bobo

<img src="assets/project_bobo.png" alt="Preview" width="1000" height="100"/>

• Bobo — Embedding Model (derived from mixedbread-ai/mxbai-embed-large-v1)

Bobo is a text-embedding, LLM derived from mixedbread-ai/mxbai-embed-large-v1, packaged for drop-in use in semantic search, RAG (Retrieval-Augmented Generation), clustering, deduplication, and zero-shot classification. It produces dense vector representations suitable for ANN indexes (FAISS, ScaNN, Milvus, pgvector) and common retrieval stacks.

Key Features

• Derived from the proven mixedbread-ai/mxbai-embed-large-v1 embedding family.
• Strong performance on retrieval-style tasks (semantic search, RAG, clustering).
• Sentence-Transformers–compatible API for fast adoption.
• Mean pooling with optional L2 normalization for cosine similarity workflows.
• Production-friendly guidance on chunking, batching, and indexing.

Technical Specifications

Tip: Always detect the dimension in code (see Quickstart) and configure your index accordingly.

🎯 Quickstart

• Here, we provide several ways to produce sentence embeddings. Please note that you have to provide the prompt Represent this sentence for searching relevant passages: for query if you want to use it for retrieval. Besides that you don't need any prompt.

⚙️ Fine-Tuneing Datasets

🏗️ Sentence Transformers

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("bobo/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)

🧠 Transformers

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 = 'bobo/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)

🏁 Evaluation

As of March 2024, our model archives SOTA performance for Bert-large sized models on the MTEB. It ourperforms commercial models like OpenAIs text-embedding-3-large and matches the performance of model 20x it's size like the echo-mistral-7b. Our model was trained with no overlap of the MTEB data, which indicates that our model generalizes well across several domains, tasks and text length. We know there are some limitations with this model, which will be fixed in v2.

💻 Matryoshka and Binary Quantization

Embeddings in their commonly used form (float arrays) have a high memory footprint when used at scale. Two approaches to solve this problem are Matryoshka Representation Learning (MRL) and (Binary) Quantization. While MRL reduces the number of dimensions of an embedding, binary quantization transforms the value of each dimension from a float32 into a lower precision (int8 or even binary). <b> The model supports both approaches! </b>

You can also take it one step further, and combine both MRL and quantization. This combination of binary quantization and MRL allows you to reduce the memory usage of your embeddings significantly. This leads to much lower costs when using a vector database in particular.

📝License

• Bobo is published under the MIT General Public License v3