nomic-embed-text-v1

El método más sencillo para empezar con Nomic Embed es a través de la Nomic Embedding API. Generar embeddings con el cliente de Python de nomic es tan fácil como:

from nomic import embed

output = embed.text(
  texts=['Nomic Embedding API', '#keepAIOpen'],
  model='nomic-embed-text-v1',
  task_type='search_document'
)

print(output)

Para más información, consulte la referencia de API.

Sentence Transformers

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True)
sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']
embeddings = model.encode(sentences)
print(embeddings)

Transformers

import torch
import torch.nn.functional as F
from transformers import AutoTokenizer, AutoModel

def mean_pooling(model_output, attention_mask):
  token_embeddings = model_output[0]
  input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
  return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']

tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True)
model.eval()

encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

with torch.no_grad():
  model_output = model(**encoded_input)

embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
embeddings = F.normalize(embeddings, p=2, dim=1)
print(embeddings)

El modelo soporta nativamente el escalado de la longitud de la secuencia más allá de 2048 tokens. Para hacerlo,

- tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
+ tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192)

- model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True)
+ model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True, rotary_scaling_factor=2)

Transformers.js

import { pipeline } from '@xenova/transformers';

// Crear un pipeline de extracción de características
const extractor = await pipeline('feature-extraction', 'nomic-ai/nomic-embed-text-v1', {
  quantized: false, // Comentario esta línea para usar la versión cuantificada
});

// Calcular embeddings de oraciones
const texts = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'];
const embeddings = await extractor(texts, { pooling: 'mean', normalize: true });
console.log(embeddings);