From 1393900c227a9591d4818f487b95c0b05fdf427d Mon Sep 17 00:00:00 2001 From: Benjamin Chrobot Date: Wed, 12 Nov 2025 21:08:52 -0500 Subject: [PATCH] [Docs] Fix code block indentation for fallbacks page (#16542) --- docs/my-website/docs/proxy/reliability.md | 172 +++++++++++----------- 1 file changed, 86 insertions(+), 86 deletions(-) diff --git a/docs/my-website/docs/proxy/reliability.md b/docs/my-website/docs/proxy/reliability.md index 682421ede17..86de7cc1142 100644 --- a/docs/my-website/docs/proxy/reliability.md +++ b/docs/my-website/docs/proxy/reliability.md @@ -28,7 +28,7 @@ fallbacks=[{"gpt-3.5-turbo": ["gpt-4"]}] ```python from litellm import Router router = Router( - model_list=[ + model_list=[ { "model_name": "gpt-3.5-turbo", "litellm_params": { @@ -47,8 +47,8 @@ router = Router( "rpm": 6 } } - ], - fallbacks=[{"gpt-3.5-turbo": ["gpt-4"]}] # 👈 KEY CHANGE + ], + fallbacks=[{"gpt-3.5-turbo": ["gpt-4"]}] # 👈 KEY CHANGE ) ``` @@ -104,9 +104,9 @@ model_list = [{..}, {..}] # defined in Step 1. router = Router(model_list=model_list, fallbacks=[{"bad-model": ["my-good-model"]}]) response = router.completion( - model="bad-model", - messages=[{"role": "user", "content": "Hey, how's it going?"}], - mock_testing_fallbacks=True, + model="bad-model", + messages=[{"role": "user", "content": "Hey, how's it going?"}], + mock_testing_fallbacks=True, ) ``` @@ -431,32 +431,32 @@ content_policy_fallbacks=[{"claude-2": ["my-fallback-model"]}] from litellm import Router router = Router( - model_list=[ - { - "model_name": "claude-2", - "litellm_params": { - "model": "claude-2", - "api_key": "", - "mock_response": Exception("content filtering policy"), - }, - }, - { - "model_name": "my-fallback-model", - "litellm_params": { - "model": "claude-2", - "api_key": "", - "mock_response": "This works!", - }, - }, - ], - content_policy_fallbacks=[{"claude-2": ["my-fallback-model"]}], # 👈 KEY CHANGE - # fallbacks=[..], # [OPTIONAL] - # context_window_fallbacks=[..], # [OPTIONAL] + model_list=[ + { + "model_name": "claude-2", + "litellm_params": { + "model": "claude-2", + "api_key": "", + "mock_response": Exception("content filtering policy"), + }, + }, + { + "model_name": "my-fallback-model", + "litellm_params": { + "model": "claude-2", + "api_key": "", + "mock_response": "This works!", + }, + }, + ], + content_policy_fallbacks=[{"claude-2": ["my-fallback-model"]}], # 👈 KEY CHANGE + # fallbacks=[..], # [OPTIONAL] + # context_window_fallbacks=[..], # [OPTIONAL] ) response = router.completion( - model="claude-2", - messages=[{"role": "user", "content": "Hey, how's it going?"}], + model="claude-2", + messages=[{"role": "user", "content": "Hey, how's it going?"}], ) ``` @@ -466,7 +466,7 @@ In your proxy config.yaml just add this line 👇 ```yaml router_settings: - content_policy_fallbacks=[{"claude-2": ["my-fallback-model"]}] + content_policy_fallbacks=[{"claude-2": ["my-fallback-model"]}] ``` Start proxy @@ -495,32 +495,32 @@ context_window_fallbacks=[{"claude-2": ["my-fallback-model"]}] from litellm import Router router = Router( - model_list=[ - { - "model_name": "claude-2", - "litellm_params": { - "model": "claude-2", - "api_key": "", - "mock_response": Exception("prompt is too long"), - }, - }, - { - "model_name": "my-fallback-model", - "litellm_params": { - "model": "claude-2", - "api_key": "", - "mock_response": "This works!", - }, - }, - ], - context_window_fallbacks=[{"claude-2": ["my-fallback-model"]}], # 👈 KEY CHANGE - # fallbacks=[..], # [OPTIONAL] - # content_policy_fallbacks=[..], # [OPTIONAL] + model_list=[ + { + "model_name": "claude-2", + "litellm_params": { + "model": "claude-2", + "api_key": "", + "mock_response": Exception("prompt is too long"), + }, + }, + { + "model_name": "my-fallback-model", + "litellm_params": { + "model": "claude-2", + "api_key": "", + "mock_response": "This works!", + }, + }, + ], + context_window_fallbacks=[{"claude-2": ["my-fallback-model"]}], # 👈 KEY CHANGE + # fallbacks=[..], # [OPTIONAL] + # content_policy_fallbacks=[..], # [OPTIONAL] ) response = router.completion( - model="claude-2", - messages=[{"role": "user", "content": "Hey, how's it going?"