feast-dev · patelchaitany · Jun 9, 2026 · SIDDHESH1564 · Jun 9, 2026 · patelchaitany
@@ -14,7 +14,7 @@ Below are supported vector databases and implemented features:
 | Milvus          | [x]       | [x]      | [x]         | [x]         |
 | Faiss           | [ ]       | [ ]      | []          | []          |
 | SQLite          | [x]       | [ ]      | [x]         | [x]         |
-| Qdrant          | [x]       | [x]      | []          | []          |
+| Qdrant          | [x]       | [x]      | [x]         | [x]         |
 
 *Note: V2 Support means the SDK supports retrieval of features along with vector embeddings from vector similarity search.
 
@@ -30,7 +30,7 @@ Beyond that, we will then have `retrieve_online_documents` and `retrieve_online_
 backwards compatibility and the adopt industry standard naming conventions.
 {% endhint %}
 
-**Note**: Milvus and SQLite implement the v2 `retrieve_online_documents_v2` method in the SDK. This will be the longer-term solution so that Data Scientists can easily enable vector similarity search by just flipping a flag.
+**Note**: Milvus, SQLite, PostgreSQL, Elasticsearch, MongoDB, and Qdrant implement the v2 `retrieve_online_documents_v2` method in the SDK. This will be the longer-term solution so that Data Scientists can easily enable vector similarity search by just flipping a flag.
 
 ## Examples
 

@@ -47,10 +47,67 @@ The full set of configuration options is available in [QdrantOnlineStoreConfig](
 | collocated by feature view                                | yes      |
 | collocated by feature service                             | no       |
 | collocated by entity key                                  | no       |
+| retrieve_online_documents_v2 (vector search)              | yes      |
+| hybrid text search (`query_string`)                       | yes (opt-in) |
 
 To compare this set of functionality against other online stores, please see the full [functionality matrix](overview.md#functionality-matrix).
 
-## Retrieving online document vectors
+## Vector search with retrieve_online_documents_v2
+
+Qdrant stores one point per feature. `retrieve_online_documents_v2` runs dense vector search on the embedding feature, then joins sibling feature points by `entity_key` so the response includes every requested feature in a single `Dict[str, ValueProto]`.
+
+{% code title="python" %}
+
+```python
+from feast import FeatureStore
+
+store = FeatureStore(repo_path="feature_store.yaml")
+
+results = store.retrieve_online_documents_v2(
+    features=["documents:embedding", "documents:text_field"],
+    query=[0.1, 0.2, 0.3],  # embedding vector
+    top_k=5,
+)
+```
+
+{% endcode %}
+
+## Opt-in hybrid search
+
+Hybrid keyword + vector search is **disabled by default**. Enable it in `feature_store.yaml`, recreate the collection (`feast teardown` + `feast apply`), and install `fastembed` so the Qdrant client can encode sparse vectors at upload time (via `models.Document`):
+
+{% code title="feature_store.yaml" %}
+
+```yaml
+online_store:
+    type: qdrant
+    host: localhost
+    port: 6333
+    vector_enabled: true
+    text_search_enabled: true
+    sparse_vector_name: sparse
+    sparse_embedding_model: Qdrant/bm25
+    text_feature: text_field  # optional; defaults to first STRING feature
+```
+
+{% endcode %}
+
+{% code title="python" %}
+
+```python
+results = store.retrieve_online_documents_v2(
+    features=["documents:embedding", "documents:text_field"],
+    query=[0.1, 0.2, 0.3],
+    query_string="searchable keywords",
+    top_k=5,
+)
+```
+
+{% endcode %}
+
+Hybrid queries use Qdrant's Query API with reciprocal rank fusion (RRF) over dense and sparse vectors.
+
+## Retrieving online document vectors (v1)
 
 The Qdrant online store supports retrieving document vectors for a given list of entity keys. The document vectors are returned as a dictionary where the key is the entity key and the value is the document vector. The document vector is a dense vector of floats.