qdrant-haystack 9.2.0__tar.gz → 10.0.0__tar.gz

{qdrant_haystack-9.2.0 → qdrant_haystack-10.0.0}/CHANGELOG.md

@@ -1,6 +1,61 @@
 # Changelog
 
-## [integrations/qdrant-v9.1.3] - 2025-05-28
+## [integrations/qdrant-v9.5.0] - 2026-01-07
+
+### 🚀 Features
+
+- Adding `delete_by_filter()` and `update_by_filter()` to `QdrantDocumentStore` (#2650)
+
+### 🐛 Bug Fixes
+
+- Fix types for qdrant-client 1.16.1 (#2561)
+
+### 🧹 Chores
+
+- Remove Readme API CI workflow and configs (#2573)
+
+
+## [integrations/qdrant-v9.4.0] - 2025-11-18
+
+### 🧹 Chores
+
+- [**breaking**] Qdrant - remove `init_from` init parameter for compatibility with `qdrant-client==1.16.0` (#2531)
+
+### 🌀 Miscellaneous
+
+- Enhancement: Adopt PEP 585 type hinting (part 5) (#2528)
+
+## [integrations/qdrant-v9.3.0] - 2025-11-11
+
+### 🚀 Features
+
+- Adding `delete_all_docs` to Qdrant document store (#2363)
+
+### 📚 Documentation
+
+- Add pydoc configurations for Docusaurus (#2411)
+
+### ⚙️ CI
+
+- Change pytest command (#2475)
+
+### 🧹 Chores
+
+- Remove black (#1985)
+- Standardize readmes - part 2 (#2205)
+
+
+## [integrations/qdrant-v9.2.0] - 2025-06-12
+
+### 🐛 Bug Fixes
+
+- Fix Qdrant types + add py.typed (#1919)
+
+
+### 🧹 Chores
+
+- Align core-integrations Hatch scripts (#1898)
+- Update md files for new hatch scripts (#1911)
 
 ### 🌀 Miscellaneous
 

{qdrant_haystack-9.2.0 → qdrant_haystack-10.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: qdrant-haystack
-Version: 9.2.0
+Version: 10.0.0
 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
@@ -11,15 +11,14 @@ License-File: LICENSE.txt
 Classifier: Development Status :: 4 - Beta
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
-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
-Requires-Dist: haystack-ai>=2.11.0
+Requires-Python: >=3.10
+Requires-Dist: haystack-ai>=2.22.0
 Requires-Dist: qdrant-client>=1.12.0
 Description-Content-Type: text/markdown
 
@@ -28,26 +27,11 @@ Description-Content-Type: text/markdown
 [![PyPI - Version](https://img.shields.io/pypi/v/qdrant-haystack.svg)](https://pypi.org/project/qdrant-haystack)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/qdrant-haystack.svg)](https://pypi.org/project/qdrant-haystack)
 
------
+- [Integration page](https://haystack.deepset.ai/integrations/qdrant-document-store)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/qdrant/CHANGELOG.md)
 
-**Table of Contents**
+---
 
-- [Installation](#installation)
-- [License](#license)
+## Contributing
 
-## Installation
-
-```console
-pip install qdrant-haystack
-```
-
-## Testing
-The test suites use Qdrant's in-memory instance. No additional steps required.
-
-```console
-hatch run test:all
-```
-
-## License
-
-`qdrant-haystack` is distributed under the terms of the [Apache-2.0](https://spdx.org/licenses/Apache-2.0.html) license.
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

qdrant_haystack-10.0.0/README.md

@@ -0,0 +1,13 @@
+# qdrant-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/qdrant-haystack.svg)](https://pypi.org/project/qdrant-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/qdrant-haystack.svg)](https://pypi.org/project/qdrant-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/qdrant-document-store)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/qdrant/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

