qdrant-haystack 9.1.0__tar.gz → 9.1.2__tar.gz

{qdrant_haystack-9.1.0 → qdrant_haystack-9.1.2}/CHANGELOG.md

@@ -1,5 +1,21 @@
 # Changelog
 
+## [integrations/qdrant-v9.1.1] - 2025-03-20
+
+### ⚙️ CI
+
+- Review testing workflows (#1541)
+
+### 🌀 Miscellaneous
+
+- Fix: `TypeError` in `QdrantDocumentStore` when handling duplicate documents (#1551)
+
+## [integrations/qdrant-v9.1.0] - 2025-03-14
+
+### 🚀 Features
+
+- Qdrant -- async support (#1480)
+
 ## [integrations/qdrant-v9.0.0] - 2025-03-11
 
 ### 🧹 Chores

{qdrant_haystack-9.1.0 → qdrant_haystack-9.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: qdrant-haystack
-Version: 9.1.0
+Version: 9.1.2
 Summary: An integration of Qdrant ANN vector database backend with Haystack
 Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/qdrant/README.md
@@ -15,6 +15,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Requires-Python: >=3.9

{qdrant_haystack-9.1.0 → qdrant_haystack-9.1.2}/pyproject.toml

@@ -22,6 +22,7 @@ classifiers = [
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
@@ -55,9 +56,6 @@ cov = ["test-cov", "cov-report"]
 cov-retry = ["test-cov-retry", "cov-report"]
 docs = ["pydoc-markdown pydoc/config.yml"]
 
-[[tool.hatch.envs.all.matrix]]
-python = [ "3.9", "3.10", "3.11"]
-
 [tool.hatch.envs.lint]
 installer = "uv"
 detached = true

{qdrant_haystack-9.1.0 → qdrant_haystack-9.1.2}/src/haystack_integrations/components/retrievers/qdrant/retriever.py

@@ -46,7 +46,7 @@ class QdrantEmbeddingRetriever:
         score_threshold: Optional[float] = None,
         group_by: Optional[str] = None,
         group_size: Optional[int] = None,
-    ):
+    ) -> None:
         """
         Create a QdrantEmbeddingRetriever component.
 
@@ -136,7 +136,7 @@ class QdrantEmbeddingRetriever:
         score_threshold: Optional[float] = None,
         group_by: Optional[str] = None,
         group_size: Optional[int] = None,
-    ):
+    ) -> Dict[str, List[Document]]:
         """
         Run the Embedding Retriever on the given input data.
 
@@ -180,7 +180,7 @@ class QdrantEmbeddingRetriever:
         score_threshold: Optional[float] = None,
         group_by: Optional[str] = None,
         group_size: Optional[int] = None,
-    ):
+    ) -> Dict[str, List[Document]]:
         """
         Asynchronously run the Embedding Retriever on the given input data.
 
@@ -252,7 +252,7 @@ class QdrantSparseEmbeddingRetriever:
         score_threshold: Optional[float] = None,
         group_by: Optional[str] = None,
         group_size: Optional[int] = None,
-    ):
+    ) -> None:
         """
         Create a QdrantSparseEmbeddingRetriever component.
 
@@ -342,7 +342,7 @@ class QdrantSparseEmbeddingRetriever:
         score_threshold: Optional[float] = None,
         group_by: Optional[str] = None,
         group_size: Optional[int] = None,
-    ):
+    ) -> Dict[str, List[Document]]:
         """
         Run the Sparse Embedding Retriever on the given input data.
 
@@ -391,7 +391,7 @@ class QdrantSparseEmbeddingRetriever:
         score_threshold: Optional[float] = None,
         group_by: Optional[str] = None,
         group_size: Optional[int] = None,
-    ):
+    ) -> Dict[str, List[Document]]:
         """
         Asynchronously run the Sparse Embedding Retriever on the given input data.
 
