mxbai-embed-large-v1

Model Description

mxbai-embed-large-v1 is our powerful English embedding model that provides state-of-the-art performance among efficiently sized models. It outperforms closed source models like OpenAI's text-embedding-ada-002.

The model was trained on a vast dataset of over 700 million pairs using contrastive training and fine-tuned on more than 30 million high-quality triplets using the AnglE loss function. This extensive training enables the model to adapt to a wide range of topics and domains, making it suitable for various real-world applications and Retrieval-Augmented Generation (RAG) use cases.

mxbai-embed-large-v1 is well-suited for binary embeddings. This helps you save 32x storage and achieve 40x faster retrieval, while maintaining over 96% of the performance.

mxbai-embed-large-v1 achieves top performance on the Massive Text Embedding Benchmark (MTEB), which measures embedding models across seven tasks: classification, clustering, pair classification, re-ranking, retrieval, semantic textual similarity, and summarization. The model's strong performance across these diverse tasks demonstrates its versatility and robustness.

Using a Prompt

Adding a domain-specific prompt to a text can help the model understand how the embedding will be used.

For retrieval tasks, the query can be preceded by the prompt: Represent this sentence for searching relevant passages:. For other tasks, the text can be used as-is without any additional prompt.

Suitable Scoring Methods

• Cosine Similarity: Ideal for measuring the similarity between text vectors, commonly used in tasks like semantic textual similarity and information retrieval.
• Euclidean Distance: Useful for measuring dissimilarity between embeddings, especially effective in clustering and outlier detection.
• Dot Product: Appropriate when embeddings are normalized; used in tasks where alignment of vector orientation is critical.

Limitations

• Language: mxbai-embed-large-v1 is trained on English text and is specifically designed for the English language.
• Sequence Length: The suggested maximum sequence length is 512 tokens. Longer sequences may be truncated, leading to a loss of information.

Examples

Calculate Sentence Similarities

The following code illustrates how to compute similarities between sentences using the cosine similarity score function.

from mixedbread_ai.client import MixedbreadAi
from sentence_transformers.util import cos_sim
 
mxbai = MixedbreadAI(api_key="YOUR_API_KEY")
model = "mixedbread-ai/mxbai-embed-large-v1"
 
docs = [
    "A man is eating food.",
    "A man is eating pasta.",
]
 
result = mxbai.embeddings(
    model=model,
    input=docs,
)
 
embeddings = [item.embedding for item in result.data]
 
# Calculate cosine similarity
similarity = cos_sim(embeddings[0], embeddings[1])
print(similarity)

Information Retrieval

The following code snippet demonstrates the retrieval of information related to a specific query from a given corpus. Note that the prompt Represent this sentence for searching relevant passages: is used for the query.

from mixedbread_ai.client import MixedbreadAi
from sentence_transformers.util import cos_sim
 
mxbai = MixedbreadAI(api_key="YOUR_API_KEY")
model = "mixedbread-ai/mxbai-embed-large-v1"
 
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.",
]
 
query_result = mxbai.embeddings(
    model=model,
    prompt=prompt,
    input=[query],
)
 
docs_result = mxbai.embeddings(
    model=model,
    input=docs
)
 
query_embedding = query_result.data[0].embedding
docs_embeddings = [item.embedding for item in docs_result.data]
 
# Calculate cosine similarity
similarities = cos_sim(query_embedding, docs_embeddings)
similarity_scores = similarities.squeeze().tolist()
 
# Retrieve documents sorted by similarity
retrieved_docs = sorted(zip(docs, similarity_scores), key=lambda x: x[1], reverse=True)
 
# Print the retrieved documents and their similarity scores
for doc, score in retrieved_docs:
    print(f"Document: {doc}\nSimilarity Score: {score}\n")