jina-embeddings-v2-base-es is a Spanish/English bilingual text embedding model supporting 8192 sequence length. It is based on a BERT architecture (JinaBERT) that supports the symmetric bidirectional variant of ALiBi to allow longer sequence length. We have designed it for high performance in mono-lingual & cross-lingual applications and trained it specifically to support mixed Spanish-English input without bias. Additionally, we provide the following embedding models:

jina-embeddings-v2-base-es es un modelo (embedding) de texto bilingüe Inglés/Español que admite una longitud de secuencia de 8192. Se basa en la arquitectura BERT (JinaBERT) que incorpora la variante bi-direccional simétrica de ALiBi para permitir una mayor longitud de secuencia. Hemos diseñado este modelo para un alto rendimiento en aplicaciones monolingües y bilingües, y está entrenando específicamente para admitir entradas mixtas de español e inglés sin sesgo. Adicionalmente, proporcionamos los siguientes modelos (embeddings):

jina-embeddings-v2-small-en: 33 million parameters.
jina-embeddings-v2-base-en: 137 million parameters.
jina-embeddings-v2-base-zh: Chinese-English Bilingual embeddings.
jina-embeddings-v2-base-de: German-English Bilingual embeddings.
jina-embeddings-v2-base-es: Spanish-English Bilingual embeddings (you are here).

Data & Parameters

The data and training details are described in this technical report

Usage

Please apply mean pooling when integrating the model.

Why mean pooling?

mean pooling takes all token embeddings from model output and averaging them at sentence/paragraph level. It has been proved to be the most effective way to produce high-quality sentence embeddings. We offer an encode function to deal with this.

However, if you would like to do it without using the default encode function:

python

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 = ['How is the weather today?', 'What is the current weather like today?']

tokenizer = AutoTokenizer.from_pretrained('jinaai/jina-embeddings-v2-base-es')
model = AutoModel.from_pretrained('jinaai/jina-embeddings-v2-base-es', trust_remote_code=True)

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)

You can use Jina Embedding models directly from the transformers package:

python

!pip install transformers
from transformers import AutoModel
from numpy.linalg import norm

cos_sim = lambda a,b: (a @ b.T) / (norm(a)*norm(b))
model = AutoModel.from_pretrained('jinaai/jina-embeddings-v2-base-es', trust_remote_code=True) # trust_remote_code is needed to use the encode method
embeddings = model.encode(['How is the weather today?', '¿Qué tiempo hace hoy?'])
print(cos_sim(embeddings[0], embeddings[1]))

If you only want to handle shorter sequence, such as 2k, pass the max_length parameter to the encode function:

python

embeddings = model.encode(
    ['Very long ... document'],
    max_length=2048
)

Or you can use the model with the sentence-transformers package:

python

from sentence_transformers import SentenceTransformer, util

model = SentenceTransformer("jinaai/jina-embeddings-v2-base-es", trust_remote_code=True)
embeddings = model.encode(['How is the weather today?', '¿Qué tiempo hace hoy?'])
print(util.cos_sim(embeddings[0], embeddings[1]))

And if you only want to handle shorter sequence, such as 2k, then you can set the model.max_seq_length

model.max_seq_length = 2048

Alternatives to Transformers and Sentence Transformers

Managed SaaS: Get started with a free key on Jina AI's Embedding API.
Private and high-performance deployment: Get started by picking from our suite of models and deploy them on AWS Sagemaker.

Use Jina Embeddings for RAG

According to the latest blog post from LLamaIndex,

In summary, to achieve the peak performance in both hit rate and MRR, the combination of OpenAI or JinaAI-Base embeddings with the CohereRerank/bge-reranker-large reranker stands out.

Plans

Bilingual embedding models supporting more European & Asian languages, including French, Italian and Japanese.
Multimodal embedding models enable Multimodal RAG applications.
High-performt rerankers.

Contact

Join our Discord community and chat with other community members about ideas.

Citation

If you find Jina Embeddings useful in your research, please cite the following paper:

@article{mohr2024multi,
  title={Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings},
  author={Mohr, Isabelle and Krimmel, Markus and Sturua, Saba and Akram, Mohammad Kalim and Koukounas, Andreas and G{\"u}nther, Michael and Mastrapas, Georgios and Ravishankar, Vinit and Mart{\'\i}nez, Joan Fontanals and Wang, Feng and others},
  journal={arXiv preprint arXiv:2402.17016},
  year={2024}
}