@@ -473,7 +473,7 @@ class QdrantHybridRetriever:
         score_threshold: Optional[float] = None,
         group_by: Optional[str] = None,
         group_size: Optional[int] = None,
-    ):
+    ) -> None:
         """
         Create a QdrantHybridRetriever component.
 
@@ -557,7 +557,7 @@ class QdrantHybridRetriever:
         score_threshold: Optional[float] = None,
         group_by: Optional[str] = None,
         group_size: Optional[int] = None,
-    ):
+    ) -> Dict[str, List[Document]]:
         """
         Run the Sparse Embedding Retriever on the given input data.
 
@@ -606,7 +606,7 @@ class QdrantHybridRetriever:
         score_threshold: Optional[float] = None,
         group_by: Optional[str] = None,
         group_size: Optional[int] = None,
-    ):
+    ) -> Dict[str, List[Document]]:
         """
         Asynchronously run the Sparse Embedding Retriever on the given input data.
 

{qdrant_haystack-9.1.0 → qdrant_haystack-9.1.2}/src/haystack_integrations/document_stores/qdrant/document_store.py

@@ -1,6 +1,6 @@
 import inspect
 from itertools import islice
-from typing import Any, AsyncGenerator, ClassVar, Dict, Generator, List, Optional, Set, Union
+from typing import Any, AsyncGenerator, ClassVar, Dict, Generator, List, Optional, Set, Tuple, Union
 
 import numpy as np
 import qdrant_client
@@ -18,6 +18,7 @@ from tqdm import tqdm
 from .converters import (
     DENSE_VECTORS_NAME,
     SPARSE_VECTORS_NAME,
+    QdrantPoint,
     convert_haystack_documents_to_qdrant_points,
     convert_id,
     convert_qdrant_point_to_haystack_document,
@@ -34,7 +35,7 @@ class QdrantStoreError(DocumentStoreError):
 FilterType = Dict[str, Union[Dict[str, Any], List[Any], str, int, float, bool]]
 
 
-def get_batches_from_generator(iterable, n):
+def get_batches_from_generator(iterable: List, n: int) -> Generator:
     """
     Batch elements of an iterable into fixed-length chunks or blocks.
     """
@@ -127,10 +128,10 @@ class QdrantDocumentStore:
         write_batch_size: int = 100,
         scroll_size: int = 10_000,
         payload_fields_to_index: Optional[List[dict]] = None,
-    ):
+    ) -> None:
         """
         :param location:
-            If `memory` - use in-memory Qdrant instance.
+            If `":memory:"` - use in-memory Qdrant instance.
             If `str` - use it as a URL parameter.
             If `None` - use default values for host and port.
         :param url:
@@ -164,7 +165,7 @@ class QdrantDocumentStore:
             Dimension of the embeddings.
         :param on_disk:
             Whether to store the collection on disk.
-        :param use_sparse_embedding:
+        :param use_sparse_embeddings:
             If set to `True`, enables support for sparse embeddings.
         :param sparse_idf:
             If set to `True`, computes the Inverse Document Frequency (IDF) when using sparse embeddings.
@@ -232,7 +233,6 @@ class QdrantDocumentStore:
         self.path = path
         self.force_disable_check_same_thread = force_disable_check_same_thread
         self.metadata = metadata or {}
-        self.api_key = api_key
 
         # Store the Qdrant collection specific attributes
         self.shard_number = shard_number
@@ -258,9 +258,10 @@ class QdrantDocumentStore:
         self.write_batch_size = write_batch_size
         self.scroll_size = scroll_size
 
-    def _initialize_client(self):
+    def _initialize_client(self) -> None:
         if self._client is None:
             client_params = self._prepare_client_params()
+            # This step adds the api-key and User-Agent to metadata
             self._client = qdrant_client.QdrantClient(**client_params)
             # Make sure the collection is properly set up
             self._set_up_collection(
@@ -274,7 +275,7 @@ class QdrantDocumentStore:
                 self.payload_fields_to_index,
             )
 
