mxbai-embed-2d-large-v1

python -m pip install -U sentence-transformers

from sentence_transformers import models, SentenceTransformer
from sentence_transformers.util import cos_sim

# 1. load model with `cls` pooling
model = SentenceTransformer("mixedbread-ai/mxbai-embed-2d-large-v1")

# 2. set adaptive layer and embedding size.
# it is recommended to set layers from 20 to 24.
new_num_layers = 22  # 1D: set layer size
model[0].auto_model.encoder.layer = model[0].auto_model.encoder.layer[:new_num_layers]

new_embedding_size = 768  # 2D: set embedding size

# 3. encode
embeddings = model.encode(
    [
        'Who is german and likes bread?',
        'Everybody in Germany.'
    ]
)

# Similarity of the first sentence with the other two
similarities = cos_sim(embeddings[0, :new_embedding_size], embeddings[1, :new_embedding_size])

print('similarities:', similarities)

python -m pip install -U angle-emb

from angle_emb import AnglE
from sentence_transformers.util import cos_sim

# 1. load model
model = AnglE.from_pretrained("mixedbread-ai/mxbai-embed-2d-large-v1", pooling_strategy='cls').cuda()

# 2. set adaptive layer and embedding size.
# it is recommended to set layers from 20 to 24.
layer_index = 22  # 1d: layer
embedding_size = 768  # 2d: embedding size

# 3. encode
embeddings = model.encode([
    'Who is german and likes bread?',
    'Everybody in Germany.'
], layer_index=layer_index, embedding_size=embedding_size)

similarities = cos_sim(embeddings[0], embeddings[1:])
print('similarities:', similarities)

npm i @xenova/transformers

import { pipeline, cos_sim } from '@xenova/transformers';
// Create a feature-extraction pipeline
const extractor = await pipeline('feature-extraction', 'mixedbread-ai/mxbai-embed-2d-large-v1', {
    quantized: false, // (Optional) remove this line to use the 8-bit quantized model
});

// Compute sentence embeddings (with `cls` pooling)
const sentences = ['Who is german and likes bread?', 'Everybody in Germany.' ];
const output = await extractor(sentences, { pooling: 'cls' });

// Set embedding size and truncate embeddings
const new_embedding_size = 768;
const truncated = output.slice(null, [0, new_embedding_size]);

// Compute cosine similarity
console.log(cos_sim(truncated[0].data, truncated[1].data)); // 0.6979532021425204

from mixedbread_ai.client import MixedbreadAI
from sklearn.metrics.pairwise import cosine_similarity
import os

mxbai = MixedbreadAI(api_key="{MIXEDBREAD_API_KEY}")

english_sentences = [
    'What is the capital of Australia?',
    'Canberra is the capital of Australia.'
] 

res = mxbai.embeddings(
     input=english_sentences,
     model="mixedbread-ai/mxbai-embed-2d-large-v1",
     dimensions=512,
)
embeddings = [entry.embedding for entry in res.data]

similarities = cosine_similarity([embeddings[0]], [embeddings[1]])
print(similarities)