DocumentationAPI Reference📓 Tutorials🧑‍🍳 Cookbook🤝 Integrations💜 Discord🎨 Studio
API Reference

Embedders

Transforms queries into vectors to look for similar or relevant Documents.

Module azure_document_embedder

AzureOpenAIDocumentEmbedder

Calculates document embeddings using OpenAI models deployed on Azure.

Usage example

from haystack import Document
from haystack.components.embedders import AzureOpenAIDocumentEmbedder

doc = Document(content="I love pizza!")

document_embedder = AzureOpenAIDocumentEmbedder()

result = document_embedder.run([doc])
print(result['documents'][0].embedding)

# [0.017020374536514282, -0.023255806416273117, ...]

AzureOpenAIDocumentEmbedder.__init__

def __init__(azure_endpoint: Optional[str] = None,
             api_version: Optional[str] = "2023-05-15",
             azure_deployment: str = "text-embedding-ada-002",
             dimensions: Optional[int] = None,
             api_key: Optional[Secret] = Secret.from_env_var(
                 "AZURE_OPENAI_API_KEY", strict=False),
             azure_ad_token: Optional[Secret] = Secret.from_env_var(
                 "AZURE_OPENAI_AD_TOKEN", strict=False),
             organization: Optional[str] = None,
             prefix: str = "",
             suffix: str = "",
             batch_size: int = 32,
             progress_bar: bool = True,
             meta_fields_to_embed: Optional[List[str]] = None,
             embedding_separator: str = "\n",
             timeout: Optional[float] = None,
             max_retries: Optional[int] = None)

Creates an AzureOpenAIDocumentEmbedder component.

Arguments:

  • azure_endpoint: The endpoint of the model deployed on Azure.
  • api_version: The version of the API to use.
  • azure_deployment: The name of the model deployed on Azure. The default model is text-embedding-ada-002.
  • dimensions: The number of dimensions of the resulting embeddings. Only supported in text-embedding-3 and later models.
  • api_key: The Azure OpenAI API key. You can set it with an environment variable AZURE_OPENAI_API_KEY, or pass with this parameter during initialization.
  • azure_ad_token: Microsoft Entra ID token, see Microsoft's Entra ID documentation for more information. You can set it with an environment variable AZURE_OPENAI_AD_TOKEN, or pass with this parameter during initialization. Previously called Azure Active Directory.
  • organization: Your organization ID. See OpenAI's Setting Up Your Organization for more information.
  • prefix: A string to add at the beginning of each text.
  • suffix: A string to add at the end of each text.
  • batch_size: Number of documents to embed at once.
  • progress_bar: If True, shows a progress bar when running.
  • meta_fields_to_embed: List of metadata fields to embed along with the document text.
  • embedding_separator: Separator used to concatenate the metadata fields to the document text.
  • timeout: The timeout for AzureOpenAI client calls, in seconds. If not set, defaults to either the OPENAI_TIMEOUT environment variable, or 30 seconds.
  • max_retries: Maximum number of retries to contact AzureOpenAI after an internal error. If not set, defaults to either the OPENAI_MAX_RETRIES environment variable or to 5 retries.

AzureOpenAIDocumentEmbedder.to_dict

def to_dict() -> Dict[str, Any]

Serializes the component to a dictionary.

Returns:

Dictionary with serialized data.

AzureOpenAIDocumentEmbedder.from_dict

@classmethod
def from_dict(cls, data: Dict[str, Any]) -> "AzureOpenAIDocumentEmbedder"

Deserializes the component from a dictionary.

Arguments:

  • data: Dictionary to deserialize from.

Returns:

Deserialized component.

AzureOpenAIDocumentEmbedder.run

@component.output_types(documents=List[Document], meta=Dict[str, Any])
def run(documents: List[Document]) -> Dict[str, Any]

Embeds a list of documents.

Arguments:

  • documents: Documents to embed.

Returns:

A dictionary with the following keys:

  • documents: A list of documents with embeddings.
  • meta: Information about the usage of the model.

Module azure_text_embedder

AzureOpenAITextEmbedder

Embeds strings using OpenAI models deployed on Azure.

