Snowflake Arctic-embed-m-v1.5

import torch
from sentence_transformers import SentenceTransformer
from torch.nn.functional import normalize
# Model constant.
MODEL_ID = "Snowflake/snowflake-arctic-embed-m-v1.5"
# Your queries and docs.
queries = ['what is snowflake?', '¿Dónde puedo conseguir los mejores tacos?']
documents = ['The Data Cloud!', '¡Ciudad de México, por supuesto!']
# Load the model.
model = SentenceTransformer(
MODEL_ID, model_kwargs=dict(add_pooling_layer=False),
)
# Generate text embeddings.
query_embeddings = model.encode(queries, prompt_name="query")
document_embeddings = model.encode(documents)
# Scores via dotproduct.
scores = query_embeddings @ document_embeddings.T
# Pretty-print 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(f'Query: "{query}"')
for document, score in doc_score_pairs:
print(f'Score: {score:.4f} | Document: "{document}"')
print()

import torch
from torch.nn.functional import normalize
from transformers import AutoModel, AutoTokenizer
# Model constants.
MODEL_ID = "Snowflake/snowflake-arctic-embed-m-v1.5"
QUERY_PREFIX = 'Representa esta oración para buscar pasajes relevantes: '
# Your queries and docs.
queries  = ['what is snowflake?', '¿Dónde puedo conseguir los mejores tacos?']
documents = ['The Data Cloud!', '¡Ciudad de México, por supuesto!']
# Load the model and tokenizer.
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModel.from_pretrained(MODEL_ID, add_pooling_layer=False)
model.eval()
# Add query prefix and tokenize queries and docs.
queries_with_prefix = [f"{QUERY_PREFIX}{q}" for q in queries]
query_tokens = tokenizer(queries_with_prefix, padding=True, truncation=True, return_tensors='pt', max_length=512)
document_tokens =  tokenizer(documents, padding=True, truncation=True, return_tensors='pt', max_length=512)
# Use the model to generate text embeddings.
with torch.inference_mode():
query_embeddings = model(**query_tokens)[0][:, 0]
document_embeddings = model(**document_tokens)[0][:, 0]
# Remember to normalize embeddings.
query_embeddings = normalize(query_embeddings)
document_embeddings = normalize(document_embeddings)
# Scores via dotproduct.
scores = query_embeddings @ document_embeddings.T
# Pretty-print 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(f'Query: "{query}"')
for document, score in doc_score_pairs:
print(f'Score: {score:.4f} | Document: "{document}"')
print()