Structs§
- Delta
Aggregator - Aggregates a stream of
NvCreateEmbeddingResponse
s into a singleNvCreateEmbeddingResponse
. For embeddings, this is typically simpler than text generation as embeddings are usually returned as a complete response. - NvCreate
Embedding Request - NvCreate
Embedding Response - A response structure for unary chat completion responses, embedding OpenAI’s
CreateChatCompletionResponse
. - NvExt
- NVIDIA LLM extensions to the OpenAI API