python -m pip install -U sentence-transformers

from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
from sentence_transformers.quantization import quantize_embeddings

# 1. Specify preffered dimensions
dimensions = 512

# 2. load model
model = SentenceTransformer("mixedbread-ai/mxbai-embed-large-v1", truncate_dim=dimensions)

# The prompt used for query retrieval tasks:
# query_prompt = 'Represent this sentence for searching relevant passages: '

query = "A man is eating a piece of bread"
docs = [
    "A man is eating food.",
    "A man is eating pasta.",
    "The girl is carrying a baby.",
    "A man is riding a horse.",
]

# 2. Encode
query_embedding = model.encode(query, prompt_name="query")
# Equivalent Alternatives:
# query_embedding = model.encode(query_prompt + query)
# query_embedding = model.encode(query, prompt=query_prompt)

docs_embeddings = model.encode(docs)

# Optional: Quantize the embeddings
binary_query_embedding = quantize_embeddings(query_embedding, precision="ubinary")
binary_docs_embeddings = quantize_embeddings(docs_embeddings, precision="ubinary")

similarities = cos_sim(query_embedding, docs_embeddings)
print('similarities:', similarities)

from typing import Dict

import torch
import numpy as np
from transformers import AutoModel, AutoTokenizer
from sentence_transformers.util import cos_sim

# For retrieval you need to pass this prompt. Please find our more in our blog post.
def transform_query(query: str) -> str:
    """ For retrieval, add the prompt for query (not for documents).
    """
    return f'Represent this sentence for searching relevant passages: {query}'

# The model works really well with cls pooling (default) but also with mean pooling.
def pooling(outputs: torch.Tensor, inputs: Dict,  strategy: str = 'cls') -> np.ndarray:
    if strategy == 'cls':
        outputs = outputs[:, 0]
    elif strategy == 'mean':
        outputs = torch.sum(
            outputs * inputs["attention_mask"][:, :, None], dim=1) / torch.sum(inputs["attention_mask"], dim=1, keepdim=True)
    else:
        raise NotImplementedError
    return outputs.detach().cpu().numpy()

# 1. load model
model_id = 'mixedbread-ai/mxbai-embed-large-v1'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModel.from_pretrained(model_id).cuda()


docs = [
    transform_query('A man is eating a piece of bread'),
    "A man is eating food.",
    "A man is eating pasta.",
    "The girl is carrying a baby.",
    "A man is riding a horse.",
]

# 2. encode
inputs = tokenizer(docs, padding=True, return_tensors='pt')
for k, v in inputs.items():
    inputs[k] = v.cuda()
outputs = model(**inputs).last_hidden_state
embeddings = pooling(outputs, inputs, 'cls')

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

npm i @huggingface/transformers

import { pipeline, cos_sim } from "@huggingface/transformers";

// Create a feature extraction pipeline
const extractor = await pipeline("feature-extraction", "mixedbread-ai/mxbai-embed-large-v1", {
    dtype: "fp32", // Options: "fp32", "fp16", "q8"
});

// Generate sentence embeddings
const docs = [
    "Represent this sentence for searching relevant passages: A man is eating a piece of bread",
    "A man is eating food.",
    "A man is eating pasta.",
    "The girl is carrying a baby.",
    "A man is riding a horse.",
]
const output = await extractor(docs, { pooling: "cls" });

// Compute similarity scores
const [source_embeddings, ...document_embeddings ] = output.tolist();
const similarities = document_embeddings.map(x => cos_sim(source_embeddings, x));
console.log(similarities); // [0.7919578577247139, 0.6369278664248345, 0.16512018371357193, 0.3620778366720027]

from mixedbread_ai.client import MixedbreadAI, EncodingFormat
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-large-v1",
     normalized=True,
     encoding_format=[EncodingFormat.FLOAT, EncodingFormat.UBINARY, EncodingFormat.INT_8],
     dimensions=512
)

encoded_embeddings = res.data[0].embedding
print(res.dimensions, encoded_embeddings.ubinary, encoded_embeddings.float_, encoded_embeddings.int_8)

docker run --gpus all -v $PWD/data:/app/.cache -p "7997":"7997" \
michaelf34/infinity:0.0.68 \
v2 --model-id mixedbread-ai/mxbai-embed-large-v1 --revision "main" --dtype float16 --engine torch --port 7997

@online{emb2024mxbai,
  title={Open Source Strikes Bread - New Fluffy Embeddings Model},
  author={Sean Lee and Aamir Shakir and Darius Koenig and Julius Lipp},
  year={2024},
  url={https://www.mixedbread.ai/blog/mxbai-embed-large-v1},
}

@article{li2023angle,
  title={AnglE-optimized Text Embeddings},
  author={Li, Xianming and Li, Jing},
  journal={arXiv preprint arXiv:2309.12871},
  year={2023}
}