Usage example

from haystack.components.embedders import AzureOpenAITextEmbedder

text_to_embed = "I love pizza!"

text_embedder = AzureOpenAITextEmbedder()

print(text_embedder.run(text_to_embed))

# {'embedding': [0.017020374536514282, -0.023255806416273117, ...],
# 'meta': {'model': 'text-embedding-ada-002-v2',
#          'usage': {'prompt_tokens': 4, 'total_tokens': 4}}}

AzureOpenAITextEmbedder.__init__

def __init__(azure_endpoint: Optional[str] = None,
             api_version: Optional[str] = "2023-05-15",
             azure_deployment: str = "text-embedding-ada-002",
             dimensions: Optional[int] = None,
             api_key: Optional[Secret] = Secret.from_env_var(
                 "AZURE_OPENAI_API_KEY", strict=False),
             azure_ad_token: Optional[Secret] = Secret.from_env_var(
                 "AZURE_OPENAI_AD_TOKEN", strict=False),
             organization: Optional[str] = None,
             timeout: Optional[float] = None,
             max_retries: Optional[int] = None,
             prefix: str = "",
             suffix: str = "")

Creates an AzureOpenAITextEmbedder component.

Arguments:

  • azure_endpoint: The endpoint of the model deployed on Azure.
  • api_version: The version of the API to use.
  • azure_deployment: The name of the model deployed on Azure. The default model is text-embedding-ada-002.
  • dimensions: The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.
  • api_key: The Azure OpenAI API key. You can set it with an environment variable AZURE_OPENAI_API_KEY, or pass with this parameter during initialization.
  • azure_ad_token: Microsoft Entra ID token, see Microsoft's Entra ID documentation for more information. You can set it with an environment variable AZURE_OPENAI_AD_TOKEN, or pass with this parameter during initialization. Previously called Azure Active Directory.
  • organization: Your organization ID. See OpenAI's Setting Up Your Organization for more information.
  • timeout: The timeout for AzureOpenAI client calls, in seconds. If not set, defaults to either the OPENAI_TIMEOUT environment variable, or 30 seconds.
  • max_retries: Maximum number of retries to contact AzureOpenAI after an internal error. If not set, defaults to either the OPENAI_MAX_RETRIES environment variable, or to 5 retries.
  • prefix: A string to add at the beginning of each text.
  • suffix: A string to add at the end of each text.

AzureOpenAITextEmbedder.to_dict

def to_dict() -> Dict[str, Any]

Serializes the component to a dictionary.

Returns:

Dictionary with serialized data.

AzureOpenAITextEmbedder.from_dict

@classmethod
def from_dict(cls, data: Dict[str, Any]) -> "AzureOpenAITextEmbedder"

Deserializes the component from a dictionary.

Arguments:

  • data: Dictionary to deserialize from.

Returns:

Deserialized component.

AzureOpenAITextEmbedder.run

@component.output_types(embedding=List[float], meta=Dict[str, Any])
def run(text: str)

Embeds a single string.

Arguments:

  • text: Text to embed.

Returns:

A dictionary with the following keys:

  • embedding: The embedding of the input text.
  • meta: Information about the usage of the model.

Module hugging_face_api_document_embedder

HuggingFaceAPIDocumentEmbedder

Embeds documents using Hugging Face APIs.

Use it with the following Hugging Face APIs:

Usage examples

With free serverless inference API

from haystack.components.embedders import HuggingFaceAPIDocumentEmbedder
from haystack.utils import Secret
from haystack.dataclasses import Document

doc = Document(content="I love pizza!")

doc_embedder = HuggingFaceAPIDocumentEmbedder(api_type="serverless_inference_api",
                                              api_params={"model": "BAAI/bge-small-en-v1.5"},
                                              token=Secret.from_token("<your-api-key>"))

result = document_embedder.run([doc])
print(result["documents"][0].embedding)

# [0.017020374536514282, -0.023255806416273117, ...]

With paid inference endpoints

from haystack.components.embedders import HuggingFaceAPIDocumentEmbedder
from haystack.utils import Secret
from haystack.dataclasses import Document

doc = Document(content="I love pizza!")

doc_embedder = HuggingFaceAPIDocumentEmbedder(api_type="inference_endpoints",
                                              api_params={"url": "<your-inference-endpoint-url>"},
                                              token=Secret.from_token("<your-api-key>"))

result = document_embedder.run([doc])
print(result["documents"][0].embedding)

