qdrant-haystack 6.0.0__tar.gz → 8.0.0__tar.gz

{qdrant_haystack-6.0.0 → qdrant_haystack-8.0.0}/CHANGELOG.md

@@ -1,5 +1,14 @@
 # Changelog
 
+## [integrations/qdrant-v7.0.0] - 2024-10-29
+
+### ⚙️ Miscellaneous Tasks
+
+- Update ruff linting scripts and settings (#1105)
+- Adopt uv as installer (#1142)
+
+## [integrations/qdrant-v6.0.0] - 2024-09-13
+
 ## [integrations/qdrant-v5.1.0] - 2024-09-12
 
 ### 🚀 Features
@@ -103,8 +112,6 @@
 
 - Fix haystack-ai pin (#649)
 
-
-
 ## [integrations/qdrant-v3.2.0] - 2024-03-27
 
 ### 🚀 Features
@@ -115,15 +122,11 @@
 ### 🐛 Bug Fixes
 
 - Fix linter errors (#282)
-
-
 - Fix order of API docs (#447)
 
 This PR will also push the docs to Readme
 - Fixes (#518)
 
-
-
 ### 🚜 Refactor
 
 - [**breaking**] Qdrant - update secret management (#405)
@@ -154,8 +157,6 @@ This PR will also push the docs to Readme
 
 - Fix import paths for beta5 (#237)
 
-
-
 ### 🚜 Refactor
 
 - Use `hatch_vcs` to manage integrations versioning (#103)

{qdrant_haystack-6.0.0 → qdrant_haystack-8.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: qdrant-haystack
-Version: 6.0.0
+Version: 8.0.0
 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-6.0.0 → qdrant_haystack-8.0.0}/pyproject.toml

@@ -44,6 +44,7 @@ root = "../.."
 git_describe_command = 'git describe --tags --match="integrations/qdrant-v[0-9]*"'
 
 [tool.hatch.envs.default]
+installer = "uv"
 dependencies = ["coverage[toml]>=6.5", "pytest", "pytest-rerunfailures", "haystack-pydoc-tools"]
 [tool.hatch.envs.default.scripts]
 test = "pytest {args:tests}"
@@ -58,12 +59,13 @@ docs = ["pydoc-markdown pydoc/config.yml"]
 python = ["3.8", "3.9", "3.10", "3.11"]
 
 [tool.hatch.envs.lint]
+installer = "uv"
 detached = true
-dependencies = ["black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243"]
+dependencies = ["pip", "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 check {args:. --exclude tests/, examples/}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff --fix {args:. --exclude tests/, examples/}", "style"]
+style = ["ruff check {args:.}", "black --check --diff {args:.}"]
+fmt = ["black {args:.}", "ruff check --fix {args:.}", "style"]
 all = ["style", "typing"]
 
 [tool.black]
@@ -74,6 +76,8 @@ skip-string-normalization = true
 [tool.ruff]
 target-version = "py38"
 line-length = 120
+
+[tool.ruff.lint]
 select = [
   "A",
   "ARG",
@@ -125,10 +129,10 @@ unfixable = [
   "F401",
 ]
 
-[tool.ruff.flake8-tidy-imports]
+[tool.ruff.lint.flake8-tidy-imports]
 ban-relative-imports = "parents"
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
 "tests/**/*" = ["PLR2004", "S101", "TID252"]
 # examples can contain "print" commands

{qdrant_haystack-6.0.0 → qdrant_haystack-8.0.0}/src/haystack_integrations/components/retrievers/qdrant/__init__.py

@@ -4,4 +4,4 @@
 
 from .retriever import QdrantEmbeddingRetriever, QdrantHybridRetriever, QdrantSparseEmbeddingRetriever
 
-__all__ = ("QdrantEmbeddingRetriever", "QdrantSparseEmbeddingRetriever", "QdrantHybridRetriever")
+__all__ = ("QdrantEmbeddingRetriever", "QdrantHybridRetriever", "QdrantSparseEmbeddingRetriever")

