intelli-embed-v2

intelli-embed-v2

The best-performing local embedding model for GraphRAG and memory-augmented AI applications.

Built for apps that store, retrieve, and deduplicate personal memories in graph databases — intelli-embed-v2 achieves 98% of Azure text-embedding-3-small quality while running entirely on-device at ~10 ms per embedding. No API calls, no rate limits, no data leaving your infrastructure.

Training

Fine-tuned from Snowflake/snowflake-arctic-embed-l-v2.0 using a three-phase curriculum that distills knowledge from Azure text-embedding-3-large across 200k real-world sentences.

Three-phase curriculum fine-tuning on arctic-l-v2:

Usage

With sentence-transformers

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("serhiiseletskyi/intelli-embed-v2")
embeddings = model.encode(["Hello world", "Another sentence"])
print(embeddings.shape)  # (2, 1024)

With ONNX Runtime (INT8, recommended for CPU inference)

import onnxruntime as ort
from transformers import AutoTokenizer
import numpy as np

tokenizer = AutoTokenizer.from_pretrained("serhiiseletskyi/intelli-embed-v2")
session = ort.InferenceSession("onnx/model_quantized.onnx")

def embed(texts):
    enc = tokenizer(texts, padding=True, truncation=True, max_length=512, return_tensors="np")
    out = session.run(None, {"input_ids": enc["input_ids"], "attention_mask": enc["attention_mask"]})[0]
    # mean pool + L2 normalize
    mask = enc["attention_mask"][..., None].astype(np.float32)
    pooled = (out * mask).sum(1) / mask.sum(1)
    return pooled / np.linalg.norm(pooled, axis=1, keepdims=True)

vecs = embed(["Hello world", "Another sentence"])
print(vecs.shape)  # (2, 1024)

With ort-node (Node.js / TypeScript)

import * as ort from "onnxruntime-node";
import { AutoTokenizer } from "@huggingface/transformers";

const tokenizer = await AutoTokenizer.from_pretrained("serhiiseletskyi/intelli-embed-v2");
const session = await ort.InferenceSession.create("onnx/model_quantized.onnx");

async function embed(texts: string[]): Promise<number[][]> {
  const enc = await tokenizer(texts, { padding: true, truncation: true, max_length: 512 });
  const inputIds = new ort.Tensor("int64", enc.input_ids.data, enc.input_ids.dims);
  const attentionMask = new ort.Tensor("int64", enc.attention_mask.data, enc.attention_mask.dims);
  const result = await session.run({ input_ids: inputIds, attention_mask: attentionMask });
  // result["last_hidden_state"] → mean pool → L2 normalize
  // ...
  return vectors;
}

Files

Benchmark Results (run15, 2026-02-23)

Evaluated on a 6-suite benchmark including SW-engineering pairs, memory-domain pairs, dedup fitness, asymmetric retrieval, negation safety, and entity description retrieval.

Sep = mean(PosSim) − mean(NegSim) on SW-engineering pairs — higher is better.

OpenMemory Use-Case Metrics

License

Apache 2.0 — inherited from base model Snowflake/snowflake-arctic-embed-l-v2.0.