snowflake-arctic-embed-m-v2.0

from sentence_transformers import SentenceTransformer

# Load the model
model_name = 'Snowflake/snowflake-arctic-embed-m-v2.0'
model = SentenceTransformer(model_name, trust_remote_code=True)

# Define the queries and documents
queries = ['what is snowflake?', 'Where can I get the best tacos?']
documents = ['The Data Cloud!', 'Mexico City of Course!']

# Compute embeddings: use `prompt_name="query"` to encode queries!
query_embeddings = model.encode(queries, prompt_name="query") 
document_embeddings = model.encode(documents)

# Compute cosine similarity scores
scores = model.similarity(query_embeddings, document_embeddings)

# Output the results
for query, query_scores in zip(queries, scores):
    doc_score_pairs = list(zip(documents, query_scores))
    doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
    print("Query:", query)
    for document, score in doc_score_pairs:
        print(score, document)

import torch
from transformers import AutoModel, AutoTokenizer

model_name = 'Snowflake/snowflake-arctic-embed-m-v2.0'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, add_pooling_layer=False, trust_remote_code=True)
model.eval()

query_prefix = 'query: '
queries  = ['what is snowflake?', 'Where can I get the best tacos?']
queries_with_prefix = ["{}{}".format(query_prefix, i) for i in queries]
query_tokens = tokenizer(queries_with_prefix, padding=True, truncation=True, return_tensors='pt', max_length=8192)

documents = ['The Data Cloud!', 'Mexico City of Course!']
document_tokens =  tokenizer(documents, padding=True, truncation=True, return_tensors='pt', max_length=8192)

# Compute token embeddings
with torch.no_grad():
    query_embeddings = model(**query_tokens)[0][:, 0]
    document_embeddings = model(**document_tokens)[0][:, 0]


# normalize embeddings
query_embeddings = torch.nn.functional.normalize(query_embeddings, p=2, dim=1)
document_embeddings = torch.nn.functional.normalize(document_embeddings, p=2, dim=1)

scores = torch.mm(query_embeddings, document_embeddings.transpose(0, 1))
for query, query_scores in zip(queries, scores):
    doc_score_pairs = list(zip(documents, query_scores))
    doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
    #Output passages & scores
    print("Query:", query)
    for document, score in doc_score_pairs:
        print(score, document)

npm i @huggingface/transformers

import { pipeline, dot } from '@huggingface/transformers';

// Create feature extraction pipeline
const extractor = await pipeline('feature-extraction', 'Snowflake/snowflake-arctic-embed-m-v2.0');

// Generate sentence embeddings
const sentences = [
    'query: what is snowflake?',
    'The Data Cloud!',
    'Mexico City of Course!',
]
const output = await extractor(sentences, { normalize: true, pooling: 'cls' });

// Compute similarity scores
const [source_embeddings, ...document_embeddings ] = output.tolist();
const similarities = document_embeddings.map(x => dot(source_embeddings, x));
console.log(similarities); // [0.32719788157046004, 0.06960141111667434]