Python SDK, Proxy Server to call 100+ LLM APIs using the OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Google Vertex AI now supports Claude 3 Opus in beta. Adding it to the model config works fine. However, our default retry setting causes an error using the proxy health check:
{
"model": "vertex_ai/claude-3-opus@20240229",
"max_retries": 2,
"cache": {
"no-cache": true
},
"error": "AsyncMessages.create() got an unexpected keyword argument 'max_retries' stack trace: Traceback (most recent call last):\n File \"/usr/local/lib/python3.11/site-packages/litellm/main.py\", line 317, in acompletion\n response = await init_response\n ^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.11/site-packages/litellm/llms/vertex_ai_anthropic.py\", line 355, in async_completion\n message = await vertex_ai_client.messages.create(*data) # type: ignore\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.11/site-packages/anthropic/_utils/_utils.py\", line 275, in wrapper\n return func(args, kwargs)\n ^^^^^^^^^^^^^^^^^^^^^\nTypeError: AsyncMessages.create() got an unexpected keyword argument 'max_retries'\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n File \"/usr/local/lib/python3.11/site-packages/litellm/main.py\", line 3818, in ahealth_check\n await acompletion(model_params)\n File \"/usr/local/lib/python3.11/site-packages/litellm/utils.py\","
},
Motivation, pitch
It's the latest and greatest model from Anthropic which would be nice to use via Google Vertex AI.
The Feature
Google Vertex AI now supports Claude 3 Opus in beta. Adding it to the model config works fine. However, our default retry setting causes an error using the proxy health check:
{ "model": "vertex_ai/claude-3-opus@20240229", "max_retries": 2, "cache": { "no-cache": true }, "error": "AsyncMessages.create() got an unexpected keyword argument 'max_retries' stack trace: Traceback (most recent call last):\n File \"/usr/local/lib/python3.11/site-packages/litellm/main.py\", line 317, in acompletion\n response = await init_response\n ^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.11/site-packages/litellm/llms/vertex_ai_anthropic.py\", line 355, in async_completion\n message = await vertex_ai_client.messages.create(*data) # type: ignore\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/usr/local/lib/python3.11/site-packages/anthropic/_utils/_utils.py\", line 275, in wrapper\n return func(args, kwargs)\n ^^^^^^^^^^^^^^^^^^^^^\nTypeError: AsyncMessages.create() got an unexpected keyword argument 'max_retries'\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n File \"/usr/local/lib/python3.11/site-packages/litellm/main.py\", line 3818, in ahealth_check\n await acompletion(model_params)\n File \"/usr/local/lib/python3.11/site-packages/litellm/utils.py\"," },
Motivation, pitch
It's the latest and greatest model from Anthropic which would be nice to use via Google Vertex AI.