qdrant_haystack-10.0.0/pydoc/config_docusaurus.yml

@@ -0,0 +1,30 @@
+loaders:
+- ignore_when_discovered:
+  - __init__
+  modules:
+  - haystack_integrations.components.retrievers.qdrant.retriever
+  - haystack_integrations.document_stores.qdrant.document_store
+  - haystack_integrations.document_stores.qdrant.migrate_to_sparse
+  search_path:
+  - ../src
+  type: haystack_pydoc_tools.loaders.CustomPythonLoader
+processors:
+- do_not_filter_modules: false
+  documented_only: true
+  expression: null
+  skip_empty_modules: true
+  type: filter
+- type: smart
+- type: crossref
+renderer:
+  description: Qdrant integration for Haystack
+  id: integrations-qdrant
+  markdown:
+    add_member_class_prefix: false
+    add_method_class_prefix: true
+    classdef_code_block: false
+    descriptive_class_title: false
+    descriptive_module_title: true
+    filename: qdrant.md
+  title: Qdrant
+  type: haystack_pydoc_tools.renderers.DocusaurusRenderer

{qdrant_haystack-9.2.0 → qdrant_haystack-10.0.0}/pyproject.toml

@@ -7,7 +7,7 @@ name = "qdrant-haystack"
 dynamic = ["version"]
 description = 'An integration of Qdrant ANN vector database backend with Haystack'
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 license = "Apache-2.0"
 keywords = []
 authors = [
@@ -18,7 +18,6 @@ classifiers = [
   "License :: OSI Approved :: Apache Software License",
   "Development Status :: 4 - Beta",
   "Programming Language :: Python",
-  "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
@@ -26,7 +25,7 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai>=2.11.0", "qdrant-client>=1.12.0"]
+dependencies = ["haystack-ai>=2.22.0", "qdrant-client>=1.12.0"]
 
 [project.urls]
 Source = "https://github.com/deepset-ai/haystack-core-integrations"
@@ -49,8 +48,8 @@ installer = "uv"
 dependencies = ["haystack-pydoc-tools", "ruff"]
 
 [tool.hatch.envs.default.scripts]
-docs = ["pydoc-markdown pydoc/config.yml"]
-fmt = "ruff check --fix {args} && ruff format {args}"
+docs = ["pydoc-markdown pydoc/config_docusaurus.yml"]
+fmt = "ruff check --fix {args}; ruff format {args}"
 fmt-check = "ruff check {args} && ruff format --check {args}"
 
 [tool.hatch.envs.test]
@@ -67,7 +66,7 @@ dependencies = [
 unit = 'pytest -m "not integration" {args:tests}'
 integration = 'pytest -m "integration" {args:tests}'
 all = 'pytest {args:tests}'
-cov-retry = 'all --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x'
+cov-retry = 'pytest --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x {args:tests}'
 
 types = """mypy -p haystack_integrations.document_stores.qdrant \
 -p haystack_integrations.components.retrievers.qdrant {args}"""
@@ -78,13 +77,8 @@ non_interactive = true
 check_untyped_defs = true
 disallow_incomplete_defs = true
 
-[tool.black]
-target-version = ["py38"]
-line-length = 120
-skip-string-normalization = true
 
 [tool.ruff]
-target-version = "py38"
 line-length = 120
 
 [tool.ruff.lint]
@@ -136,10 +130,6 @@ ignore = [
   # Ignore assertions
   "S101",
 ]
-unfixable = [
-  # Don't touch unused imports
-  "F401",
-]
 
 [tool.ruff.lint.flake8-tidy-imports]
 ban-relative-imports = "parents"