-    async def _initialize_async_client(self):
+    async def _initialize_async_client(self) -> None:
         """
         Returns the asynchronous Qdrant client, initializing it if necessary.
         """
@@ -628,8 +629,6 @@ class QdrantDocumentStore:
 
         :param ids:
             A list of document IDs to retrieve.
-        :param index:
-            The name of the index to retrieve documents from.
         :returns:
             A list of documents.
         """
@@ -661,8 +660,6 @@ class QdrantDocumentStore:
 
         :param ids:
             A list of document IDs to retrieve.
-        :param index:
-            The name of the index to retrieve documents from.
         :returns:
             A list of documents.
         """
@@ -1210,7 +1207,7 @@ class QdrantDocumentStore:
             )
             raise QdrantStoreError(msg) from ke
 
-    def _create_payload_index(self, collection_name: str, payload_fields_to_index: Optional[List[dict]] = None):
+    def _create_payload_index(self, collection_name: str, payload_fields_to_index: Optional[List[dict]] = None) -> None:
         """
         Create payload index for the collection if payload_fields_to_index is provided
         See: https://qdrant.tech/documentation/concepts/indexing/#payload-index
@@ -1229,7 +1226,7 @@ class QdrantDocumentStore:
 
     async def _create_payload_index_async(
         self, collection_name: str, payload_fields_to_index: Optional[List[dict]] = None
-    ):
+    ) -> None:
         """
         Asynchronously create payload index for the collection if payload_fields_to_index is provided
         See: https://qdrant.tech/documentation/concepts/indexing/#payload-index
@@ -1257,7 +1254,7 @@ class QdrantDocumentStore:
         sparse_idf: bool,
         on_disk: bool = False,
         payload_fields_to_index: Optional[List[dict]] = None,
-    ):
+    ) -> None:
         """
         Sets up the Qdrant collection with the specified parameters.
         :param collection_name:
@@ -1313,7 +1310,7 @@ class QdrantDocumentStore:
         sparse_idf: bool,
         on_disk: bool = False,
         payload_fields_to_index: Optional[List[dict]] = None,
-    ):
+    ) -> None:
         """
         Asynchronously sets up the Qdrant collection with the specified parameters.
         :param collection_name:
@@ -1367,7 +1364,7 @@ class QdrantDocumentStore:
         on_disk: Optional[bool] = None,
         use_sparse_embeddings: Optional[bool] = None,
         sparse_idf: bool = False,
-    ):
+    ) -> None:
         """
         Recreates the Qdrant collection with the specified parameters.
 
@@ -1410,7 +1407,7 @@ class QdrantDocumentStore:
         on_disk: Optional[bool] = None,
         use_sparse_embeddings: Optional[bool] = None,
         sparse_idf: bool = False,
-    ):
+    ) -> None:
         """
         Asynchronously recreates the Qdrant collection with the specified parameters.
 
@@ -1449,7 +1446,7 @@ class QdrantDocumentStore:
         self,
         documents: List[Document],
         policy: DuplicatePolicy = None,
-    ):
+    ) -> List[Document]:
         """
         Checks whether any of the passed documents is already existing in the chosen index and returns a list of
         documents that are not in the index yet.
@@ -1476,7 +1473,7 @@ class QdrantDocumentStore:
         self,
         documents: List[Document],
         policy: DuplicatePolicy = None,
-    ):
+    ) -> List[Document]:
         """
         Asynchronously checks whether any of the passed documents is already existing
         in the chosen index and returns a list of
@@ -1511,9 +1508,9 @@ class QdrantDocumentStore:
         for document in documents:
             if document.id in _hash_ids:
                 logger.info(
-                    "Duplicate Documents: Document with id '%s' already exists in index '%s'",
-                    document.id,
-                    self.index,
+                    "Duplicate Documents: Document with id '{document_id}' already exists in index '{index}'",
+                    document_id=document.id,
+                    index=self.index,
                 )
                 continue
             _documents.append(document)
@@ -1521,7 +1518,7 @@ class QdrantDocumentStore:
 
         return _documents
 
-    def _prepare_collection_params(self):
+    def _prepare_collection_params(self) -> Dict[str, Any]:
         """
         Prepares the common parameters for collection creation.
         """
@@ -1537,7 +1534,7 @@ class QdrantDocumentStore:
             "init_from": self.init_from,
         }
 
-    def _prepare_client_params(self):
+    def _prepare_client_params(self) -> Dict[str, Any]:
         """
         Prepares the common parameters for client initialization.
 
