1  ---
  2  title: "WatsonxTextEmbedder"
  3  id: watsonxtextembedder
  4  slug: "/watsonxtextembedder"
  5  description: "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."
  6  ---
  7  
  8  # WatsonxTextEmbedder
  9  
 10  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.
 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 init variables** | `api_key`: An IBM Cloud API key. Can be set with `WATSONX_API_KEY` env var.  <br /> <br />`project_id`: An IBM Cloud project ID. Can be set with `WATSONX_PROJECT_ID` env var. |
 18  | **Mandatory run variables** | `text`: A string |
 19  | **Output variables** | `embedding`: A list of float numbers  <br /> <br />`meta`: A dictionary of metadata |
 20  | **API reference** | [Watsonx](/reference/integrations-watsonx) |
 21  | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/watsonx |
 22  
 23  </div>
 24  
 25  ## Overview
 26  
 27  To see the list of compatible IBM watsonx.ai embedding models, head over to IBM [documentation](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models-embed.html?context=wx). The default model for `WatsonxTextEmbedder` is `ibm/slate-30m-english-rtrvr`. You can specify another model with the `model` parameter when initializing this component.
 28  
 29  Use `WatsonxTextEmbedder` to embed a simple string (such as a query) into a vector. For embedding lists of documents, use the [`WatsonxDocumentEmbedder`](watsonxdocumentembedder.mdx), which enriches the document with the computed embedding, also known as vector.
 30  
 31  The component uses `WATSONX_API_KEY` and `WATSONX_PROJECT_ID` environment variables by default. Otherwise, you can pass API credentials at initialization with `api_key` and `project_id`:
 32  
 33  ```python
 34  embedder = WatsonxTextEmbedder(
 35      api_key=Secret.from_token("<your-api-key>"),
 36      project_id=Secret.from_token("<your-project-id>"),
 37  )
 38  ```
 39  
 40  ## Usage
 41  
 42  Install the `watsonx-haystack` package to use the `WatsonxTextEmbedder`:
 43  
 44  ```shell
 45  pip install watsonx-haystack
 46  ```
 47  
 48  ### On its own
 49  
 50  Here is how you can use the component on its own:
 51  
 52  ```python
 53  from haystack_integrations.components.embedders.watsonx.text_embedder import (
 54      WatsonxTextEmbedder,
 55  )
 56  from haystack.utils import Secret
 57  
 58  text_to_embed = "I love pizza!"
 59  
 60  text_embedder = WatsonxTextEmbedder(
 61      api_key=Secret.from_env_var("WATSONX_API_KEY"),
 62      project_id=Secret.from_env_var("WATSONX_PROJECT_ID"),
 63      model="ibm/slate-30m-english-rtrvr",
 64  )
 65  
 66  print(text_embedder.run(text_to_embed))
 67  
 68  ## {'embedding': [0.017020374536514282, -0.023255806416273117, ...],
 69  ## 'meta': {'model': 'ibm/slate-30m-english-rtrvr',
 70  ## 'truncated_input_tokens': 3}}
 71  ```
 72  
 73  :::info
 74  We recommend setting WATSONX_API_KEY and WATSONX_PROJECT_ID as environment variables instead of setting them as parameters.
 75  :::
 76  
 77  ### In a pipeline
 78  
 79  ```python
 80  from haystack import Document
 81  from haystack import Pipeline
 82  from haystack.document_stores.in_memory import InMemoryDocumentStore
 83  from haystack_integrations.components.embedders.watsonx.text_embedder import (
 84      WatsonxTextEmbedder,
 85  )
 86  from haystack_integrations.components.embedders.watsonx.document_embedder import (
 87      WatsonxDocumentEmbedder,
 88  )
 89  from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
 90  
 91  document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")
 92  
 93  documents = [
 94      Document(content="My name is Wolfgang and I live in Berlin"),
 95      Document(content="I saw a black horse running"),
 96      Document(content="Germany has many big cities"),
 97  ]
 98  
 99  document_embedder = WatsonxDocumentEmbedder()
100  documents_with_embeddings = document_embedder.run(documents)["documents"]
101  document_store.write_documents(documents_with_embeddings)
102  
103  query_pipeline = Pipeline()
104  query_pipeline.add_component("text_embedder", WatsonxTextEmbedder())
105  query_pipeline.add_component(
106      "retriever",
107      InMemoryEmbeddingRetriever(document_store=document_store),
108  )
109  query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
110  
111  query = "Who lives in Berlin?"
112  
113  result = query_pipeline.run({"text_embedder": {"text": query}})
114  
115  print(result["retriever"]["documents"][0])
116  
117  ## Document(id=..., mimetype: 'text/plain',
118  ## text: 'My name is Wolfgang and I live in Berlin')
119  ```