qdrant-haystack 3.8.1__tar.gz → 4.0.0__tar.gz

{qdrant_haystack-3.8.1 → qdrant_haystack-4.0.0}/.gitignore

@@ -135,3 +135,12 @@ dmypy.json
 # Docs generation artifacts
 _readme_*.md
 .idea
+
+# macOS
+.DS_Store
+
+# http cache (requests-cache)
+**/http_cache.sqlite
+
+# ruff
+.ruff_cache

{qdrant_haystack-3.8.1 → qdrant_haystack-4.0.0}/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## [integrations/qdrant-v3.8.1] - 2024-06-20
+
+### 📚 Documentation
+
+- Added docstrings for QdrantDocumentStore (#808)
+
 ## [integrations/qdrant-v3.8.0] - 2024-06-06
 
 ### 🚀 Features

{qdrant_haystack-3.8.1 → qdrant_haystack-4.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: qdrant-haystack
-Version: 3.8.1
+Version: 4.0.0
 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

{qdrant_haystack-3.8.1 → qdrant_haystack-4.0.0}/pyproject.toml

@@ -44,10 +44,10 @@ root = "../.."
 git_describe_command = 'git describe --tags --match="integrations/qdrant-v[0-9]*"'
 
 [tool.hatch.envs.default]
-dependencies = ["coverage[toml]>=6.5", "pytest", "haystack-pydoc-tools"]
+dependencies = ["coverage[toml]>=6.5", "pytest", "pytest-rerunfailures", "haystack-pydoc-tools"]
 [tool.hatch.envs.default.scripts]
-test = "pytest {args:tests}"
-test-cov = "coverage run -m pytest {args:tests}"
+test = "pytest --reruns 3 --reruns-delay 30 -x {args:tests}"
+test-cov = "coverage run -m pytest --reruns 3 --reruns-delay 30 -x {args:tests}"
 cov-report = ["- coverage combine", "coverage report"]
 cov = ["test-cov", "cov-report"]
 docs = ["pydoc-markdown pydoc/config.yml"]
@@ -60,7 +60,7 @@ detached = true
 dependencies = ["black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243"]
 [tool.hatch.envs.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
-style = ["ruff {args:.}", "black --check --diff {args:.}"]
+style = ["ruff check {args:.}", "black --check --diff {args:.}"]
 fmt = ["black {args:.}", "ruff --fix {args:.}", "style"]
 all = ["style", "typing"]
 
@@ -105,7 +105,8 @@ ignore = [
   # Allow boolean positional values in function calls, like `dict.get(... True)`
   "FBT003",
   # Allow boolean arguments in function definition
-  "FBT001", "FBT002",
+  "FBT001",
+  "FBT002",
   # Ignore checks for possible passwords
   "S105",
   "S106",
@@ -140,12 +141,8 @@ parallel = false
 
 [tool.coverage.report]
 omit = ["*/tests/*", "*/__init__.py"]
-show_missing=true
-exclude_lines = [
-  "no cov",
-  "if __name__ == .__main__.:",
-  "if TYPE_CHECKING:",
-]
+show_missing = true
+exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
 
 
 [[tool.mypy.overrides]]

{qdrant_haystack-3.8.1 → qdrant_haystack-4.0.0}/src/haystack_integrations/components/retrievers/qdrant/retriever.py

@@ -37,7 +37,7 @@ class QdrantEmbeddingRetriever:
         document_store: QdrantDocumentStore,
         filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
         top_k: int = 10,
-        scale_score: bool = True,
+        scale_score: bool = False,
         return_embedding: bool = False,
     ):
         """
@@ -159,7 +159,7 @@ class QdrantSparseEmbeddingRetriever:
         document_store: QdrantDocumentStore,
         filters: Optional[Union[Dict[str, Any], models.Filter]] = None,
         top_k: int = 10,
-        scale_score: bool = True,
+        scale_score: bool = False,
         return_embedding: bool = False,
     ):
         """

{qdrant_haystack-3.8.1 → qdrant_haystack-4.0.0}/src/haystack_integrations/document_stores/qdrant/converters.py

@@ -17,7 +17,6 @@ UUID_NAMESPACE = uuid.UUID("3896d314-1e95-4a3a-b45a-945f9f0b541d")
 def convert_haystack_documents_to_qdrant_points(
     documents: List[Document],
     *,
-    embedding_field: str,
     use_sparse_embeddings: bool,
 ) -> List[rest.PointStruct]:
     points = []
@@ -26,7 +25,7 @@ def convert_haystack_documents_to_qdrant_points(
         if use_sparse_embeddings:
             vector = {}
 
