1  ---
  2  title: "ValkeyEmbeddingRetriever"
  3  id: valkeyembeddingretriever
  4  slug: "/valkeyembeddingretriever"
  5  description: "This is an embedding Retriever compatible with the Valkey Document Store."
  6  ---
  7  
  8  # ValkeyEmbeddingRetriever
  9  
 10  This is an embedding Retriever compatible with the Valkey Document Store.
 11  
 12  <div className="key-value-table">
 13  
 14  |  |  |
 15  | --- | --- |
 16  | **Most common position in a pipeline** | 1. After a Text Embedder and before a [`ChatPromptBuilder`](../builders/chatpromptbuilder.mdx) or [`PromptBuilder`](../builders/promptbuilder.mdx) in a RAG pipeline 2. The last component in a semantic search pipeline 3. After a Text Embedder and before an [`ExtractiveReader`](../readers/extractivereader.mdx) in an extractive QA pipeline |
 17  | **Mandatory init variables**           | `document_store`: An instance of a [ValkeyDocumentStore](../../document-stores/valkeydocumentstore.mdx)                                                                                                                                                                                     |
 18  | **Mandatory run variables**            | `query_embedding`: A list of floats                                                                                                                                                                                                                                       |
 19  | **Output variables**                   | `documents`: A list of documents                                                                                                                                                                                                                                          |
 20  | **API reference**                      | [Valkey](/reference/integrations-valkey)                                                                                                                                                                                                                                     |
 21  | **GitHub link**                        | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/valkey                                                                                                                                                                                |
 22  
 23  </div>
 24  
 25  ## Overview
 26  
 27  The `ValkeyEmbeddingRetriever` is an embedding-based Retriever compatible with the [`ValkeyDocumentStore`](../../document-stores/valkeydocumentstore.mdx). It compares the query and Document embeddings and fetches the Documents most relevant to the query from the `ValkeyDocumentStore` based on vector similarity.
 28  
 29  ### Parameters
 30  
 31  When using the `ValkeyEmbeddingRetriever` in your system, ensure the query and Document [embeddings](../embedders.mdx) are available. You can do so by adding a Document embedder to your indexing pipeline and a text embedder to your query pipeline.
 32  
 33  In addition to the `query_embedding`, the `ValkeyEmbeddingRetriever` accepts other optional parameters, including `top_k` (the maximum number of Documents to retrieve) and `filters` to narrow down the search space.
 34  
 35  ## Usage
 36  
 37  ### Installation
 38  
 39  To start using Valkey with Haystack, install the package with:
 40  
 41  ```shell
 42  pip install valkey-haystack
 43  ```
 44  
 45  ### On its own
 46  
 47  This Retriever needs an instance of `ValkeyDocumentStore` and indexed Documents to run.
 48  
 49  ```python
 50  from haystack_integrations.document_stores.valkey import ValkeyDocumentStore
 51  from haystack_integrations.components.retrievers.valkey import ValkeyEmbeddingRetriever
 52  
 53  document_store = ValkeyDocumentStore(
 54      nodes_list=[("localhost", 6379)],
 55      index_name="my_documents",
 56      embedding_dim=768,
 57      distance_metric="cosine",
 58  )
 59  
 60  retriever = ValkeyEmbeddingRetriever(document_store=document_store)
 61  
 62  # Using a fake vector to keep the example simple
 63  retriever.run(query_embedding=[0.1] * 768)
 64  ```
 65  
 66  ### In a Pipeline
 67  
 68  ```python
 69  from haystack import Document, Pipeline
 70  from haystack.components.embedders import (
 71      SentenceTransformersDocumentEmbedder,
 72      SentenceTransformersTextEmbedder,
 73  )
 74  from haystack.components.writers import DocumentWriter
 75  from haystack_integrations.document_stores.valkey import ValkeyDocumentStore
 76  from haystack_integrations.components.retrievers.valkey import ValkeyEmbeddingRetriever
 77  
 78  document_store = ValkeyDocumentStore(
 79      nodes_list=[("localhost", 6379)],
 80      index_name="my_documents",
 81      embedding_dim=768,
 82      distance_metric="cosine",
 83  )
 84  
 85  documents = [
 86      Document(content="There are over 7,000 languages spoken around the world today."),
 87      Document(
 88          content="Elephants have been observed to behave in a way that indicates a high level of self-awareness, such as recognizing themselves in mirrors.",
 89      ),
 90      Document(
 91          content="In certain parts of the world, like the Maldives, Puerto Rico, and San Diego, you can witness the phenomenon of bioluminescent waves.",
 92      ),
 93  ]
 94  
 95  indexing = Pipeline()
 96  indexing.add_component("embedder", SentenceTransformersDocumentEmbedder())
 97  indexing.add_component("writer", DocumentWriter(document_store))
 98  indexing.connect("embedder.documents", "writer.documents")
 99  indexing.run({"embedder": {"documents": documents}})
100  
101  query_pipeline = Pipeline()
102  query_pipeline.add_component("text_embedder", SentenceTransformersTextEmbedder())
103  query_pipeline.add_component(
104      "retriever",
105      ValkeyEmbeddingRetriever(document_store=document_store),
106  )
107  query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
108  
109  query = "How many languages are there?"
110  result = query_pipeline.run({"text_embedder": {"text": query}})
111  
112  print(result["retriever"]["documents"][0])
113  ```
114  
115  For a full RAG example with `ValkeyEmbeddingRetriever`, see the [ValkeyDocumentStore](../../document-stores/valkeydocumentstore.mdx#using-valkey-in-a-rag-pipeline) documentation.