{qdrant_haystack-6.0.0 → qdrant_haystack-8.0.0}/src/haystack_integrations/document_stores/qdrant/converters.py

@@ -22,6 +22,15 @@ def convert_haystack_documents_to_qdrant_points(
     points = []
     for document in documents:
         payload = document.to_dict(flatten=False)
+
+        if payload.pop("dataframe", None):
+            logger.warning(
+                "Document %s has the `dataframe` field set,"
+                "QdrantDocumentStore no longer supports dataframes and this field will be ignored. "
+                "The `dataframe` field will soon be removed from Haystack Document.",
+                document.id,
+            )
+
         if use_sparse_embeddings:
             vector = {}
 
@@ -64,6 +73,14 @@ def convert_qdrant_point_to_haystack_document(point: QdrantPoint, use_sparse_emb
     payload = {**point.payload}
     payload["score"] = point.score if hasattr(point, "score") else None
 
+    if payload.pop("dataframe", None):
+        logger.warning(
+            "Document %s has the `dataframe` field set,"
+            "QdrantDocumentStore no longer supports dataframes and this field will be ignored. "
+            "The `dataframe` field will soon be removed from Haystack Document.",
+            payload["id"],
+        )
+
     if not use_sparse_embeddings:
         payload["embedding"] = point.vector if hasattr(point, "vector") else None
     elif hasattr(point, "vector") and point.vector is not None:

{qdrant_haystack-6.0.0 → qdrant_haystack-8.0.0}/src/haystack_integrations/document_stores/qdrant/document_store.py

@@ -362,7 +362,6 @@ class QdrantDocumentStore:
 
         document_objects = self._handle_duplicate_documents(
             documents=documents,
-            index=self.index,
             policy=policy,
         )
 
@@ -468,7 +467,6 @@ class QdrantDocumentStore:
     def get_documents_by_id(
         self,
         ids: List[str],
-        index: Optional[str] = None,
     ) -> List[Document]:
         """
         Retrieves documents from Qdrant by their IDs.
@@ -480,13 +478,11 @@ class QdrantDocumentStore:
         :returns:
             A list of documents.
         """
-        index = index or self.index
-
         documents: List[Document] = []
 
         ids = [convert_id(_id) for _id in ids]
         records = self.client.retrieve(
-            collection_name=index,
+            collection_name=self.index,
             ids=ids,
             with_payload=True,
             with_vectors=True,
@@ -987,7 +983,6 @@ class QdrantDocumentStore:
     def _handle_duplicate_documents(
         self,
         documents: List[Document],
-        index: Optional[str] = None,
         policy: DuplicatePolicy = None,
     ):
         """
@@ -995,31 +990,28 @@ class QdrantDocumentStore:
         documents that are not in the index yet.
 
         :param documents: A list of Haystack Document objects.
-        :param index: name of the index
         :param policy: The duplicate policy to use when writing documents.
         :returns: A list of Haystack Document objects.
         """
 
-        index = index or self.index
         if policy in (DuplicatePolicy.SKIP, DuplicatePolicy.FAIL):
-            documents = self._drop_duplicate_documents(documents, index)
-            documents_found = self.get_documents_by_id(ids=[doc.id for doc in documents], index=index)
+            documents = self._drop_duplicate_documents(documents)
+            documents_found = self.get_documents_by_id(ids=[doc.id for doc in documents])
             ids_exist_in_db: List[str] = [doc.id for doc in documents_found]
 
             if len(ids_exist_in_db) > 0 and policy == DuplicatePolicy.FAIL:
-                msg = f"Document with ids '{', '.join(ids_exist_in_db)} already exists in index = '{index}'."
+                msg = f"Document with ids '{', '.join(ids_exist_in_db)} already exists in index = '{self.index}'."
                 raise DuplicateDocumentError(msg)
 
             documents = list(filter(lambda doc: doc.id not in ids_exist_in_db, documents))
 
         return documents
 
-    def _drop_duplicate_documents(self, documents: List[Document], index: Optional[str] = None) -> List[Document]:
+    def _drop_duplicate_documents(self, documents: List[Document]) -> List[Document]:
         """
         Drop duplicate documents based on same hash ID.
 