{qdrant_haystack-9.2.0 → qdrant_haystack-10.0.0}/src/haystack_integrations/components/retrievers/qdrant/retriever.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional, Union
+from typing import Any
 
 from haystack import Document, component, default_from_dict, default_to_dict
 from haystack.dataclasses.sparse_embedding import SparseEmbedding
@@ -43,14 +43,14 @@ class QdrantEmbeddingRetriever:
     def __init__(
         self,
         document_store: QdrantDocumentStore,
-        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
+        filters: dict[str, Any] | models.Filter | None = None,
         top_k: int = 10,
         scale_score: bool = False,
         return_embedding: bool = False,
-        filter_policy: Union[str, FilterPolicy] = FilterPolicy.REPLACE,
-        score_threshold: Optional[float] = None,
-        group_by: Optional[str] = None,
-        group_size: Optional[int] = None,
+        filter_policy: str | FilterPolicy = FilterPolicy.REPLACE,
+        score_threshold: float | None = None,
+        group_by: str | None = None,
+        group_size: int | None = None,
     ) -> None:
         """
         Create a QdrantEmbeddingRetriever component.
@@ -89,7 +89,7 @@ class QdrantEmbeddingRetriever:
         self._group_by = group_by
         self._group_size = group_size
 
-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
         """
         Serializes the component to a dictionary.
 
@@ -113,7 +113,7 @@ class QdrantEmbeddingRetriever:
         return d
 
     @classmethod
-    def from_dict(cls, data: Dict[str, Any]) -> "QdrantEmbeddingRetriever":
+    def from_dict(cls, data: dict[str, Any]) -> "QdrantEmbeddingRetriever":
         """
         Deserializes the component from a dictionary.
 
@@ -130,18 +130,18 @@ class QdrantEmbeddingRetriever:
             data["init_parameters"]["filter_policy"] = FilterPolicy.from_str(filter_policy)
         return default_from_dict(cls, data)
 
-    @component.output_types(documents=List[Document])
+    @component.output_types(documents=list[Document])
     def run(
         self,
-        query_embedding: List[float],
-        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
-        top_k: Optional[int] = None,
-        scale_score: Optional[bool] = None,
-        return_embedding: Optional[bool] = None,
-        score_threshold: Optional[float] = None,
-        group_by: Optional[str] = None,
-        group_size: Optional[int] = None,
-    ) -> Dict[str, List[Document]]:
+        query_embedding: list[float],
+        filters: dict[str, Any] | models.Filter | None = None,
+        top_k: int | None = None,
+        scale_score: bool | None = None,
+        return_embedding: bool | None = None,
+        score_threshold: float | None = None,
+        group_by: str | None = None,
+        group_size: int | None = None,
+    ) -> dict[str, list[Document]]:
         """
         Run the Embedding Retriever on the given input data.
 
@@ -185,18 +185,18 @@ class QdrantEmbeddingRetriever:
 
         return {"documents": docs}
 
-    @component.output_types(documents=List[Document])
+    @component.output_types(documents=list[Document])
     async def run_async(
         self,
-        query_embedding: List[float],
-        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
-        top_k: Optional[int] = None,
-        scale_score: Optional[bool] = None,
-        return_embedding: Optional[bool] = None,
-        score_threshold: Optional[float] = None,
-        group_by: Optional[str] = None,
-        group_size: Optional[int] = None,
-    ) -> Dict[str, List[Document]]:
+        query_embedding: list[float],
+        filters: dict[str, Any] | models.Filter | None = None,
+        top_k: int | None = None,
+        scale_score: bool | None = None,
+        return_embedding: bool | None = None,
+        score_threshold: float | None = None,
+        group_by: str | None = None,
+        group_size: int | None = None,
+    ) -> dict[str, list[Document]]:
         """
         Asynchronously run the Embedding Retriever on the given input data.
 
