1  ---
  2  title: "OpenAITextEmbedder"
  3  id: openaitextembedder
  4  slug: "/openaitextembedder"
  5  description: "OpenAITextEmbedder transforms a string into a vector that captures its semantics using an OpenAI embedding model."
  6  ---
  7  
  8  # OpenAITextEmbedder
  9  
 10  OpenAITextEmbedder transforms a string into a vector that captures its semantics using an OpenAI embedding model.
 11  
 12  When you perform embedding retrieval, you use this component to transform your query into a vector. Then, the embedding Retriever looks for similar or relevant documents.
 13  
 14  <div className="key-value-table">
 15  
 16  |  |  |
 17  | --- | --- |
 18  | **Most common position in a pipeline** | Before an embedding [Retriever](../retrievers.mdx)  in a query/RAG pipeline |
 19  | **Mandatory init variables** | `api_key`: An OpenAI API key. Can be set with `OPENAI_API_KEY` env var. |
 20  | **Mandatory run variables** | `text`: A string |
 21  | **Output variables** | `embedding`: A list of float numbers  <br /> <br />`meta`: A dictionary of metadata |
 22  | **API reference** | [Embedders](/reference/embedders-api) |
 23  | **GitHub link** | https://github.com/deepset-ai/haystack/blob/main/haystack/components/embedders/openai_text_embedder.py |
 24  
 25  </div>
 26  
 27  ## Overview
 28  
 29  To see the list of compatible OpenAI embedding models, head over to OpenAI [documentation](https://platform.openai.com/docs/guides/embeddings/embedding-models). The default model for `OpenAITextEmbedder` is `text-embedding-ada-002`. You can specify another model with the `model` parameter when initializing this component.
 30  
 31  Use `OpenAITextEmbedder` to embed a simple string (such as a query) into a vector. For embedding lists of documents, use the [OpenAIDocumentEmbedder](openaidocumentembedder.mdx), which enriches the document with the computed embedding, also known as vector.
 32  
 33  The component uses an `OPENAI_API_KEY` environment variable by default. Otherwise, you can pass an API key at initialization with `api_key`:
 34  
 35  ```python
 36  embedder = OpenAITextEmbedder(api_key=Secret.from_token("<your-api-key>"))
 37  ```
 38  
 39  ## Usage
 40  
 41  ### On its own
 42  
 43  Here is how you can use the component on its own:
 44  
 45  ```python
 46  from haystack.components.embedders import OpenAITextEmbedder
 47  
 48  text_to_embed = "I love pizza!"
 49  
 50  text_embedder = OpenAITextEmbedder(api_key=Secret.from_token("<your-api-key>"))
 51  
 52  print(text_embedder.run(text_to_embed))
 53  
 54  ## {'embedding': [0.017020374536514282, -0.023255806416273117, ...],
 55  ## 'meta': {'model': 'text-embedding-ada-002-v2',
 56  ## 'usage': {'prompt_tokens': 4, 'total_tokens': 4}}}
 57  ```
 58  
 59  :::info
 60  We recommend setting OPENAI_API_KEY as an environment variable instead of setting it as a parameter.
 61  :::
 62  
 63  ### In a pipeline
 64  
 65  ```python
 66  from haystack import Document
 67  from haystack import Pipeline
 68  from haystack.document_stores.in_memory import InMemoryDocumentStore
 69  from haystack.components.embedders import OpenAITextEmbedder, OpenAIDocumentEmbedder
 70  from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
 71  
 72  document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")
 73  
 74  documents = [
 75      Document(content="My name is Wolfgang and I live in Berlin"),
 76      Document(content="I saw a black horse running"),
 77      Document(content="Germany has many big cities"),
 78  ]
 79  
 80  document_embedder = OpenAIDocumentEmbedder()
 81  documents_with_embeddings = document_embedder.run(documents)["documents"]
 82  document_store.write_documents(documents_with_embeddings)
 83  
 84  query_pipeline = Pipeline()
 85  query_pipeline.add_component("text_embedder", OpenAITextEmbedder())
 86  query_pipeline.add_component(
 87      "retriever",
 88      InMemoryEmbeddingRetriever(document_store=document_store),
 89  )
 90  query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
 91  
 92  query = "Who lives in Berlin?"
 93  
 94  result = query_pipeline.run({"text_embedder": {"text": query}})
 95  
 96  print(result["retriever"]["documents"][0])
 97  
 98  ## Document(id=..., mimetype: 'text/plain',
 99  ## text: 'My name is Wolfgang and I live in Berlin')
100  ```