# [0.017020374536514282, -0.023255806416273117, ...]

With self-hosted text embeddings inference

from haystack.components.embedders import HuggingFaceAPIDocumentEmbedder
from haystack.dataclasses import Document

doc = Document(content="I love pizza!")

doc_embedder = HuggingFaceAPIDocumentEmbedder(api_type="text_embeddings_inference",
                                              api_params={"url": "http://localhost:8080"})

result = document_embedder.run([doc])
print(result["documents"][0].embedding)

# [0.017020374536514282, -0.023255806416273117, ...]

HuggingFaceAPIDocumentEmbedder.__init__

def __init__(api_type: Union[HFEmbeddingAPIType, str],
             api_params: Dict[str, str],
             token: Optional[Secret] = Secret.from_env_var(
                 ["HF_API_TOKEN", "HF_TOKEN"], strict=False),
             prefix: str = "",
             suffix: str = "",
             truncate: bool = True,
             normalize: bool = False,
             batch_size: int = 32,
             progress_bar: bool = True,
             meta_fields_to_embed: Optional[List[str]] = None,
             embedding_separator: str = "\n")

Creates a HuggingFaceAPIDocumentEmbedder component.

Arguments:

  • api_type: The type of Hugging Face API to use.
  • api_params: A dictionary with the following keys:
  • model: Hugging Face model ID. Required when api_type is SERVERLESS_INFERENCE_API.
  • url: URL of the inference endpoint. Required when api_type is INFERENCE_ENDPOINTS or TEXT_EMBEDDINGS_INFERENCE.
  • token: The Hugging Face token to use as HTTP bearer authorization. Check your HF token in your account settings.
  • prefix: A string to add at the beginning of each text.
  • suffix: A string to add at the end of each text.
  • truncate: Truncates the input text to the maximum length supported by the model. Applicable when api_type is TEXT_EMBEDDINGS_INFERENCE, or INFERENCE_ENDPOINTS if the backend uses Text Embeddings Inference. If api_type is SERVERLESS_INFERENCE_API, this parameter is ignored. It is always set to True and cannot be changed.
  • normalize: Normalizes the embeddings to unit length. Applicable when api_type is TEXT_EMBEDDINGS_INFERENCE, or INFERENCE_ENDPOINTS if the backend uses Text Embeddings Inference. If api_type is SERVERLESS_INFERENCE_API, this parameter is ignored. It is always set to False and cannot be changed.
  • batch_size: Number of documents to process at once.
  • progress_bar: If True, shows a progress bar when running.
  • meta_fields_to_embed: List of metadata fields to embed along with the document text.
  • embedding_separator: Separator used to concatenate the metadata fields to the document text.

HuggingFaceAPIDocumentEmbedder.to_dict

def to_dict() -> Dict[str, Any]

Serializes the component to a dictionary.

Returns:

Dictionary with serialized data.

HuggingFaceAPIDocumentEmbedder.from_dict

@classmethod
def from_dict(cls, data: Dict[str, Any]) -> "HuggingFaceAPIDocumentEmbedder"

Deserializes the component from a dictionary.

Arguments:

  • data: Dictionary to deserialize from.

Returns:

Deserialized component.

HuggingFaceAPIDocumentEmbedder.run

@component.output_types(documents=List[Document])
def run(documents: List[Document])

Embeds a list of documents.

Arguments:

  • documents: Documents to embed.

Returns:

A dictionary with the following keys:

  • documents: A list of documents with embeddings.

Module hugging_face_api_text_embedder

HuggingFaceAPITextEmbedder

Embeds strings using Hugging Face APIs.

Use it with the following Hugging Face APIs:

Usage examples

With free serverless inference API

from haystack.components.embedders import HuggingFaceAPITextEmbedder
from haystack.utils import Secret

text_embedder = HuggingFaceAPITextEmbedder(api_type="serverless_inference_api",
                                           api_params={"model": "BAAI/bge-small-en-v1.5"},
                                           token=Secret.from_token("<your-api-key>"))

print(text_embedder.run("I love pizza!"))

# {'embedding': [0.017020374536514282, -0.023255806416273117, ...],

With paid inference endpoints

from haystack.components.embedders import HuggingFaceAPITextEmbedder
from haystack.utils import Secret
text_embedder = HuggingFaceAPITextEmbedder(api_type="inference_endpoints",
                                           api_params={"model": "BAAI/bge-small-en-v1.5"},
                                           token=Secret.from_token("<your-api-key>"))

print(text_embedder.run("I love pizza!"))