@@ -1554,7 +1551,10 @@ class QdrantDocumentStore:
             "timeout": self.timeout,
             "host": self.host,
             "path": self.path,
-            "metadata": self.metadata,
+            # NOTE: We purposefully expand the fields of self.metadata to avoid modifying the original self.metadata
+            # class attribute. For example, the resolved api key is added to metadata by the QdrantClient class
+            # when using a hosted Qdrant service, which means running to_dict() exposes the api key.
+            "metadata": {**self.metadata},
             "force_disable_check_same_thread": self.force_disable_check_same_thread,
         }
 
@@ -1565,7 +1565,7 @@ class QdrantDocumentStore:
         on_disk: Optional[bool] = None,
         use_sparse_embeddings: Optional[bool] = None,
         sparse_idf: bool = False,
-    ):
+    ) -> Tuple[Dict[str, rest.VectorParams], Optional[Dict[str, rest.SparseVectorParams]]]:
         """
         Prepares the configuration for creating or recreating a Qdrant collection.
 
@@ -1595,9 +1595,12 @@ class QdrantDocumentStore:
 
         return vectors_config, sparse_vectors_config
 
-    def _validate_filters(self, filters: Optional[Union[Dict[str, Any], rest.Filter]] = None):
+    def _validate_filters(self, filters: Optional[Union[Dict[str, Any], rest.Filter]] = None) -> None:
         """
         Validates the filters provided for querying.
+
+        :param filters: Filters to validate. Can be a dictionary or an instance of `qdrant_client.http.models.Filter`.
+        :raises ValueError: If the filters are not in the correct format or syntax.
         """
         if filters and not isinstance(filters, dict) and not isinstance(filters, rest.Filter):
             msg = "Filter must be a dictionary or an instance of `qdrant_client.http.models.Filter`"
@@ -1607,7 +1610,7 @@ class QdrantDocumentStore:
             msg = "Invalid filter syntax. See https://docs.haystack.deepset.ai/docs/metadata-filtering for details."
             raise ValueError(msg)
 
-    def _process_query_point_results(self, results, scale_score: bool = False):
+    def _process_query_point_results(self, results: List[QdrantPoint], scale_score: bool = False) -> List[Document]:
         """
         Processes query results from Qdrant.
         """
@@ -1627,7 +1630,7 @@ class QdrantDocumentStore:
 
         return documents
 
-    def _process_group_results(self, groups):
+    def _process_group_results(self, groups: List[rest.PointGroup]) -> List[Document]:
         """
         Processes grouped query results from Qdrant.
 
@@ -1647,7 +1650,7 @@ class QdrantDocumentStore:
         collection_info,
         distance,
         embedding_dim: int,
-    ):
+    ) -> None:
         """
         Validates that an existing collection is compatible with the current configuration.
         """

{qdrant_haystack-9.1.0 → qdrant_haystack-9.1.2}/src/haystack_integrations/document_stores/qdrant/filters.py

@@ -138,10 +138,10 @@ def convert_filters_to_qdrant(
 
 
 def build_filters_for_repeated_operators(
-    must_clauses,
-    should_clauses,
-    must_not_clauses,
-    qdrant_filter,
+    must_clauses: List,
+    should_clauses: List,
+    must_not_clauses: List,
+    qdrant_filter: List[models.Filter],
 ) -> List[models.Filter]:
     """
     Flattens the nested lists of clauses by creating separate Filters for each clause of a logical operator.

