Python SDK, Proxy Server to call 100+ LLM APIs using the OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Looks like LiteLLM is sending YOUR_DEPLOYMENT_NAME twice in YOUR_RESOURCE_NAME/text-embedding-3-small/deployments/text-embedding-3-small/embeddings?api-version=2024-05-01-preview.
This is a recent regression I think. I had this config awhile ago and it was working fine.
What happened?
Looks like LiteLLM is sending
YOUR_DEPLOYMENT_NAME
twice inYOUR_RESOURCE_NAME/text-embedding-3-small/deployments/text-embedding-3-small/embeddings?api-version=2024-05-01-preview
.This is a recent regression I think. I had this config awhile ago and it was working fine.
Relevant log output
No response
Twitter / LinkedIn details
https://www.linkedin.com/in/davidmanouchehri/