File size: 7,645 Bytes
e3278e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
model_list:
  - model_name: gpt-3.5-turbo-end-user-test
    litellm_params:
      model: gpt-3.5-turbo
      region_name: "eu"
    model_info:
      id: "1"
  - model_name: gpt-3.5-turbo-end-user-test
    litellm_params:
      model: azure/chatgpt-v-2
      api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
      api_version: "2023-05-15"
      api_key: os.environ/AZURE_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
  - model_name: gpt-3.5-turbo
    litellm_params:
      model: azure/chatgpt-v-2
      api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
      api_version: "2023-05-15"
      api_key: os.environ/AZURE_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
  - model_name: gpt-3.5-turbo-large
    litellm_params: 
      model: "gpt-3.5-turbo-1106"
      api_key: os.environ/OPENAI_API_KEY
      rpm: 480
      timeout: 300
      stream_timeout: 60
  - model_name: gpt-4
    litellm_params:
      model: azure/chatgpt-v-2
      api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
      api_version: "2023-05-15"
      api_key: os.environ/AZURE_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
      rpm: 480
      timeout: 300
      stream_timeout: 60
  - model_name: sagemaker-completion-model
    litellm_params:
      model: sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4
      input_cost_per_second: 0.000420  
  - model_name: text-embedding-ada-002
    litellm_params: 
      model: azure/azure-embedding-model
      api_key: os.environ/AZURE_API_KEY
      api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
      api_version: "2023-05-15"
    model_info:
      mode: embedding
      base_model: text-embedding-ada-002
  - model_name: dall-e-2
    litellm_params:
      model: azure/
      api_version: 2023-06-01-preview
      api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
      api_key: os.environ/AZURE_API_KEY
  - model_name: openai-dall-e-3
    litellm_params:
      model: dall-e-3
  - model_name: fake-openai-endpoint
    litellm_params:
      model: openai/fake
      api_key: fake-key
      api_base: https://exampleopenaiendpoint-production.up.railway.app/
  - model_name: fake-openai-endpoint-2
    litellm_params:
      model: openai/my-fake-model
      api_key: my-fake-key
      api_base: https://exampleopenaiendpoint-production.up.railway.app/
      stream_timeout: 0.001
      rpm: 1
  - model_name: fake-openai-endpoint-3
    litellm_params:
      model: openai/my-fake-model
      api_key: my-fake-key
      api_base: https://exampleopenaiendpoint-production.up.railway.app/
      stream_timeout: 0.001
      rpm: 1000
  - model_name: fake-openai-endpoint-4
    litellm_params:
      model: openai/my-fake-model
      api_key: my-fake-key
      api_base: https://exampleopenaiendpoint-production.up.railway.app/
      num_retries: 50
  - model_name: fake-openai-endpoint-3
    litellm_params:
      model: openai/my-fake-model-2
      api_key: my-fake-key
      api_base: https://exampleopenaiendpoint-production.up.railway.app/
      stream_timeout: 0.001
      rpm: 1000
  - model_name: bad-model
    litellm_params:
      model: openai/bad-model
      api_key: os.environ/OPENAI_API_KEY
      api_base: https://exampleopenaiendpoint-production.up.railway.app/
      mock_timeout: True
      timeout: 60
      rpm: 1000
    model_info:
      health_check_timeout: 1
  - model_name: good-model
    litellm_params:
      model: openai/bad-model
      api_key: os.environ/OPENAI_API_KEY
      api_base: https://exampleopenaiendpoint-production.up.railway.app/
      rpm: 1000
    model_info:
      health_check_timeout: 1
  - model_name: "*"
    litellm_params:
      model: openai/*
      api_key: os.environ/OPENAI_API_KEY
  