# {'embedding': [0.017020374536514282, -0.023255806416273117, ...],

With self-hosted text embeddings inference

from haystack.components.embedders import HuggingFaceAPITextEmbedder
from haystack.utils import Secret

text_embedder = HuggingFaceAPITextEmbedder(api_type="text_embeddings_inference",
                                           api_params={"url": "http://localhost:8080"})

print(text_embedder.run("I love pizza!"))

# {'embedding': [0.017020374536514282, -0.023255806416273117, ...],

HuggingFaceAPITextEmbedder.__init__

def __init__(api_type: Union[HFEmbeddingAPIType, str],
             api_params: Dict[str, str],
             token: Optional[Secret] = Secret.from_env_var(
                 ["HF_API_TOKEN", "HF_TOKEN"], strict=False),
             prefix: str = "",
             suffix: str = "",
             truncate: bool = True,
             normalize: bool = False)

Creates a HuggingFaceAPITextEmbedder component.

Arguments:

  • api_type: The type of Hugging Face API to use.
  • api_params: A dictionary with the following keys:
  • model: Hugging Face model ID. Required when api_type is SERVERLESS_INFERENCE_API.
  • url: URL of the inference endpoint. Required when api_type is INFERENCE_ENDPOINTS or TEXT_EMBEDDINGS_INFERENCE.
  • token: The Hugging Face token to use as HTTP bearer authorization. Check your HF token in your account settings.
  • prefix: A string to add at the beginning of each text.
  • suffix: A string to add at the end of each text.
  • truncate: Truncates the input text to the maximum length supported by the model. Applicable when api_type is TEXT_EMBEDDINGS_INFERENCE, or INFERENCE_ENDPOINTS if the backend uses Text Embeddings Inference. If api_type is SERVERLESS_INFERENCE_API, this parameter is ignored. It is always set to True and cannot be changed.
  • normalize: Normalizes the embeddings to unit length. Applicable when api_type is TEXT_EMBEDDINGS_INFERENCE, or INFERENCE_ENDPOINTS if the backend uses Text Embeddings Inference. If api_type is SERVERLESS_INFERENCE_API, this parameter is ignored. It is always set to False and cannot be changed.

HuggingFaceAPITextEmbedder.to_dict

def to_dict() -> Dict[str, Any]

Serializes the component to a dictionary.

Returns:

Dictionary with serialized data.

HuggingFaceAPITextEmbedder.from_dict

@classmethod
def from_dict(cls, data: Dict[str, Any]) -> "HuggingFaceAPITextEmbedder"

Deserializes the component from a dictionary.

Arguments:

  • data: Dictionary to deserialize from.

Returns:

Deserialized component.

HuggingFaceAPITextEmbedder.run

@component.output_types(embedding=List[float])
def run(text: str)

Embeds a single string.

Arguments:

  • text: Text to embed.

Returns:

A dictionary with the following keys:

  • embedding: The embedding of the input text.

Module openai_document_embedder

OpenAIDocumentEmbedder

Computes document embeddings using OpenAI models.

Usage example

from haystack import Document
from haystack.components.embedders import OpenAIDocumentEmbedder

doc = Document(content="I love pizza!")

document_embedder = OpenAIDocumentEmbedder()

result = document_embedder.run([doc])
print(result['documents'][0].embedding)

# [0.017020374536514282, -0.023255806416273117, ...]

OpenAIDocumentEmbedder.__init__

def __init__(api_key: Secret = Secret.from_env_var("OPENAI_API_KEY"),
             model: str = "text-embedding-ada-002",
             dimensions: Optional[int] = None,
             api_base_url: Optional[str] = None,
             organization: Optional[str] = None,
             prefix: str = "",
             suffix: str = "",
             batch_size: int = 32,
             progress_bar: bool = True,
             meta_fields_to_embed: Optional[List[str]] = None,
             embedding_separator: str = "\n",
             timeout: Optional[float] = None,
             max_retries: Optional[int] = None)

Creates an OpenAIDocumentEmbedder component.

Before initializing the component, you can set the 'OPENAI_TIMEOUT' and 'OPENAI_MAX_RETRIES' environment variables to override the timeout and max_retries parameters respectively in the OpenAI client.

