NV-Embed-v2
by nvidia
Top-ranked 7B text embedding model on MTEB English benchmark
nvidia/NV-Embed-v2mixpeek://text_extractor@v1/nvidia_nv_embed_v2Overview
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
import { Mixpeek } from "mixpeek";
const mx = new Mixpeek({ apiKey: "API_KEY" });
// Managed: create a collection over a bucket; Mixpeek runs this model's extractor
const collection = await mx.collections.create({
namespace_id: "my-namespace",
collection_name: "my-collection",
source: { type: "bucket", bucket_ids: ["bkt_your_bucket"] },
feature_extractor: {
feature_extractor_name: "s3",
version: "v1",
parameters: { model_id: "mixpeek://text_extractor@v1/nvidia_nv_embed_v2" },
},
});Capabilities
- 72.31 average on MTEB English benchmark (former #1)
- 4096-dimensional embeddings
- Strong on retrieval, classification, clustering, and STS tasks simultaneously
- Instruction-tuned for task-specific query formatting
Use Cases on Mixpeek
Benchmarks
| Dataset | Metric | Score | Source |
|---|---|---|---|
| MTEB English (avg) | Score | 72.31 | Model card |
| MTEB Retrieval | NDCG@10 | 62.84 | Model card |
Performance
Common Pipeline Companions
Explore on Mixpeek
Compare alternatives in this category
Hand-picked tools & platforms compared
Deep-dive technical guide
See how Mixpeek runs models as extractors
Store & search embeddings at scale
Usage-based pricing for pipelines
Compare models, APIs & infrastructure
Specification
Research Paper
Model paper or technical report
arxiv.orgBuild a pipeline with NV-Embed-v2
Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.
Run on your data, free