Mixedbread AI 嵌入模型¶

探索 MixedBread AI 嵌入模型的强大功能，支持自定义编码格式（二进制、整型、浮点型、base64 等）、嵌入维度（Matryoshka 嵌套式）以及上下文提示。

如果您在 Colab 上打开此 Notebook，可能需要安装 LlamaIndex 🦙。

In [ ]:

%pip install llama-index-embeddings-mixedbreadai

%pip install llama-index-embeddings-mixedbreadai

In [ ]:

!pip install llama-index

!pip install llama-index

In [ ]:

import os
from llama_index.embeddings.mixedbreadai import MixedbreadAIEmbedding
from llama_index.embeddings.mixedbreadai import EncodingFormat

import os from llama_index.embeddings.mixedbreadai import MixedbreadAIEmbedding from llama_index.embeddings.mixedbreadai import EncodingFormat

In [ ]:

# API Key and Embedding Initialization

# You can visit https://www.mixedbread.ai/api-reference#quick-start-guide
# to get an api key
mixedbread_api_key = os.environ.get("MXBAI_API_KEY", "your-api-key")

# Please check https://www.mixedbread.ai/docs/embeddings/models#whats-new-in-the-mixedbread-embed-model-family
# for our embedding models
model_name = "mixedbread-ai/mxbai-embed-large-v1"

# API Key and Embedding Initialization # You can visit https://www.mixedbread.ai/api-reference#quick-start-guide # to get an api key mixedbread_api_key = os.environ.get("MXBAI_API_KEY", "your-api-key") # Please check https://www.mixedbread.ai/docs/embeddings/models#whats-new-in-the-mixedbread-embed-model-family # for our embedding models model_name = "mixedbread-ai/mxbai-embed-large-v1"

In [ ]:

oven = MixedbreadAIEmbedding(api_key=mixedbread_api_key, model_name=model_name)

embeddings = oven.get_query_embedding("Why bread is so tasty?")

print(len(embeddings))
print(embeddings[:5])

oven = MixedbreadAIEmbedding(api_key=mixedbread_api_key, model_name=model_name) embeddings = oven.get_query_embedding("Why bread is so tasty?") print(len(embeddings)) print(embeddings[:5])

1024
[0.011276245, 0.0309906, -0.0060424805, 0.029174805, -0.03857422]

使用提示语实现上下文嵌入¶

提示语能够增强模型对嵌入向量在后续任务中应用方式的理解，从而提升性能表现。我们的实验表明，采用特定领域提示语可显著提高模型效果。

In [ ]:

prompt_for_retrieval = (
    "Represent this sentence for searching relevant passages:"
)

contextual_oven = MixedbreadAIEmbedding(
    api_key=mixedbread_api_key,
    model_name=model_name,
    prompt=prompt_for_retrieval,
)

contextual_embeddings = contextual_oven.get_query_embedding(
    "What bread is invented in Germany?"
)

print(len(contextual_embeddings))
print(contextual_embeddings[:5])

prompt_for_retrieval = ( "Represent this sentence for searching relevant passages:" ) contextual_oven = MixedbreadAIEmbedding( api_key=mixedbread_api_key, model_name=model_name, prompt=prompt_for_retrieval, ) contextual_embeddings = contextual_oven.get_query_embedding( "What bread is invented in Germany?" ) print(len(contextual_embeddings)) print(contextual_embeddings[:5])

1024
[-0.023544312, -0.015213013, 0.008407593, 0.00340271, -0.044708252]

量化与套娃嵌入支持¶

Mixedbread AI 的嵌入模型支持量化和套娃技术，可在保留大部分性能的同时缩减嵌入向量尺寸以优化存储效率。更多技术细节请参阅以下文章：

• 二值化与标量嵌入量化：实现更快速、更低成本的检索
• 每个嵌入仅占64字节，哟吼！

使用不同的编码格式¶

默认的 encoding_format 为 float。我们还支持 float16、binary、ubinary、int8、uint8 和 base64 格式。

In [ ]:

# with `binary` embedding types
binary_oven = MixedbreadAIEmbedding(
    api_key=mixedbread_api_key,
    model_name=model_name,
    encoding_format=EncodingFormat.BINARY,
)

binary_embeddings = binary_oven.get_text_embedding(
    "The bread is tiny but still filling!"
)

print(len(binary_embeddings))
print(binary_embeddings[:5])

# with `binary` embedding types binary_oven = MixedbreadAIEmbedding( api_key=mixedbread_api_key, model_name=model_name, encoding_format=EncodingFormat.BINARY, ) binary_embeddings = binary_oven.get_text_embedding( "The bread is tiny but still filling!" ) print(len(binary_embeddings)) print(binary_embeddings[:5])

128
[-121.0, 96.0, -108.0, 111.0, 110.0]

使用不同的嵌入维度¶

Mixedbread AI 的嵌入模型支持 Matryoshka 维度截断技术，默认维度设置为模型的最大值。请持续关注我们的官网，了解哪些模型支持 Matryoshka 功能。

In [ ]:

# with truncated dimension
half_oven = MixedbreadAIEmbedding(
    api_key=mixedbread_api_key,
    model_name=model_name,
    dimensions=512,  # 1024 is the maximum of `mxbai-embed-large-v1`
)

half_embeddings = half_oven.get_text_embedding(
    "I want the better half of my bread."
)

print(len(half_embeddings))
print(half_embeddings[:5])

# with truncated dimension half_oven = MixedbreadAIEmbedding( api_key=mixedbread_api_key, model_name=model_name, dimensions=512, # 1024 is the maximum of `mxbai-embed-large-v1` ) half_embeddings = half_oven.get_text_embedding( "I want the better half of my bread." ) print(len(half_embeddings)) print(half_embeddings[:5])

512
[-0.014221191, -0.013671875, -0.03314209, 0.025909424, -0.035095215]