Unstructured

pip install unstructured unstructured[embed-mixedbreadai]

import os
os.environ["MXBAI_API_KEY"] = "your_api_key_here"

import os
from unstructured.embed.mixedbreadai import (
    MixedbreadAIEmbeddingConfig,
    MixedbreadAIEmbeddingEncoder,
)
from unstructured.documents.elements import Text
 
embedding_encoder = MixedbreadAIEmbeddingEncoder(
    config=MixedbreadAIEmbeddingConfig(
        api_key=os.getenv("MXBAI_API_KEY"),
        model_name="mixedbread-ai/mxbai-embed-large-v1",
    )
)
 
elements = embedding_encoder.embed_documents(
    elements=[Text("Bread is life"), Text("Bread is love")]
)
 
query = "Represent this sentence for searching relevant passages: What is bread?"
query_embedding = embedding_encoder.embed_query(query)
 
[print(element.embedding) for element in elements]
print(query_embedding)
print(embedding_encoder.is_unit_vector, embedding_encoder.num_of_dimensions)

import os
from unstructured.embed.mixedbreadai import (
    MixedbreadAIEmbeddingConfig,
    MixedbreadAIEmbeddingEncoder,
)
from unstructured.documents.elements import Text
 
embeddings = MixedbreadAIEmbeddingEncoder(
    config=MixedbreadAIEmbeddingConfig(
        api_key=os.getenv("MXBAI_API_KEY"),
        model_name="mixedbread-ai/mxbai-embed-large-v1",
        batch_size=64,
        normalized=True,
        dimensions=512,
        encoding_format="binary"
    )
)
 
elements = embedding_encoder.embed_documents(
    elements=[Text("Bread is life"), Text("Bread is love")]
)
 
query = "Represent this sentence for searching relevant passages: What is bread?"
query_embedding = embedding_encoder.embed_query(query)
 
[print(element.embedding) for element in elements]
print(query_embedding)
print(embedding_encoder.is_unit_vector, embedding_encoder.num_of_dimensions)