1  ---
  2  title: "QdrantDocumentStore"
  3  id: qdrant-document-store
  4  slug: "/qdrant-document-store"
  5  description: "Use the Qdrant vector database with Haystack."
  6  ---
  7  
  8  # QdrantDocumentStore
  9  
 10  Use the Qdrant vector database with Haystack.
 11  
 12  <div className="key-value-table">
 13  
 14  |  |  |
 15  | --- | --- |
 16  | API reference | [Qdrant](/reference/integrations-qdrant)                                                        |
 17  | GitHub link   | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/qdrant |
 18  
 19  </div>
 20  
 21  Qdrant is a powerful high-performance, massive-scale vector database. The `QdrantDocumentStore` can be used with any Qdrant instance, in-memory, locally persisted, hosted, and the official Qdrant Cloud.
 22  
 23  ### Installation
 24  
 25  You can simply install the Qdrant Haystack integration with:
 26  
 27  ```shell
 28  pip install qdrant-haystack
 29  ```
 30  
 31  ### Initialization
 32  
 33  The quickest way to use `QdrantDocumentStore` is to create an in-memory instance of it:
 34  
 35  ```python
 36  from haystack.dataclasses.document import Document
 37  from haystack_integrations.document_stores.qdrant import QdrantDocumentStore
 38  
 39  document_store = QdrantDocumentStore(
 40      ":memory:",
 41      recreate_index=True,
 42      return_embedding=True,
 43      wait_result_from_api=True,
 44  )
 45  document_store.write_documents(
 46      [
 47          Document(content="This is first", embedding=[0.0] * 5),
 48          Document(content="This is second", embedding=[0.1, 0.2, 0.3, 0.4, 0.5]),
 49      ],
 50  )
 51  print(document_store.count_documents())
 52  ```
 53  
 54  :::warning[Collections Created Outside Haystack]
 55  
 56  When you create a `QdrantDocumentStore` instance, Haystack takes care of setting up the collection. In general, you cannot use a Qdrant collection created without Haystack with Haystack. If you want to migrate your existing collection, see the sample script at https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/qdrant/src/haystack_integrations/document_stores/qdrant/migrate_to_sparse.py.
 57  :::
 58  
 59  You can also connect directly to [Qdrant Cloud](https://cloud.qdrant.io/login) directly. Once you have your API key and your cluster URL from the Qdrant dashboard, you can connect like this:
 60  
 61  ```python
 62  from haystack.dataclasses.document import Document
 63  from haystack_integrations.document_stores.qdrant import QdrantDocumentStore
 64  from haystack.utils import Secret
 65  
 66  document_store = QdrantDocumentStore(
 67      url="https://XXXXXXXXX.us-east4-0.gcp.cloud.qdrant.io:6333",
 68      index="your_index_name",
 69      embedding_dim=1024,  # based on the embedding model
 70      recreate_index=True,  # enable only to recreate the index and not connect to the existing one
 71      api_key=Secret.from_token("YOUR_TOKEN"),
 72  )
 73  
 74  document_store.write_documents(
 75      [
 76          Document(content="This is first", embedding=[0.0] * 5),
 77          Document(content="This is second", embedding=[0.1, 0.2, 0.3, 0.4, 0.5]),
 78      ],
 79  )
 80  print(document_store.count_documents())
 81  ```
 82  
 83  :::tip[More information]
 84  
 85  You can find more ways to initialize and use QdrantDocumentStore on our [integration page](https://haystack.deepset.ai/integrations/qdrant-document-store).
 86  :::
 87  
 88  ### Supported Retrievers
 89  
 90  - [`QdrantEmbeddingRetriever`](../pipeline-components/retrievers/qdrantembeddingretriever.mdx): Retrieves documents from the `QdrantDocumentStore` based on their dense embeddings (vectors).
 91  - [`QdrantSparseEmbeddingRetriever`](../pipeline-components/retrievers/qdrantsparseembeddingretriever.mdx): Retrieves documents from the `QdrantDocumentStore` based on their sparse embeddings.
 92  - [`QdrantHybridRetriever`](../pipeline-components/retrievers/qdranthybridretriever.mdx): Retrieves documents from the `QdrantDocumentStore` based on both dense and sparse embeddings.
 93  
 94  :::note[Sparse Embedding Support]
 95  
 96  To use Sparse Embedding support, you need to initialize the `QdrantDocumentStore` with `use_sparse_embeddings=True`, which is `False` by default.
 97  
 98  If you want to use Document Store or collection previously created with this feature disabled, you must migrate the existing data. You can do this by taking advantage of the `migrate_to_sparse_embeddings_support` utility function.
 99  :::
100  
101  ## Additional References
102  
103  🧑‍🍳 Cookbook: [Sparse Embedding Retrieval with Qdrant and FastEmbed](https://haystack.deepset.ai/cookbook/sparse_embedding_retrieval)