-            dense_vector = payload.pop(embedding_field, None)
+            dense_vector = payload.pop("embedding", None)
             if dense_vector is not None:
                 vector[DENSE_VECTORS_NAME] = dense_vector
 
@@ -36,7 +35,7 @@ def convert_haystack_documents_to_qdrant_points(
                 vector[SPARSE_VECTORS_NAME] = sparse_vector_instance
 
         else:
-            vector = payload.pop(embedding_field) or {}
+            vector = payload.pop("embedding") or {}
         _id = convert_id(payload.get("id"))
 
         point = rest.PointStruct(

{qdrant_haystack-3.8.1 → qdrant_haystack-4.0.0}/src/haystack_integrations/document_stores/qdrant/document_store.py

@@ -110,14 +110,10 @@ class QdrantDocumentStore:
         index: str = "Document",
         embedding_dim: int = 768,
         on_disk: bool = False,
-        content_field: str = "content",
-        name_field: str = "name",
-        embedding_field: str = "embedding",
         use_sparse_embeddings: bool = False,
         similarity: str = "cosine",
         return_embedding: bool = False,
         progress_bar: bool = True,
-        duplicate_documents: str = "overwrite",
         recreate_index: bool = False,
         shard_number: Optional[int] = None,
         replication_factor: Optional[int] = None,
@@ -170,12 +166,6 @@ class QdrantDocumentStore:
             Dimension of the embeddings.
         :param on_disk:
             Whether to store the collection on disk.
-        :param content_field:
-            The field for the document content.
-        :param name_field:
-            The field for the document name.
-        :param embedding_field:
-            The field for the document embeddings.
         :param use_sparse_embedding:
             If set to `True`, enables support for sparse embeddings.
         :param similarity:
@@ -184,8 +174,6 @@ class QdrantDocumentStore:
             Whether to return embeddings in the search results.
         :param progress_bar:
             Whether to show a progress bar or not.
-        :param duplicate_documents:
-            The parameter is not used and will be removed in future release.
         :param recreate_index:
             Whether to recreate the index.
         :param shard_number:
@@ -260,14 +248,10 @@ class QdrantDocumentStore:
         self.use_sparse_embeddings = use_sparse_embeddings
         self.embedding_dim = embedding_dim
         self.on_disk = on_disk
-        self.content_field = content_field
-        self.name_field = name_field
-        self.embedding_field = embedding_field
         self.similarity = similarity
         self.index = index
         self.return_embedding = return_embedding
         self.progress_bar = progress_bar
-        self.duplicate_documents = duplicate_documents
         self.write_batch_size = write_batch_size
         self.scroll_size = scroll_size
 
@@ -380,7 +364,6 @@ class QdrantDocumentStore:
             for document_batch in batched_documents:
                 batch = convert_haystack_documents_to_qdrant_points(
                     document_batch,
-                    embedding_field=self.embedding_field,
                     use_sparse_embeddings=self.use_sparse_embeddings,
                 )
 
@@ -513,7 +496,7 @@ class QdrantDocumentStore:
         query_sparse_embedding: SparseEmbedding,
         filters: Optional[Union[Dict[str, Any], rest.Filter]] = None,
         top_k: int = 10,
-        scale_score: bool = True,
+        scale_score: bool = False,
         return_embedding: bool = False,
     ) -> List[Document]:
         """
@@ -570,7 +553,7 @@ class QdrantDocumentStore:
         query_embedding: List[float],
         filters: Optional[Union[Dict[str, Any], rest.Filter]] = None,
         top_k: int = 10,
-        scale_score: bool = True,
+        scale_score: bool = False,
         return_embedding: bool = False,
     ) -> List[Document]:
         """
@@ -891,12 +874,7 @@ class QdrantDocumentStore:
 
         :param documents: A list of Haystack Document objects.
         :param index: name of the index
-        :param duplicate_documents: Handle duplicate documents based on parameter options.
-                                    Parameter options : ( 'skip','overwrite','fail')
-                                    skip (default option): Ignore the duplicates documents.
-                                    overwrite: Update any existing documents with the same ID when adding documents.
-                                    fail: An error is raised if the document ID of the document being added already
-                                    exists.
+        :param policy: The duplicate policy to use when writing documents.
         :returns: A list of Haystack Document objects.
         """
 

