nomic-embed-text-v1

La forma más fácil de empezar con Nomic Embed es a través de la API de Embedding de Nomic. Generar embeddings con el cliente de Python de nomic es tan simple 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 API.

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?']


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

Transformers.js

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

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

// Compute sentence embeddings
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);