}], + model="claude-2", + messages=[{"role": "user", "content": "Hey, how's it going?"}], ) ``` @@ -530,7 +530,7 @@ In your proxy config.yaml just add this line 👇 ```yaml router_settings: - context_window_fallbacks=[{"claude-2": ["my-fallback-model"]}] + context_window_fallbacks=[{"claude-2": ["my-fallback-model"]}] ``` Start proxy @@ -725,22 +725,22 @@ Filter older instances of a model (e.g. gpt-3.5-turbo) with smaller context wind ```yaml router_settings: - enable_pre_call_checks: true # 1. Enable pre-call checks + enable_pre_call_checks: true # 1. Enable pre-call checks model_list: - - model_name: gpt-3.5-turbo - litellm_params: - model: azure/chatgpt-v-2 - api_base: os.environ/AZURE_API_BASE - api_key: os.environ/AZURE_API_KEY - api_version: "2023-07-01-preview" - model_info: - base_model: azure/gpt-4-1106-preview # 2. 👈 (azure-only) SET BASE MODEL - - - model_name: gpt-3.5-turbo - litellm_params: - model: gpt-3.5-turbo-1106 - api_key: os.environ/OPENAI_API_KEY + - model_name: gpt-3.5-turbo + litellm_params: + model: azure/chatgpt-v-2 + api_base: os.environ/AZURE_API_BASE + api_key: os.environ/AZURE_API_KEY + api_version: "2023-07-01-preview" + model_info: + base_model: azure/gpt-4-1106-preview # 2. 👈 (azure-only) SET BASE MODEL + + - model_name: gpt-3.5-turbo + litellm_params: + model: gpt-3.5-turbo-1106 + api_key: os.environ/OPENAI_API_KEY ``` **2. Start proxy** @@ -766,8 +766,8 @@ text = "What is the meaning of 42?" * 5000 response = client.chat.completions.create( model="gpt-3.5-turbo", messages = [ - {"role": "system", "content": text}, - {"role": "user", "content": "Who was Alexander?"}, + {"role": "system", "content": text}, + {"role": "user", "content": "Who was Alexander?"}, ], ) @@ -782,20 +782,20 @@ Fallback to larger models if current model is too small. ```yaml router_settings: - enable_pre_call_checks: true # 1. Enable pre-call checks + enable_pre_call_checks: true # 1. Enable pre-call checks model_list: - - model_name: gpt-3.5-turbo-small - litellm_params: - model: azure/chatgpt-v-2 + - model_name: gpt-3.5-turbo-small + litellm_params: + model: azure/chatgpt-v-2 api_base: os.environ/AZURE_API_BASE api_key: os.environ/AZURE_API_KEY api_version: "2023-07-01-preview" model_info: base_model: azure/gpt-4-1106-preview # 2. 👈 (azure-only) SET BASE MODEL - - - model_name: gpt-3.5-turbo-large - litellm_params: + + - model_name: gpt-3.5-turbo-large + litellm_params: model: gpt-3.5-turbo-1106 api_key: os.environ/OPENAI_API_KEY @@ -831,8 +831,8 @@ text = "What is the meaning of 42?" * 5000 response = client.chat.completions.create( model="gpt-3.5-turbo", messages = [ - {"role": "system", "content": text}, - {"role": "user", "content": "Who was Alexander?"}, + {"role": "system", "content": text}, + {"role": "user", "content": "Who was Alexander?"}, ], ) @@ -849,9 +849,9 @@ Fallback across providers (e.g. from Azure OpenAI to Anthropic) if you hit conte ```yaml model_list: - - model_name: gpt-3.5-turbo-small - litellm_params: - model: azure/chatgpt-v-2 + - model_name: gpt-3.5-turbo-small + litellm_params: + model: azure/chatgpt-v-2 api_base: os.environ/AZURE_API_BASE api_key: os.environ/AZURE_API_KEY api_version: "2023-07-01-preview" @@ -874,9 +874,9 @@ You can also set default_fallbacks, in case a specific model group is misconfigu ```yaml model_list: - - model_name: gpt-3.5-turbo-small - litellm_params: - model: azure/chatgpt-v-2 + - model_name: gpt-3.5-turbo-small + litellm_params: + model: azure/chatgpt-v-2 api_base: os.environ/AZURE_API_BASE api_key: os.environ/AZURE_API_KEY api_version: "2023-07-01-preview" @@ -906,7 +906,7 @@ Set 'region_name' of deployment. ```yaml router_settings: - enable_pre_call_checks: true # 1. Enable pre-call checks + enable_pre_call_checks: true # 1. Enable pre-call checks model_list: - model_name: gpt-3.5-turbo