@@ -271,14 +271,14 @@ class QdrantSparseEmbeddingRetriever:
     def __init__(
         self,
         document_store: QdrantDocumentStore,
-        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
+        filters: dict[str, Any] | models.Filter | None = None,
         top_k: int = 10,
         scale_score: bool = False,
         return_embedding: bool = False,
-        filter_policy: Union[str, FilterPolicy] = FilterPolicy.REPLACE,
-        score_threshold: Optional[float] = None,
-        group_by: Optional[str] = None,
-        group_size: Optional[int] = None,
+        filter_policy: str | FilterPolicy = FilterPolicy.REPLACE,
+        score_threshold: float | None = None,
+        group_by: str | None = None,
+        group_size: int | None = None,
     ) -> None:
         """
         Create a QdrantSparseEmbeddingRetriever component.
@@ -317,7 +317,7 @@ class QdrantSparseEmbeddingRetriever:
         self._group_by = group_by
         self._group_size = group_size
 
-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
         """
         Serializes the component to a dictionary.
 
@@ -341,7 +341,7 @@ class QdrantSparseEmbeddingRetriever:
         return d
 
     @classmethod
-    def from_dict(cls, data: Dict[str, Any]) -> "QdrantSparseEmbeddingRetriever":
+    def from_dict(cls, data: dict[str, Any]) -> "QdrantSparseEmbeddingRetriever":
         """
         Deserializes the component from a dictionary.
 
@@ -358,18 +358,18 @@ class QdrantSparseEmbeddingRetriever:
             data["init_parameters"]["filter_policy"] = FilterPolicy.from_str(filter_policy)
         return default_from_dict(cls, data)
 
-    @component.output_types(documents=List[Document])
+    @component.output_types(documents=list[Document])
     def run(
         self,
         query_sparse_embedding: SparseEmbedding,
-        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
-        top_k: Optional[int] = None,
-        scale_score: Optional[bool] = None,
-        return_embedding: Optional[bool] = None,
-        score_threshold: Optional[float] = None,
-        group_by: Optional[str] = None,
-        group_size: Optional[int] = None,
-    ) -> Dict[str, List[Document]]:
+        filters: dict[str, Any] | models.Filter | None = None,
+        top_k: int | None = None,
+        scale_score: bool | None = None,
+        return_embedding: bool | None = None,
+        score_threshold: float | None = None,
+        group_by: str | None = None,
+        group_size: int | None = None,
+    ) -> dict[str, list[Document]]:
         """
         Run the Sparse Embedding Retriever on the given input data.
 
@@ -418,18 +418,18 @@ class QdrantSparseEmbeddingRetriever:
 
         return {"documents": docs}
 
-    @component.output_types(documents=List[Document])
+    @component.output_types(documents=list[Document])
     async def run_async(
         self,
         query_sparse_embedding: SparseEmbedding,
-        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
-        top_k: Optional[int] = None,
-        scale_score: Optional[bool] = None,
-        return_embedding: Optional[bool] = None,
-        score_threshold: Optional[float] = None,
-        group_by: Optional[str] = None,
-        group_size: Optional[int] = None,
-    ) -> Dict[str, List[Document]]:
+        filters: dict[str, Any] | models.Filter | None = None,
+        top_k: int | None = None,
+        scale_score: bool | None = None,
+        return_embedding: bool | None = None,
+        score_threshold: float | None = None,
+        group_by: str | None = None,
+        group_size: int | None = None,
+    ) -> dict[str, list[Document]]:
         """
         Asynchronously run the Sparse Embedding Retriever on the given input data.
 
@@ -515,13 +515,13 @@ class QdrantHybridRetriever:
     def __init__(
         self,
         document_store: QdrantDocumentStore,
-        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
+        filters: dict[str, Any] | models.Filter | None = None,
         top_k: int = 10,
         return_embedding: bool = False,
-        filter_policy: Union[str, FilterPolicy] = FilterPolicy.REPLACE,
-        score_threshold: Optional[float] = None,
-        group_by: Optional[str] = None,
-        group_size: Optional[int] = None,
+        filter_policy: str | FilterPolicy = FilterPolicy.REPLACE,
+        score_threshold: float | None = None,
+        group_by: str | None = None,
+        group_size: int | None = None,
     ) -> None:
         """
         Create a QdrantHybridRetriever component.
@@ -558,7 +558,7 @@ class QdrantHybridRetriever:
         self._group_by = group_by
         self._group_size = group_size
 
-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
         """
         Serializes the component to a dictionary.
 
