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  |               |                                                                                          |
 13  | :------------ | :--------------------------------------------------------------------------------------- |
 14  | API reference | [Qdrant](/reference/integrations-qdrant)                                                        |
 15  | GitHub link   | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/qdrant |
 16  
 17  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.
 18  
 19  ### Installation
 20  
 21  You can simply install the Qdrant Haystack integration with:
 22  
 23  ```shell
 24  pip install qdrant-haystack
 25  ```
 26  
 27  ### Initialization
 28  
 29  The quickest way to use `QdrantDocumentStore` is to create an in-memory instance of it:
 30  
 31  ```python
 32  from haystack.dataclasses.document import Document
 33  from haystack_integrations.document_stores.qdrant import QdrantDocumentStore
 34  
 35  document_store = QdrantDocumentStore(
 36      ":memory:",
 37      recreate_index=True,
 38      return_embedding=True,
 39      wait_result_from_api=True,
 40  )
 41  document_store.write_documents(
 42      [
 43          Document(content="This is first", embedding=[0.0] * 5),
 44          Document(content="This is second", embedding=[0.1, 0.2, 0.3, 0.4, 0.5]),
 45      ],
 46  )
 47  print(document_store.count_documents())
 48  ```
 49  
 50  :::warning
 51  Collections Created Outside Haystack
 52  
 53  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.
 54  :::
 55  
 56  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:
 57  
 58  ```python
 59  from haystack.dataclasses.document import Document
 60  from haystack_integrations.document_stores.qdrant import QdrantDocumentStore
 61  from haystack.utils import Secret
 62  
 63  document_store = QdrantDocumentStore(
 64      url="https://XXXXXXXXX.us-east4-0.gcp.cloud.qdrant.io:6333",
 65      index="your_index_name",
 66      embedding_dim=1024,  # based on the embedding model
 67      recreate_index=True,  # enable only to recreate the index and not connect to the existing one
 68      api_key=Secret.from_token("YOUR_TOKEN"),
 69  )
 70  
 71  document_store.write_documents(
 72      [
 73          Document(content="This is first", embedding=[0.0] * 5),
 74          Document(content="This is second", embedding=[0.1, 0.2, 0.3, 0.4, 0.5]),
 75      ],
 76  )
 77  print(document_store.count_documents())
 78  ```
 79  
 80  :::tip
 81  More information
 82  
 83  You can find more ways to initialize and use QdrantDocumentStore on our [integration page](https://haystack.deepset.ai/integrations/qdrant-document-store).
 84  :::
 85  
 86  ### Supported Retrievers
 87  
 88  - [`QdrantEmbeddingRetriever`](../pipeline-components/retrievers/qdrantembeddingretriever.mdx): Retrieves documents from the `QdrantDocumentStore` based on their dense embeddings (vectors).
 89  - [`QdrantSparseEmbeddingRetriever`](../pipeline-components/retrievers/qdrantsparseembeddingretriever.mdx): Retrieves documents from the `QdrantDocumentStore` based on their sparse embeddings.
 90  - [`QdrantHybridRetriever`](../pipeline-components/retrievers/qdranthybridretriever.mdx): Retrieves documents from the `QdrantDocumentStore` based on both dense and sparse embeddings.
 91  
 92  :::note
 93  Sparse Embedding Support
 94  
 95  To use Sparse Embedding support, you need to initialize the `QdrantDocumentStore` with `use_sparse_embeddings=True`, which is `False` by default.
 96  
 97  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.
 98  :::
 99  
100  ## Additional References
101  
102  🧑‍🍳 Cookbook: [Sparse Embedding Retrieval with Qdrant and FastEmbed](https://haystack.deepset.ai/cookbook/sparse_embedding_retrieval)