The embeddings produced by Haystack embedders are fixed-length vectors. They capture contextual information and semantic relationships within the text. The primary goal of embeddings is to transform text into a format the language model can understand and process in a more nuanced and contextually aware way.

Text and Document Embedders

There are two types of Embedders: text and document.

Text Embedders work with text strings and are most often used at the beginning of query pipelines to convert query text into vectors and send it to a Retriever.

Document Embedders embed Document objects and are most often used in indexing pipelines, after Converters, and before a DocumentWriter.

You must use the same embedding model for text and documents. This means that if you use CohereDocumentEmbedder in your indexing pipeline, you must then use CohereTextEmbedder with the same model in your query pipeline.

These are the Embedders available in Haystack:

Embedder	Description
AmazonBedrockTextEmbedder	Computes embeddings for text (such as a query) using models through Amazon Bedrock API.
AmazonBedrockDocumentEmbedder	Computes embeddings for documents using models through Amazon Bedrock API.
AzureOpenAITextEmbedder	Computes embeddings for text (such as a query) using OpenAI models deployed through Azure.
AzureOpenAIDocumentEmbedder	Computes embeddings for documents using OpenAI models deployed through Azure.
CohereTextEmbedder	Embeds a simple string (such as a query) with a Cohere model. Requires an API key from Cohere
CohereDocumentEmbedder	Embeds a list of documents with a Cohere model. Requires an API key from Cohere.
FastembedTextEmbedder	Computes the embeddings of a string using embedding models supported by Fastembed.
FastembedDocumentEmbedder	Computes the embeddings of a list of documents using the models supported by Fastembed.
FastembedSparseTextEmbedder	Embeds a simple string (such as a query) into a sparse vector using the models supported by Fastembed.
FastembedSparseDocumentEmbedder	Enriches a list of documents with their sparse embeddings using the models supported by Fastembed.
HuggingFaceAPIDocumentEmbedder	Computes document embeddings using various Hugging Face APIs.
HuggingFaceAPITextEmbedder	Embeds strings using various Hugging Face APIs.
HuggingFaceTEIDocumentEmbedder	Computes embeddings for documents using the TEI library.
HuggingFaceTEITextEmbedder	Cmputes embeddings for text using the TEI library.
JinaTextEmbedder	Embeds a simple string (such as a query) with a Jina AI Embeddings model. Requires an API key from Jina AI.
JinaDocumentEmbedder	Embeds a list of documents with a Jina AI Embeddings model. Requires an API key from Jina AI.
MistralTextEmbedder	Transforms a string into a vector using the Mistral API and models.
MistralDocumentEmbedder	Computes the embeddings of a list of documents using the Mistral API and models.
NvidiaTextEmbedder	Embeds a simple string (such as a query) into a vector.
NvidiaDocumentEmbedder	Enriches the metadata of documents with an embedding of their content.
OllamaTextEmbedder	Computes the embeddings of a string using embedding models compatible with the Ollama Library.
OllamaDocumentEmbedder	Computes the embeddings of a list of documents using embedding models compatible with the Ollama Library.
OpenAIDocumentEmbedder	Embeds a list of documents with an OpenAI embedding model. Requires an API key from an active OpenAI account.
OpenAITextEmbedder	Embeds a simple string (such as a query) with an OpenAI embedding model. Requires an API key from an active OpenAI account.
OptimumTextEmbedder	Embeds text using models loaded with the Hugging Face Optimum library.
OptimumDocumentEmbedder	Computes documents’ embeddings using models loaded with the Hugging Face Optimum library.
SentenceTransformersTextEmbedder	Embeds a simple string (such as a query) using a Sentence Transformer model.
SentenceTransformersDocumentEmbedder	Embeds a list of documents with a Sentence Transformer model.