@@ -578,7 +578,7 @@ class QdrantHybridRetriever:
         )
 
     @classmethod
-    def from_dict(cls, data: Dict[str, Any]) -> "QdrantHybridRetriever":
+    def from_dict(cls, data: dict[str, Any]) -> "QdrantHybridRetriever":
         """
         Deserializes the component from a dictionary.
 
@@ -595,18 +595,18 @@ class QdrantHybridRetriever:
             data["init_parameters"]["filter_policy"] = FilterPolicy.from_str(filter_policy)
         return default_from_dict(cls, data)
 
-    @component.output_types(documents=List[Document])
+    @component.output_types(documents=list[Document])
     def run(
         self,
-        query_embedding: List[float],
+        query_embedding: list[float],
         query_sparse_embedding: SparseEmbedding,
-        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
-        top_k: Optional[int] = None,
-        return_embedding: Optional[bool] = None,
-        score_threshold: Optional[float] = None,
-        group_by: Optional[str] = None,
-        group_size: Optional[int] = None,
-    ) -> Dict[str, List[Document]]:
+        filters: dict[str, Any] | models.Filter | None = None,
+        top_k: int | None = None,
+        return_embedding: bool | None = None,
+        score_threshold: float | None = None,
+        group_by: str | None = None,
+        group_size: int | None = None,
+    ) -> dict[str, list[Document]]:
         """
         Run the Sparse Embedding Retriever on the given input data.
 
@@ -655,18 +655,18 @@ class QdrantHybridRetriever:
 
         return {"documents": docs}
 
-    @component.output_types(documents=List[Document])
+    @component.output_types(documents=list[Document])
     async def run_async(
         self,
-        query_embedding: List[float],
+        query_embedding: list[float],
         query_sparse_embedding: SparseEmbedding,
-        filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
-        top_k: Optional[int] = None,
-        return_embedding: Optional[bool] = None,
-        score_threshold: Optional[float] = None,
-        group_by: Optional[str] = None,
-        group_size: Optional[int] = None,
-    ) -> Dict[str, List[Document]]:
+        filters: dict[str, Any] | models.Filter | None = None,
+        top_k: int | None = None,
+        return_embedding: bool | None = None,
+        score_threshold: float | None = None,
+        group_by: str | None = None,
+        group_size: int | None = None,
+    ) -> dict[str, list[Document]]:
         """
         Asynchronously run the Sparse Embedding Retriever on the given input data.
 

{qdrant_haystack-9.2.0 → qdrant_haystack-10.0.0}/src/haystack_integrations/document_stores/qdrant/converters.py

@@ -1,5 +1,4 @@
 import uuid
-from typing import List, Union
 
 from haystack import logging
 from haystack.dataclasses import Document
@@ -15,10 +14,10 @@ UUID_NAMESPACE = uuid.UUID("3896d314-1e95-4a3a-b45a-945f9f0b541d")
 
 
 def convert_haystack_documents_to_qdrant_points(
-    documents: List[Document],
+    documents: list[Document],
     *,
     use_sparse_embeddings: bool,
-) -> List[rest.PointStruct]:
+) -> list[rest.PointStruct]:
     points = []
     for document in documents:
         payload = document.to_dict(flatten=False)
@@ -58,7 +57,7 @@ def convert_id(_id: str) -> str:
     return uuid.uuid5(UUID_NAMESPACE, _id).hex
 
 
-QdrantPoint = Union[rest.ScoredPoint, rest.Record]
+QdrantPoint = rest.ScoredPoint | rest.Record
 
 
 def convert_qdrant_point_to_haystack_document(point: QdrantPoint, use_sparse_embeddings: bool) -> Document: