NV-Embed-v2

by nvidia

Top-ranked 7B text embedding model on MTEB English benchmark

1.5Mdl/month

7Bparams

HuggingFace Use in Pipeline

Identifiers

Model ID

nvidia/NV-Embed-v2

Feature URI

mixpeek://text_extractor@v1/nvidia_nv_embed_v2

Overview

NV-Embed-v2 is NVIDIA's 7B-parameter text embedding model that held the #1 position on the MTEB English benchmark with a score of 72.31. It uses a latent attention layer to remove the mean token pooling bottleneck and applies a two-stage contrastive training recipe: first on retrieval datasets, then on a blend of retrieval plus non-retrieval tasks (classification, clustering, STS).

On Mixpeek, NV-Embed-v2 is the highest-accuracy text embedder available for English-dominant workloads. Its 7B parameter count delivers superior quality for knowledge bases, legal corpora, and technical documentation where recall matters more than latency.

Architecture

Mistral-7B decoder backbone with a learned latent attention pooling layer replacing mean pooling. 7B parameters. Two-stage instruction-tuned contrastive training with causal attention masks removed during embedding.

Mixpeek SDK Integration

from mixpeek import Mixpeek

mixpeek = Mixpeek(api_key="YOUR_API_KEY")

mixpeek.ingest.documents(
    collection="knowledge_base",
    source={"type": "s3", "bucket": "enterprise-docs"},
    pipeline={
        "embedding": {
            "model": "mixpeek://text_extractor@v1/nvidia_nv_embed_v2"
        }
    }
)