1  ---
  2  title: "FastembedTextEmbedder"
  3  id: fastembedtextembedder
  4  slug: "/fastembedtextembedder"
  5  description: "This component computes the embeddings of a string using embedding models supported by FastEmbed."
  6  ---
  7  
  8  # FastembedTextEmbedder
  9  
 10  This component computes the embeddings of a string using embedding models supported by FastEmbed.
 11  
 12  <div className="key-value-table">
 13  
 14  |  |  |
 15  | --- | --- |
 16  | **Most common position in a pipeline** | Before an embedding [Retriever](../retrievers.mdx)  in a query/RAG pipeline                  |
 17  | **Mandatory run variables**            | `text`: A string                                                                            |
 18  | **Output variables**                   | `embedding`: A vector (list of float numbers)                                               |
 19  | **API reference**                      | [FastEmbed](/reference/fastembed-embedders)                                                        |
 20  | **GitHub link**                        | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/fastembed |
 21  
 22  </div>
 23  
 24  This component should be used to embed a simple string (such as a query) into a vector. For embedding lists of documents, use the [`FastembedDocumentEmbedder`](fastembeddocumentembedder.mdx), which enriches the document with the computed embedding, known as vector.
 25  
 26  ## Overview
 27  
 28  `FastembedTextEmbedder` transforms a string into a vector that captures its semantics using embedding [models supported by FastEmbed](https://qdrant.github.io/fastembed/examples/Supported_Models/).
 29  
 30  When you perform embedding retrieval, use this component first to transform your query into a vector. Then, the embedding Retriever will use the vector to search for similar or relevant documents.
 31  
 32  ### Compatible models
 33  
 34  You can find the original models in the [FastEmbed documentation](https://qdrant.github.io/fastembed/).
 35  
 36  Currently, most of the models in the [Massive Text Embedding Benchmark (MTEB) Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) are compatible with FastEmbed. You can look for compatibility in the [supported model list](https://qdrant.github.io/fastembed/examples/Supported_Models/).
 37  
 38  ### Installation
 39  
 40  To start using this integration with Haystack, install the package with:
 41  
 42  ```bash
 43  pip install fastembed-haystack
 44  ```
 45  
 46  ### Instructions
 47  
 48  Some recent models that you can find in MTEB require prepending the text with an instruction to work better for retrieval.
 49  For example, if you use `[BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5#model-list)` model, you should prefix your query with the `instruction: “passage:”`.
 50  
 51  This is how it works with `FastembedTextEmbedder`:
 52  
 53  ```python
 54  instruction = "passage:"
 55  embedder = FastembedTextEmbedder(
 56  	*model="*BAAI/bge-large-en-v1.5",
 57  	prefix=instruction)
 58  ```
 59  
 60  ### Parameters
 61  
 62  You can set the path where the model will be stored in a cache directory. Also, you can set the number of threads a single `onnxruntime` session can use.
 63  
 64  ```python
 65  cache_dir= "/your_cacheDirectory"
 66  embedder = FastembedTextEmbedder(
 67  	*model="*BAAI/bge-large-en-v1.5",
 68  	cache_dir=cache_dir,
 69  	threads=2
 70  )
 71  ```
 72  
 73  If you want to use the data parallel encoding, you can set the parameters `parallel` and `batch_size`.
 74  
 75  - If parallel > 1, data-parallel encoding will be used. This is recommended for offline encoding of large datasets.
 76  - If parallel is 0, use all available cores.
 77  - If None, don't use data-parallel processing; use default `onnxruntime` threading instead.
 78  
 79  :::tip
 80  If you create a Text Embedder and a Document Embedder based on the same model, Haystack uses the same resource behind the scenes to save resources.
 81  :::
 82  
 83  ## Usage
 84  
 85  ### On its own
 86  
 87  ```python
 88  from haystack_integrations.components.embedders.fastembed import FastembedTextEmbedder
 89  
 90  text = """It clearly says online this will work on a Mac OS system.
 91  The disk comes and it does not, only Windows.
 92  Do Not order this if you have a Mac!!"""
 93  text_embedder = FastembedTextEmbedder(model="BAAI/bge-small-en-v1.5")
 94  text_embedder.warm_up()
 95  embedding = text_embedder.run(text)["embedding"]
 96  ```
 97  
 98  ### In a pipeline
 99  
100  ```python
101  from haystack import Document, Pipeline
102  from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
103  from haystack.document_stores.in_memory import InMemoryDocumentStore
104  from haystack_integrations.components.embedders.fastembed import (
105      FastembedDocumentEmbedder,
106      FastembedTextEmbedder,
107  )
108  
109  document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")
110  
111  documents = [
112      Document(content="My name is Wolfgang and I live in Berlin"),
113      Document(content="I saw a black horse running"),
114      Document(content="Germany has many big cities"),
115      Document(content="fastembed is supported by and maintained by Qdrant."),
116  ]
117  
118  document_embedder = FastembedDocumentEmbedder()
119  document_embedder.warm_up()
120  documents_with_embeddings = document_embedder.run(documents)["documents"]
121  document_store.write_documents(documents_with_embeddings)
122  
123  query_pipeline = Pipeline()
124  query_pipeline.add_component("text_embedder", FastembedTextEmbedder())
125  query_pipeline.add_component(
126      "retriever",
127      InMemoryEmbeddingRetriever(document_store=document_store),
128  )
129  query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
130  
131  query = "Who supports FastEmbed?"
132  
133  result = query_pipeline.run({"text_embedder": {"text": query}})
134  
135  print(result["retriever"]["documents"][0])  # noqa: T201
136  
137  ## Document(id=...,
138  ## content: 'FastEmbed is supported by and maintained by Qdrant.',
139  ## score: 0.758..)
140  ```
141  
142  ## Additional References
143  
144  🧑‍🍳 Cookbook: [RAG Pipeline Using FastEmbed for Embeddings Generation](https://haystack.deepset.ai/cookbook/rag_fastembed)