{qdrant_haystack-3.8.1 → qdrant_haystack-4.0.0}/tests/test_dict_converters.py

@@ -22,15 +22,11 @@ def test_to_dict():
             "index": "test",
             "embedding_dim": 768,
             "on_disk": False,
-            "content_field": "content",
-            "name_field": "name",
-            "embedding_field": "embedding",
             "force_disable_check_same_thread": False,
             "use_sparse_embeddings": False,
             "similarity": "cosine",
             "return_embedding": False,
             "progress_bar": True,
-            "duplicate_documents": "overwrite",
             "recreate_index": False,
             "shard_number": None,
             "replication_factor": None,
@@ -62,15 +58,11 @@ def test_from_dict():
                 "index": "test",
                 "embedding_dim": 768,
                 "on_disk": False,
-                "content_field": "content",
-                "name_field": "name",
-                "embedding_field": "embedding",
                 "force_disable_check_same_thread": False,
                 "use_sparse_embeddings": True,
                 "similarity": "cosine",
                 "return_embedding": False,
                 "progress_bar": True,
-                "duplicate_documents": "overwrite",
                 "recreate_index": True,
                 "shard_number": None,
                 "quantization_config": None,
@@ -87,16 +79,12 @@ def test_from_dict():
     assert all(
         [
             document_store.index == "test",
-            document_store.content_field == "content",
-            document_store.name_field == "name",
-            document_store.embedding_field == "embedding",
             document_store.force_disable_check_same_thread is False,
             document_store.use_sparse_embeddings is True,
             document_store.on_disk is False,
             document_store.similarity == "cosine",
             document_store.return_embedding is False,
             document_store.progress_bar,
-            document_store.duplicate_documents == "overwrite",
             document_store.recreate_index is True,
             document_store.shard_number is None,
             document_store.replication_factor is None,

{qdrant_haystack-3.8.1 → qdrant_haystack-4.0.0}/tests/test_retriever.py

@@ -47,15 +47,11 @@ class TestQdrantRetriever(FilterableDocsFixtureMixin):
                         "index": "test",
                         "embedding_dim": 768,
                         "on_disk": False,
-                        "content_field": "content",
-                        "name_field": "name",
                         "force_disable_check_same_thread": False,
-                        "embedding_field": "embedding",
                         "use_sparse_embeddings": False,
                         "similarity": "cosine",
                         "return_embedding": False,
                         "progress_bar": True,
-                        "duplicate_documents": "overwrite",
                         "recreate_index": False,
                         "shard_number": None,
                         "replication_factor": None,
@@ -75,7 +71,7 @@ class TestQdrantRetriever(FilterableDocsFixtureMixin):
                 },
                 "filters": None,
                 "top_k": 10,
-                "scale_score": True,
+                "scale_score": False,
                 "return_embedding": False,
             },
         }
@@ -170,15 +166,11 @@ class TestQdrantSparseEmbeddingRetriever(FilterableDocsFixtureMixin):
                         "index": "test",
                         "embedding_dim": 768,
                         "on_disk": False,
-                        "content_field": "content",
-                        "name_field": "name",
-                        "embedding_field": "embedding",
                         "force_disable_check_same_thread": False,
                         "use_sparse_embeddings": False,
                         "similarity": "cosine",
                         "return_embedding": False,
                         "progress_bar": True,
-                        "duplicate_documents": "overwrite",
                         "recreate_index": False,
                         "shard_number": None,
                         "replication_factor": None,
@@ -198,7 +190,7 @@ class TestQdrantSparseEmbeddingRetriever(FilterableDocsFixtureMixin):
                 },
                 "filters": None,
                 "top_k": 10,
-                "scale_score": True,
+                "scale_score": False,
                 "return_embedding": False,
             },
         }
@@ -280,15 +272,11 @@ class TestQdrantHybridRetriever:
                         "index": "test",
                         "embedding_dim": 768,
                         "on_disk": False,
-                        "content_field": "content",
-                        "name_field": "name",
-                        "embedding_field": "embedding",
                         "force_disable_check_same_thread": False,
                         "use_sparse_embeddings": False,
                         "similarity": "cosine",
                         "return_embedding": False,
                         "progress_bar": True,
-                        "duplicate_documents": "overwrite",
                         "recreate_index": False,
                         "shard_number": None,
                         "replication_factor": None,