{qdrant_haystack-9.1.0 → qdrant_haystack-9.1.2}/src/haystack_integrations/document_stores/qdrant/migrate_to_sparse.py

@@ -11,7 +11,7 @@ logger.addHandler(python_logging.StreamHandler())
 logger.setLevel(python_logging.INFO)
 
 
-def migrate_to_sparse_embeddings_support(old_document_store: QdrantDocumentStore, new_index: str):
+def migrate_to_sparse_embeddings_support(old_document_store: QdrantDocumentStore, new_index: str) -> None:
     """
     Utility function to migrate an existing `QdrantDocumentStore` to a new one with support for sparse embeddings.
 

{qdrant_haystack-9.1.0 → qdrant_haystack-9.1.2}/tests/test_document_store.py

@@ -12,6 +12,7 @@ from haystack.testing.document_store import (
     WriteDocumentsTest,
     _random_embeddings,
 )
+from haystack.utils import Secret
 from qdrant_client.http import models as rest
 
 from haystack_integrations.document_stores.qdrant.document_store import (
@@ -38,6 +39,79 @@ class TestQdrantDocumentStore(CountDocumentsTest, WriteDocumentsTest, DeleteDocu
             QdrantDocumentStore(location=":memory:", use_sparse_embeddings=True)
             mocked_qdrant.assert_not_called()
 
+    def test_prepare_client_params_no_mutability(self):
+        metadata = {"key": "value"}
+        doc_store = QdrantDocumentStore(
+            ":memory:",
+            recreate_index=True,
+            return_embedding=True,
+            wait_result_from_api=True,
+            use_sparse_embeddings=False,
+            metadata=metadata,
+        )
+        client_params = doc_store._prepare_client_params()
+        # Mutate value of metadata in client_params
+        client_params["metadata"] = client_params["metadata"].update({"new_key": "new_value"})
+
+        # Assert that the original metadata in the document store is unchanged
+        assert metadata == {"key": "value"}
+
+    def test_to_dict(self, monkeypatch):
+        monkeypatch.setenv("QDRANT_API_KEY", "test_api_key")
+        doc_store = QdrantDocumentStore(
+            ":memory:",
+            recreate_index=True,
+            return_embedding=True,
+            wait_result_from_api=True,
+            use_sparse_embeddings=False,
+            api_key=Secret.from_env_var("QDRANT_API_KEY"),
+        )
+        expected_dict = {
+            "type": "haystack_integrations.document_stores.qdrant.document_store.QdrantDocumentStore",
+            "init_parameters": {
+                "location": ":memory:",
+                "url": None,
+                "port": 6333,
+                "grpc_port": 6334,
+                "prefer_grpc": False,
+                "https": None,
+                "api_key": {
+                    "env_vars": ["QDRANT_API_KEY"],
+                    "strict": True,
+                    "type": "env_var",
+                },
+                "prefix": None,
+                "timeout": None,
+                "host": None,
+                "path": None,
+                "force_disable_check_same_thread": False,
+                "index": "Document",
+                "embedding_dim": 768,
+                "on_disk": False,
+                "use_sparse_embeddings": False,
+                "sparse_idf": False,
+                "similarity": "cosine",
+                "return_embedding": True,
+                "progress_bar": True,
+                "recreate_index": True,
+                "shard_number": None,
+                "replication_factor": None,
+                "write_consistency_factor": None,
+                "on_disk_payload": None,
+                "hnsw_config": None,
+                "optimizers_config": None,
+                "wal_config": None,
+                "quantization_config": None,
+                "init_from": None,
+                "wait_result_from_api": True,
+                "metadata": {},
+                "write_batch_size": 100,
+                "scroll_size": 10000,
+                "payload_fields_to_index": None,
+            },
+        }
+        assert doc_store.to_dict() == expected_dict
+
     def assert_documents_are_equal(self, received: List[Document], expected: List[Document]):
         """
         Assert that two lists of Documents are equal.