Arguments:

  • api_key: The OpenAI API key. You can set it with an environment variable OPENAI_API_KEY, or pass with this parameter during initialization.
  • model: The name of the model to use for calculating embeddings. The default model is text-embedding-ada-002.
  • dimensions: The number of dimensions of the resulting embeddings. Only text-embedding-3 and later models support this parameter.
  • api_base_url: Overrides the default base URL for all HTTP requests.
  • organization: Your OpenAI organization ID. See OpenAI's Setting Up Your Organization for more information.
  • prefix: A string to add at the beginning of each text.
  • suffix: A string to add at the end of each text.
  • batch_size: Number of documents to embed at once.
  • progress_bar: If True, shows a progress bar when running.
  • meta_fields_to_embed: List of metadata fields to embed along with the document text.
  • embedding_separator: Separator used to concatenate the metadata fields to the document text.
  • timeout: Timeout for OpenAI client calls. If not set, it defaults to either the OPENAI_TIMEOUT environment variable, or 30 seconds.
  • max_retries: Maximum number of retries to contact OpenAI after an internal error. If not set, it defaults to either the OPENAI_MAX_RETRIES environment variable, or 5 retries.

OpenAIDocumentEmbedder.to_dict

def to_dict() -> Dict[str, Any]

Serializes the component to a dictionary.

Returns:

Dictionary with serialized data.

OpenAIDocumentEmbedder.from_dict

@classmethod
def from_dict(cls, data: Dict[str, Any]) -> "OpenAIDocumentEmbedder"

Deserializes the component from a dictionary.

Arguments:

  • data: Dictionary to deserialize from.

Returns:

Deserialized component.

OpenAIDocumentEmbedder.run

@component.output_types(documents=List[Document], meta=Dict[str, Any])
def run(documents: List[Document])

Embeds a list of documents.

Arguments:

  • documents: A list of documents to embed.

Returns:

A dictionary with the following keys:

  • documents: A list of documents with embeddings.
  • meta: Information about the usage of the model.

Module openai_text_embedder

OpenAITextEmbedder

Embeds strings using OpenAI models.

You can use it to embed user query and send it to an embedding Retriever.

Usage example

from haystack.components.embedders import OpenAITextEmbedder

text_to_embed = "I love pizza!"

text_embedder = OpenAITextEmbedder()

print(text_embedder.run(text_to_embed))

# {'embedding': [0.017020374536514282, -0.023255806416273117, ...],
# 'meta': {'model': 'text-embedding-ada-002-v2',
#          'usage': {'prompt_tokens': 4, 'total_tokens': 4}}}

OpenAITextEmbedder.__init__

def __init__(api_key: Secret = Secret.from_env_var("OPENAI_API_KEY"),
             model: str = "text-embedding-ada-002",
             dimensions: Optional[int] = None,
             api_base_url: Optional[str] = None,
             organization: Optional[str] = None,
             prefix: str = "",
             suffix: str = "",
             timeout: Optional[float] = None,
             max_retries: Optional[int] = None)

Creates an OpenAITextEmbedder component.

Before initializing the component, you can set the 'OPENAI_TIMEOUT' and 'OPENAI_MAX_RETRIES' environment variables to override the timeout and max_retries parameters respectively in the OpenAI client.

Arguments:

  • api_key: The OpenAI API key. You can set it with an environment variable OPENAI_API_KEY, or pass with this parameter during initialization.
  • model: The name of the model to use for calculating embeddings. The default model is text-embedding-ada-002.
  • dimensions: The number of dimensions of the resulting embeddings. Only text-embedding-3 and later models support this parameter.
  • api_base_url: Overrides default base URL for all HTTP requests.
  • organization: Your organization ID. See OpenAI's production best practices for more information.
  • prefix: A string to add at the beginning of each text to embed.
  • suffix: A string to add at the end of each text to embed.
  • timeout: Timeout for OpenAI client calls. If not set, it defaults to either the OPENAI_TIMEOUT environment variable, or 30 seconds.
  • max_retries: Maximum number of retries to contact OpenAI after an internal error. If not set, it defaults to either the OPENAI_MAX_RETRIES environment variable, or set to 5.

OpenAITextEmbedder.to_dict

def to_dict() -> Dict[str, Any]

Serializes the component to a dictionary.

Returns:

Dictionary with serialized data.

