm/proxy/proxy_config.yaml index defde37723..3935063eb4 100644 --- a/litellm/proxy/proxy_config.yaml +++ b/litellm/proxy/proxy_config.yaml @@ -14,3 +14,6 @@ model_list: general_settings: master_key: sk-1234 + +litellm_settings: + callbacks: ["otel"] \ No newline at end of file