  # provider specific wildcard routing
  - model_name: "anthropic/*"
    litellm_params:
      model: "anthropic/*"
      api_key: os.environ/ANTHROPIC_API_KEY
  - model_name: "bedrock/*"
    litellm_params:
      model: "bedrock/*"
  - model_name: "groq/*"
    litellm_params:
      model: "groq/*"
      api_key: os.environ/GROQ_API_KEY
  - model_name: mistral-embed
    litellm_params:
      model: mistral/mistral-embed
  - model_name: gpt-instruct # [PROD TEST] - tests if `/health` automatically infers this to be a text completion model
    litellm_params:
      model: text-completion-openai/gpt-3.5-turbo-instruct
  - model_name: fake-openai-endpoint-5
    litellm_params:
      model: openai/my-fake-model
      api_key: my-fake-key
      api_base: https://exampleopenaiendpoint-production.up.railway.app/
      timeout: 1
litellm_settings:
  # set_verbose: True  # Uncomment this if you want to see verbose logs; not recommended in production
  drop_params: True
  # max_budget: 100 
  # budget_duration: 30d
  num_retries: 5
  request_timeout: 600
  telemetry: False
  context_window_fallbacks: [{"gpt-3.5-turbo": ["gpt-3.5-turbo-large"]}]
  default_team_settings: 
    - team_id: team-1
      success_callback: ["langfuse"]
      failure_callback: ["langfuse"]
      langfuse_public_key: os.environ/LANGFUSE_PROJECT1_PUBLIC # Project 1
      langfuse_secret: os.environ/LANGFUSE_PROJECT1_SECRET # Project 1
    - team_id: team-2
      success_callback: ["langfuse"]
      failure_callback: ["langfuse"]
      langfuse_public_key: os.environ/LANGFUSE_PROJECT2_PUBLIC # Project 2
      langfuse_secret: os.environ/LANGFUSE_PROJECT2_SECRET # Project 2
      langfuse_host: https://us.cloud.langfuse.com

# For /fine_tuning/jobs endpoints
finetune_settings:
  - custom_llm_provider: azure
    api_base: os.environ/AZURE_API_BASE
    api_key: os.environ/AZURE_API_KEY
    api_version: "2023-03-15-preview"
  - custom_llm_provider: openai
    api_key: os.environ/OPENAI_API_KEY

# for /files endpoints
files_settings:
  - custom_llm_provider: azure
    api_base: os.environ/AZURE_API_BASE
    api_key: os.environ/AZURE_API_KEY
    api_version: "2023-03-15-preview"
  - custom_llm_provider: openai
    api_key: os.environ/OPENAI_API_KEY

router_settings:
  routing_strategy: usage-based-routing-v2 
  redis_host: os.environ/REDIS_HOST
  redis_password: os.environ/REDIS_PASSWORD
  redis_port: os.environ/REDIS_PORT
  enable_pre_call_checks: true
  model_group_alias: {"my-special-fake-model-alias-name": "fake-openai-endpoint-3"} 

general_settings: 
  master_key: sk-1234 # [OPTIONAL] Use to enforce auth on proxy. See - https://docs.litellm.ai/docs/proxy/virtual_keys
  store_model_in_db: True
  proxy_budget_rescheduler_min_time: 60
  proxy_budget_rescheduler_max_time: 64
  proxy_batch_write_at: 1
  database_connection_pool_limit: 10
  # database_url: "postgresql://<user>:<password>@<host>:<port>/<dbname>" # [OPTIONAL] use for token-based auth to proxy

  pass_through_endpoints:
    - path: "/v1/rerank"                                  # route you want to add to LiteLLM Proxy Server
      target: "https://api.cohere.com/v1/rerank"          # URL this route should forward requests to
      headers:                                            # headers to forward to this URL
        content-type: application/json                    # (Optional) Extra Headers to pass to this endpoint 
        accept: application/json
      forward_headers: True

# environment_variables:
  # settings for using redis caching
  # REDIS_HOST: redis-16337.c322.us-east-1-2.ec2.cloud.redislabs.com
  # REDIS_PORT: "16337"
  # REDIS_PASSWORD: