1  ---
  2  title: "STACKITTextEmbedder"
  3  id: stackittextembedder
  4  slug: "/stackittextembedder"
  5  description: "This component enables text embedding using the STACKIT API."
  6  ---
  7  
  8  # STACKITTextEmbedder
  9  
 10  This component enables text embedding using the STACKIT API.
 11  
 12  |                                        |                                                                                           |
 13  | -------------------------------------- | ----------------------------------------------------------------------------------------- |
 14  | **Most common position in a pipeline** | Before an embedding [Retriever](../retrievers.mdx) in a query/RAG pipeline                 |
 15  | **Mandatory init variables**           | "model": The model used through the STACKIT API                                           |
 16  | **Mandatory run variables**            | “text”: A string                                                                          |
 17  | **Output variables**                   | “embedding”: A list of float numbers                                                      |
 18  | **API reference**                      | [STACKIT](/reference/integrations-stackit)                                                       |
 19  | **GitHub link**                        | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/stackit |
 20  
 21  ## Overview
 22  
 23  `STACKITTextEmbedder` enables text embedding models served by STACKIT through their API.
 24  
 25  ### Parameters
 26  
 27  To use the `STACKITTextEmbedder`, ensure you have set a `STACKIT_API_KEY` as an environment variable. Alternatively, provide the API key as an environment variable with a different name or a token by setting `api_key` and using Haystack’s [secret management](../../concepts/secret-management.mdx).
 28  
 29  Set your preferred supported model with the `model` parameter when initializing the component. See the full list of all supported models on the [STACKIT website](https://docs.stackit.cloud/stackit/en/models-licenses-319914532.html).
 30  
 31  Optionally, you can change the default `api_base_url`, which is `"https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1"`.
 32  
 33  You can pass any text generation parameters valid for the STACKIT Chat Completion API directly to this component with the `generation_kwargs` parameter in the init or run methods.
 34  
 35  The component needs a text input to operate.
 36  
 37  ## Usage
 38  
 39  Install the `stackit-haystack` package to use the `STACKITTextEmbedder` and set an environment variable called `STACKIT_API_KEY` to your API key.
 40  
 41  ```shell
 42  pip install stackit-haystack
 43  ```
 44  
 45  ### On its own
 46  
 47  ```python
 48  from haystack_integrations.components.embedders.stackit import STACKITTextEmbedder
 49  
 50  text_embedder = STACKITTextEmbedder(model="intfloat/e5-mistral-7b-instruct")
 51  
 52  print(text_embedder.run("I love pizza!"))
 53  
 54  ## {'embedding': [0.0215301513671875, 0.01499176025390625, ...]}
 55  ```
 56  
 57  ### In a pipeline
 58  
 59  You can also use `STACKITTextEmbedder` in your pipeline.
 60  
 61  ```python
 62  from haystack import Document
 63  from haystack import Pipeline
 64  from haystack.document_stores.in_memory import InMemoryDocumentStore
 65  from haystack_integrations.components.embedders.stackit import (
 66      STACKITTextEmbedder,
 67      STACKITDocumentEmbedder,
 68  )
 69  from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
 70  
 71  document_store = InMemoryDocumentStore()
 72  
 73  documents = [
 74      Document(content="My name is Wolfgang and I live in Berlin"),
 75      Document(content="I saw a black horse running"),
 76      Document(content="Germany has many big cities"),
 77  ]
 78  
 79  document_embedder = STACKITDocumentEmbedder(model="intfloat/e5-mistral-7b-instruct")
 80  documents_with_embeddings = document_embedder.run(documents)["documents"]
 81  document_store.write_documents(documents_with_embeddings)
 82  
 83  text_embedder = STACKITTextEmbedder(model="intfloat/e5-mistral-7b-instruct")
 84  
 85  query_pipeline = Pipeline()
 86  query_pipeline.add_component("text_embedder", text_embedder)
 87  query_pipeline.add_component(
 88      "retriever",
 89      InMemoryEmbeddingRetriever(document_store=document_store),
 90  )
 91  query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
 92  
 93  query = "Where does Wolfgang live?"
 94  
 95  result = query_pipeline.run({"text_embedder": {"text": query}})
 96  
 97  print(result["retriever"]["documents"][0])
 98  
 99  ## Document(id=..., content: 'My name is Wolfgang and I live in Berlin', score: ...)
100  ```
101  
102  You can find more usage examples in the STACKIT integration [repository](https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/stackit/examples) and its [integration page](https://haystack.deepset.ai/integrations/stackit).