nomic-embed-text-v1.5

Ejemplos de usos

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True)
sentences = ['search_document: TSNE es un algoritmo de reducción de dimensionalidad creado por Laurens van Der Maaten']
embeddings = model.encode(sentences)
print(embeddings)

from transformers import AutoTokenizer, AutoModel
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, rotary_scaling_factor=2)
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.layer_norm(embeddings, normalized_shape=(embeddings.shape[1],))
    embeddings = embeddings[:, :matryoshka_dim]
    embeddings = F.normalize(embeddings, p=2, dim=1)
    print(embeddings)

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

const extractor = await pipeline('feature-extraction', 'nomic-ai/nomic-embed-text-v1.5', {
    quantized: false,
});

const texts = ['search_query: ¿Qué es TSNE?', 'search_query: ¿Quién es Laurens van der Maaten?'];

let embeddings = await extractor(texts, { pooling: 'mean' });
console.log(embeddings);

const matryoshka_dim = 512;
embeddings = layer_norm(embeddings, [embeddings.dims[1]]).slice(null, [0, matryoshka_dim]).normalize(2, -1);
console.log(embeddings.tolist());