         :param documents: A list of Haystack Document objects.
-        :param index: Name of the index.
         :returns: A list of Haystack Document objects.
         """
         _hash_ids: Set = set()
@@ -1030,7 +1022,7 @@ class QdrantDocumentStore:
                 logger.info(
                     "Duplicate Documents: Document with id '%s' already exists in index '%s'",
                     document.id,
-                    index or self.index,
+                    self.index,
                 )
                 continue
             _documents.append(document)

{qdrant_haystack-6.0.0 → qdrant_haystack-8.0.0}/tests/test_converters.py

@@ -1,7 +1,10 @@
 import numpy as np
+from haystack import Document
+from pandas import DataFrame
 from qdrant_client.http import models as rest
 
 from haystack_integrations.document_stores.qdrant.converters import (
+    convert_haystack_documents_to_qdrant_points,
     convert_id,
     convert_qdrant_point_to_haystack_document,
 )
@@ -62,3 +65,44 @@ def test_point_to_document_reverts_proper_structure_from_record_without_sparse()
     assert document.sparse_embedding is None
     assert {"test_field": 1} == document.meta
     assert 0.0 == np.sum(np.array([1.0, 0.0, 0.0, 0.0]) - document.embedding)
+
+
+def test_point_to_document_skips_dataframe():
+
+    point = rest.Record(
+        id="c7c62e8e-02b9-4ec6-9f88-46bd97b628b7",
+        payload={
+            "id": "my-id",
+            "content": "Lorem ipsum",
+            "content_type": "text",
+            "meta": {
+                "test_field": 1,
+            },
+            "dataframe": {"a": [1, 2, 3]},
+        },
+        vector=[1.0, 0.0, 0.0, 0.0],
+    )
+    document = convert_qdrant_point_to_haystack_document(point, use_sparse_embeddings=False)
+    assert "my-id" == document.id
+    assert "Lorem ipsum" == document.content
+    assert "text" == document.content_type
+    assert {"test_field": 1} == document.meta
+    assert 0.0 == np.sum(np.array([1.0, 0.0, 0.0, 0.0]) - document.embedding)
+    assert not hasattr(document, "dataframe") or document.dataframe is None
+
+
+def test_documents_to_points_skips_dataframe():
+    doc = Document(
+        id="my-id",
+        content="Lorem ipsum",
+        embedding=[1.0, 0.0, 0.0, 0.0],
+    )
+
+    doc.dataframe = DataFrame([[1, 2], [3, 4]])
+
+    points = convert_haystack_documents_to_qdrant_points([doc], use_sparse_embeddings=False)
+    assert len(points) == 1
+
+    assert points[0].payload["content"] == "Lorem ipsum"
+    assert points[0].vector == [1.0, 0.0, 0.0, 0.0]
+    assert "dataframe" not in points[0].payload

{qdrant_haystack-6.0.0 → qdrant_haystack-8.0.0}/tests/test_filters.py

@@ -208,11 +208,5 @@ class TestQdrantStoreBaseTests(FilterDocumentsTest):
 
     # ======== ========================== ========
 
-    @pytest.mark.skip(reason="Qdrant doesn't support comparision with dataframe")
-    def test_comparison_equal_with_dataframe(self, document_store, filterable_docs): ...
-
-    @pytest.mark.skip(reason="Qdrant doesn't support comparision with dataframe")
-    def test_comparison_not_equal_with_dataframe(self, document_store, filterable_docs): ...
-
     @pytest.mark.skip(reason="Cannot distinguish errors yet")
     def test_missing_top_level_operator_key(self, document_store, filterable_docs): ...