BaseEmbeddingEncoder

The BaseEmbeddingEncoder is an abstract base class that defines the methods to be implemented for each EmbeddingEncoder subclass.

OpenAIEmbeddingEncoder

The OpenAIEmbeddingEncoder class uses langchain OpenAI integration under the hood to connect to the OpenAI Text&Embedding API to obtain embeddings for pieces of text.

embed_documents will receive a list of Elements, and return an updated list which includes the embeddings attribute for each Element.

embed_query will receive a query as a string, and return a list of floats which is the embedding vector for the given query string.

num_of_dimensions is a metadata property that denotes the number of dimensions in any embedding vector obtained via this class.

is_unit_vector is a metadata property that denotes if embedding vectors obtained via this class are unit vectors.

The following code block shows an example of how to use OpenAIEmbeddingEncoder. You will see the updated elements list (with the embeddings attribute included for each element), the embedding vector for the query string, and some metadata properties about the embedding model. You will need to set an environment variable named OPENAI_API_KEY to be able to run this example. To obtain an api key, visit: https://platform.openai.com/account/api-keys

import os

from unstructured.documents.elements import Text
from unstructured.embed.openai import OpenAIEmbeddingConfig, OpenAIEmbeddingEncoder

# Initialize the encoder with OpenAI credentials
embedding_encoder = OpenAIEmbeddingEncoder(config=OpenAIEmbeddingConfig(api_key=os.environ["OPENAI_API_KEY"]))

# Embed a list of Elements
elements = embedding_encoder.embed_documents(
    elements=[Text("This is sentence 1"), Text("This is sentence 2")],
)

# Embed a single query string
query = "This is the query"
query_embedding = embedding_encoder.embed_query(query=query)

# Print embeddings
[print(e.embeddings, e) for e in elements]
print(query_embedding, query)
print(embedding_encoder.is_unit_vector(), embedding_encoder.num_of_dimensions())

HuggingFaceEmbeddingEncoder

The HuggingFaceEmbeddingEncoder class uses langchain HuggingFace integration under the hood to obtain embeddings for pieces of text using a local model.

embed_documents will receive a list of Elements, and return an updated list which includes the embeddings attribute for each Element.

embed_query will receive a query as a string, and return a list of floats which is the embedding vector for the given query string.

num_of_dimensions is a metadata property that denotes the number of dimensions in any embedding vector obtained via this class.

is_unit_vector is a metadata property that denotes if embedding vectors obtained via this class are unit vectors.

The following code block shows an example of how to use HuggingFaceEmbeddingEncoder. You will see the updated elements list (with the embeddings attribute included for each element), the embedding vector for the query string, and some metadata properties about the embedding model.

import os

from unstructured.documents.elements import Text
from unstructured.embed.huggingface import HuggingFaceEmbeddingConfig, HuggingFaceEmbeddingEncoder

embedding_encoder = HuggingFaceEmbeddingEncoder(
    config=HuggingFaceEmbeddingConfig()
)
elements = embedding_encoder.embed_documents(
    elements=[Text("This is sentence 1"), Text("This is sentence 2")],
)

query = "This is the query"
query_embedding = embedding_encoder.embed_query(query=query)

[print(e.embeddings, e) for e in elements]
print(query_embedding, query)
print(embedding_encoder.is_unit_vector(), embedding_encoder.num_of_dimensions())

BedrockEmbeddingEncoder

The BedrockEmbeddingEncoder class provides an interface to obtain embeddings for text using the Bedrock embeddings via the langchain integration. It connects to the Bedrock Runtime using AWS’s boto3 package.

Key methods and attributes include:

embed_documents: This function takes a list of Elements as its input and returns the same list with an updated embeddings attribute for each Element.

embed_query: This method takes a query as a string and returns the embedding vector for the given query string.

num_of_dimensions: A metadata property that signifies the number of dimensions in any embedding vector obtained via this class.

is_unit_vector: A metadata property that checks if embedding vectors obtained via this class are unit vectors.

Initialization: To create an instance of the BedrockEmbeddingEncoder, AWS credentials and the region name are required.

import os

from unstructured.documents.elements import Text
from unstructured.embed.bedrock import BedrockEmbeddingEncoder

# Initialize the encoder with AWS credentials
embedding_encoder = BedrockEmbeddingEncoder(
    aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
    aws_secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
    region_name="us-west-2",
)

# Embed a list of Elements
elements = embedding_encoder.embed_documents(elements=[Text("Sentence A"), Text("Sentence B")])

# Embed a single query string
query = "Example query"
query_embedding = embedding_encoder.embed_query(query=query)

# Print embeddings
[print(e.embeddings, e) for e in elements]
print(query_embedding, query)
print(embedding_encoder.is_unit_vector(), embedding_encoder.num_of_dimensions())

Dependencies: This class relies on several dependencies which include boto3, numpy, and langchain. Ensure these are installed and available in the environment where this class is utilized.

