Module nvidia_embeddings 

NVIDIA Embeddings Provider

Implements high-quality embeddings via NVIDIA Integrate API (/v1/embeddings).

Environment Variables

• NVIDIA_API_KEY: Required
• NVIDIA_BASE_URL: Optional (default: https://integrate.api.nvidia.com)
• NVIDIA_EMBEDDING_MODEL: Optional (default: nvidia/nv-embed-v1)
• NVIDIA_EMBEDDING_BATCH_SIZE: Optional (default: 64)

The NVIDIA API supports different input_type values. Memvid uses:

• passage for document/chunk embeddings
• query for query embeddings

Structs

NvidiaEmbeddingProvider