OpenAITextEmbedder.from_dict

@classmethod
def from_dict(cls, data: Dict[str, Any]) -> "OpenAITextEmbedder"

Deserializes the component from a dictionary.

Arguments:

  • data: Dictionary to deserialize from.

Returns:

Deserialized component.

OpenAITextEmbedder.run

@component.output_types(embedding=List[float], meta=Dict[str, Any])
def run(text: str)

Embeds a single string.

Arguments:

  • text: Text to embed.

Returns:

A dictionary with the following keys:

  • embedding: The embedding of the input text.
  • meta: Information about the usage of the model.

Module sentence_transformers_document_embedder

SentenceTransformersDocumentEmbedder

Calculates document embeddings using Sentence Transformers models.

It stores the embeddings in the embedding metadata field of each document. You can also embed documents' metadata. Use this component in indexing pipelines to embed input documents and send them to DocumentWriter to write a into a Document Store.

Usage example:

from haystack import Document
from haystack.components.embedders import SentenceTransformersDocumentEmbedder
doc = Document(content="I love pizza!")
doc_embedder = SentenceTransformersDocumentEmbedder()
doc_embedder.warm_up()

result = doc_embedder.run([doc])
print(result['documents'][0].embedding)

# [-0.07804739475250244, 0.1498992145061493, ...]

SentenceTransformersDocumentEmbedder.__init__

def __init__(model: str = "sentence-transformers/all-mpnet-base-v2",
             device: Optional[ComponentDevice] = None,
             token: Optional[Secret] = Secret.from_env_var(
                 ["HF_API_TOKEN", "HF_TOKEN"], strict=False),
             prefix: str = "",
             suffix: str = "",
             batch_size: int = 32,
             progress_bar: bool = True,
             normalize_embeddings: bool = False,
             meta_fields_to_embed: Optional[List[str]] = None,
             embedding_separator: str = "\n",
             trust_remote_code: bool = False,
             truncate_dim: Optional[int] = None,
             model_kwargs: Optional[Dict[str, Any]] = None,
             tokenizer_kwargs: Optional[Dict[str, Any]] = None,
             config_kwargs: Optional[Dict[str, Any]] = None,
             precision: Literal["float32", "int8", "uint8", "binary",
                                "ubinary"] = "float32")

Creates a SentenceTransformersDocumentEmbedder component.

Arguments:

  • model: The model to use for calculating embeddings. Pass a local path or ID of the model on Hugging Face.
  • device: The device to use for loading the model. Overrides the default device.
  • token: The API token to download private models from Hugging Face.
  • prefix: A string to add at the beginning of each document text. Can be used to prepend the text with an instruction, as required by some embedding models, such as E5 and bge.
  • suffix: A string to add at the end of each document text.
  • batch_size: Number of documents to embed at once.
  • progress_bar: If True, shows a progress bar when embedding documents.
  • normalize_embeddings: If True, returns vectors with length 1.
  • meta_fields_to_embed: List of metadata fields to embed along with the document text.
  • embedding_separator: Separator used to concatenate the metadata fields to the document text.
  • trust_remote_code: If False, allows only Hugging Face verified model architectures. If True, allows custom models and scripts.
  • truncate_dim: The dimension to truncate sentence embeddings to. None does no truncation. If the model wasn't trained with Matryoshka Representation Learning, truncating embeddings can significantly affect performance.
  • model_kwargs: Additional keyword arguments for AutoModelForSequenceClassification.from_pretrained when loading the model. Refer to specific model documentation for available kwargs.
  • tokenizer_kwargs: Additional keyword arguments for AutoTokenizer.from_pretrained when loading the tokenizer. Refer to specific model documentation for available kwargs.
  • config_kwargs: Additional keyword arguments for AutoConfig.from_pretrained when loading the model configuration.
  • precision: The precision to use for the embeddings. All non-float32 precisions are quantized embeddings. Quantized embeddings are smaller and faster to compute, but may have a lower accuracy. They are useful for reducing the size of the embeddings of a corpus for semantic search, among other tasks.

SentenceTransformersDocumentEmbedder.to_dict

def to_dict() -> Dict[str, Any]

Serializes the component to a dictionary.

Returns:

Dictionary with serialized data.

SentenceTransformersDocumentEmbedder.from_dict

@classmethod
def from_dict(cls, data: Dict[str,
                              Any]) -> "SentenceTransformersDocumentEmbedder"

Deserializes the component from a dictionary.