OctoAIEmbeddingEncoder

The OctoAIEmbeddingEncoder class connects to the OctoAI Text&Embedding API to obtain embeddings for pieces of text.

embed_documents will receive a list of Elements, and return an updated list which includes the embeddings attribute for each Element.

embed_query will receive a query as a string, and return a list of floats which is the embedding vector for the given query string.

num_of_dimensions is a metadata property that denotes the number of dimensions in any embedding vector obtained via this class.

is_unit_vector is a metadata property that denotes if embedding vectors obtained via this class are unit vectors.

The following code block shows an example of how to use OctoAIEmbeddingEncoder. You will see the updated elements list (with the embeddings attribute included for each element), the embedding vector for the query string, and some metadata properties about the embedding model. You will need to set an environment variable named OCTOAI_API_KEY to be able to run this example. To obtain an api key, visit: https://octo.ai/docs/getting-started/how-to-create-an-octoai-access-token

import os

from unstructured.documents.elements import Text
from unstructured.embed.octoai import OctoAiEmbeddingConfig, OctoAIEmbeddingEncoder

embedding_encoder = OctoAIEmbeddingEncoder(
    config=OctoAiEmbeddingConfig(api_key=os.environ["OCTOAI_API_KEY"])
)
elements = embedding_encoder.embed_documents(
    elements=[Text("This is sentence 1"), Text("This is sentence 2")],
)

query = "This is the query"
query_embedding = embedding_encoder.embed_query(query=query)

[print(e.embeddings, e) for e in elements]
print(query_embedding, query)
print(embedding_encoder.is_unit_vector(), embedding_encoder.num_of_dimensions())

VertexAIEmbeddingEncoder

The VertexAIEmbeddingEncoder class connects to the GCP VertexAI to obtain embeddings for pieces of text.

embed_documents will receive a list of Elements, and return an updated list which includes the embeddings attribute for each Element.

embed_query will receive a query as a string, and return a list of floats which is the embedding vector for the given query string.

num_of_dimensions is a metadata property that denotes the number of dimensions in any embedding vector obtained via this class.

is_unit_vector is a metadata property that denotes if embedding vectors obtained via this class are unit vectors.

The following code block shows an example of how to use VertexAIEmbeddingEncoder. You will see the updated elements list (with the embeddings attribute included for each element), the embedding vector for the query string, and some metadata properties about the embedding model.

To use Vertex AI PaLM tou will need to: - either, pass the full json content of your GCP VertexAI application credentials to the VertexAIEmbeddingConfig as the api_key parameter. (This will create a file in the /tmp directory with the content of the json, and set the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path of the created file.) - or, you’ll need to store the path to a manually created service account JSON file as the GOOGLE_APPLICATION_CREDENTIALS environment variable. (For more information: https://python.langchain.com/docs/integrations/text_embedding/google_vertex_ai_palm) - or, you’ll need to have the credentials configured for your environment (gcloud, workload identity, etc…)

import os

from unstructured.documents.elements import Text
from unstructured.embed.vertexai import VertexAIEmbeddingConfig, VertexAIEmbeddingEncoder

embedding_encoder = VertexAIEmbeddingEncoder(
    config=VertexAIEmbeddingConfig(api_key=os.environ["VERTEXAI_GCP_APP_CREDS_JSON_CONTENT"])
)
elements = embedding_encoder.embed_documents(
    elements=[Text("This is sentence 1"), Text("This is sentence 2")],
)

query = "This is the query"
query_embedding = embedding_encoder.embed_query(query=query)

[print(e.embeddings, e) for e in elements]
print(query_embedding, query)
print(embedding_encoder.is_unit_vector(), embedding_encoder.num_of_dimensions())

VoyageAIEmbeddingEncoder

The VoyageAIEmbeddingEncoder class connects to the VoyageAI to obtain embeddings for pieces of text.

embed_documents will receive a list of Elements, and return an updated list which includes the embeddings attribute for each Element.

embed_query will receive a query as a string, and return a list of floats which is the embedding vector for the given query string.

num_of_dimensions is a metadata property that denotes the number of dimensions in any embedding vector obtained via this class.

is_unit_vector is a metadata property that denotes if embedding vectors obtained via this class are unit vectors.

The following code block shows an example of how to use VoyageAIEmbeddingEncoder. You will see the updated elements list (with the embeddings attribute included for each element), the embedding vector for the query string, and some metadata properties about the embedding model.

To use Voyage AI you will need to pass Voyage AI API Key (obtained from https://dash.voyageai.com/) as the api_key parameter.

The model_name parameter is mandatory, please check the available models at https://docs.voyageai.com/docs/embeddings

import os

from unstructured.documents.elements import Text
from unstructured.embed.voyageai import VoyageAIEmbeddingConfig, VoyageAIEmbeddingEncoder

embedding_encoder = VoyageAIEmbeddingEncoder(
    config=VoyageAIEmbeddingConfig(
        api_key=os.environ["VOYAGE_API_KEY"],
        model_name="voyage-law-2"
    )
)
elements = embedding_encoder.embed_documents(
    elements=[Text("This is sentence 1"), Text("This is sentence 2")],
)

query = "This is the query"
query_embedding = embedding_encoder.embed_query(query=query)

[print(e, e.embeddings) for e in elements]
print(query, query_embedding)
print(embedding_encoder.is_unit_vector, embedding_encoder.num_of_dimensions)