The guide to snowflake-arctic-embed-l-v2.0| Snowflake

All models
Snowflake / snowflake-arctic-embed-l-v2.0

Snowflake / snowflake-arctic-embed-l-v2.0

AI Model Milvus Integrated

Task: Embedding

Modality: Text

Similarity Metric: IP, L1, L2, Cosine

License: Apache 2.0

Dimensions: 1024

Max Input Tokens: 8192

Price: Free

Introduction to snowflake-arctic-embed-l-v2.0

The snowflake-arctic-embed-l-v2.0 model is a multilingual text embedding model supporting 74 languages, designed to deliver high-quality retrieval and efficient inference across both English and non-English tasks. With 303M non-embedding parameters, it provides fast, scalable inference and supports compact representations through Matryoshka Representation Learning and quantization-aware training.

Compare snowflake-arctic-embed-l-v2.0 with snowflake-arctic-l models:

Model	params	non-emb params	dimensions	Language support
snowflake-arctic-l-v2.0	568M	303M	1024	multilingual
snowflake-arctic-l	335M	303M	1024	English-only

How to create embeddings with snowflake-arctic-embed-l-v2.0

There are two primary ways to generate vector embeddings:

PyMilvus: the Python SDK for Milvus that seamlessly integrates the snowflake-arctic-embed-l-v2.0 model.
The AI_EMBED function provided by Snowflake Cortex for text and images.

Once the vector embeddings are generated, they can be stored in Zilliz Cloud (a fully managed vector database service powered by Milvus) and used for semantic similarity search. Here are four key steps:

Sign up for a Zilliz Cloud account for free.
Set up a serverless cluster and obtain the Public Endpoint and API Key.
Create a vector collection and insert your vector embeddings.
Run a semantic search on the stored embeddings.

Create embeddings via PyMilvus and insert them into Zilliz Cloud for semantic search

from pymilvus.model.dense import SentenceTransformerEmbeddingFunction
from pymilvus import MilvusClient

# Load the Snowflake Arctic Embed L v2.0 model
ef = SentenceTransformerEmbeddingFunction(
    "Snowflake/snowflake-arctic-embed-l-v2.0", trust_remote_code=True
)

docs = [
    "Artificial intelligence was founded as an academic discipline in 1956.",
    "Alan Turing was the first person to conduct substantial research in AI.",
    "Born in Maida Vale, London, Turing was raised in southern England.",
]

# Generate embeddings for documents
docs_embeddings = ef(docs)

queries = ["When was artificial intelligence founded", "Where was Alan Turing born?"]

# Generate embeddings for queries
query_embeddings = ef(queries)

# Connect to Zilliz Cloud with Public Endpoint and API Key
client = MilvusClient(uri=ZILLIZ_PUBLIC_ENDPOINT, token=ZILLIZ_API_KEY)

COLLECTION = "arctic_embed_l_v2_documents"

# Drop collection if it exists
if client.has_collection(collection_name=COLLECTION):
    client.drop_collection(collection_name=COLLECTION)

# Create collection with auto-detected dimension
client.create_collection(collection_name=COLLECTION, dimension=ef.dim, auto_id=True)

# Insert documents with embeddings
for doc, embedding in zip(docs, docs_embeddings):
    client.insert(COLLECTION, {"text": doc, "vector": embedding})

# Search for similar documents
results = client.search(
    collection_name=COLLECTION,
    data=query_embeddings,
    # consistency_level="Strong",  # Strong consistency ensures accurate results but may increase latency
    output_fields=["text"],
    limit=2,
)

# Print search results
for i, query in enumerate(queries):
    print(f"\nQuery: {query}")
    for result in results[i]:
        print(f"  - {result['entity']['text']} (distance: {result['distance']:.4f})")