Arguments:

  • data: Dictionary to deserialize from.

Returns:

Deserialized component.

SentenceTransformersDocumentEmbedder.warm_up

def warm_up()

Initializes the component.

SentenceTransformersDocumentEmbedder.run

@component.output_types(documents=List[Document])
def run(documents: List[Document])

Embed a list of documents.

Arguments:

  • documents: Documents to embed.

Returns:

A dictionary with the following keys:

  • documents: Documents with embeddings.

Module sentence_transformers_text_embedder

SentenceTransformersTextEmbedder

Embeds strings using Sentence Transformers models.

You can use it to embed user query and send it to an embedding retriever.

Usage example:

from haystack.components.embedders import SentenceTransformersTextEmbedder

text_to_embed = "I love pizza!"

text_embedder = SentenceTransformersTextEmbedder()
text_embedder.warm_up()

print(text_embedder.run(text_to_embed))

# {'embedding': [-0.07804739475250244, 0.1498992145061493,, ...]}

SentenceTransformersTextEmbedder.__init__

def __init__(model: str = "sentence-transformers/all-mpnet-base-v2",
             device: Optional[ComponentDevice] = None,
             token: Optional[Secret] = Secret.from_env_var(
                 ["HF_API_TOKEN", "HF_TOKEN"], strict=False),
             prefix: str = "",
             suffix: str = "",
             batch_size: int = 32,
             progress_bar: bool = True,
             normalize_embeddings: bool = False,
             trust_remote_code: bool = False,
             truncate_dim: Optional[int] = None,
             model_kwargs: Optional[Dict[str, Any]] = None,
             tokenizer_kwargs: Optional[Dict[str, Any]] = None,
             config_kwargs: Optional[Dict[str, Any]] = None,
             precision: Literal["float32", "int8", "uint8", "binary",
                                "ubinary"] = "float32")

Create a SentenceTransformersTextEmbedder component.

Arguments:

  • model: The model to use for calculating embeddings. Specify the path to a local model or the ID of the model on Hugging Face.
  • device: Overrides the default device used to load the model.
  • token: An API token to use private models from Hugging Face.
  • prefix: A string to add at the beginning of each text to be embedded. You can use it to prepend the text with an instruction, as required by some embedding models, such as E5 and bge.
  • suffix: A string to add at the end of each text to embed.
  • batch_size: Number of texts to embed at once.
  • progress_bar: If True, shows a progress bar for calculating embeddings. If False, disables the progress bar.
  • normalize_embeddings: If True, returned vectors have a length of 1.
  • trust_remote_code: If False, permits only Hugging Face verified model architectures. If True, permits custom models and scripts.
  • truncate_dim: The dimension to truncate sentence embeddings to. None does no truncation. If the model has not been trained with Matryoshka Representation Learning, truncation of embeddings can significantly affect performance.
  • model_kwargs: Additional keyword arguments for AutoModelForSequenceClassification.from_pretrained when loading the model. Refer to specific model documentation for available kwargs.
  • tokenizer_kwargs: Additional keyword arguments for AutoTokenizer.from_pretrained when loading the tokenizer. Refer to specific model documentation for available kwargs.
  • config_kwargs: Additional keyword arguments for AutoConfig.from_pretrained when loading the model configuration.
  • precision: The precision to use for the embeddings. All non-float32 precisions are quantized embeddings. Quantized embeddings are smaller in size and faster to compute, but may have a lower accuracy. They are useful for reducing the size of the embeddings of a corpus for semantic search, among other tasks.

SentenceTransformersTextEmbedder.to_dict

def to_dict() -> Dict[str, Any]

Serializes the component to a dictionary.

Returns:

Dictionary with serialized data.

SentenceTransformersTextEmbedder.from_dict

@classmethod
def from_dict(cls, data: Dict[str, Any]) -> "SentenceTransformersTextEmbedder"

Deserializes the component from a dictionary.

Arguments:

  • data: Dictionary to deserialize from.

Returns:

Deserialized component.

SentenceTransformersTextEmbedder.warm_up

def warm_up()

Initializes the component.

SentenceTransformersTextEmbedder.run

@component.output_types(embedding=List[float])
def run(text: str)

Embed a single string.

Arguments:

  • text: Text to embed.

Returns:

A dictionary with the following keys:

  • embedding: The embedding of the input text.