qdrant-haystack 6.0.0__py3-none-any.whl → 8.0.0__py3-none-any.whl

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")

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:

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.dist-info → qdrant_haystack-8.0.0.dist-info}/METADATA

@@ -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.dist-info → qdrant_haystack-8.0.0.dist-info}/RECORD

@@ -1,11 +1,11 @@
-haystack_integrations/components/retrievers/qdrant/__init__.py,sha256=IRjcM4f8b5eKFEMn8tn6h6RrfslEGP3WafU7mrzNzQM,313
+haystack_integrations/components/retrievers/qdrant/__init__.py,sha256=AE1hdw4sqb0rTSqfAxKCRUOZVE8gbHdQ1wDccdN86hc,313
 haystack_integrations/components/retrievers/qdrant/retriever.py,sha256=VsQVsvf79imTCdWUKikUxpjczl5oxOV64a91aGXZwpE,21997
 haystack_integrations/document_stores/qdrant/__init__.py,sha256=kUGc5uewqArhmVR-JqB_NmJ4kNkTIQIvYDNSoO2ELn0,302
-haystack_integrations/document_stores/qdrant/converters.py,sha256=2hcuI3kty1dVHzX1WGXxEtlrnZ9E8TAG56XATCFa6Pw,2491
-haystack_integrations/document_stores/qdrant/document_store.py,sha256=lljz3ksd6naKM9bsFaaaKLC1W6ZkyCCLFVR44WaQ1oA,42552
+haystack_integrations/document_stores/qdrant/converters.py,sha256=ndFZjMjweJJDyC_994zDX4BGhGcW1SfLf79zBeyUits,3192
+haystack_integrations/document_stores/qdrant/document_store.py,sha256=pcVuU9pNdjwROISG19vaj2Zpkl4_N2k_3UOi2XO7b00,42246
 haystack_integrations/document_stores/qdrant/filters.py,sha256=Nv_eKIYKwUWvldJfa0omfFQ0kgqi6L3DUFeMuIWziOY,11751
 haystack_integrations/document_stores/qdrant/migrate_to_sparse.py,sha256=yhZr4GB6N1S-Ikzl52hpuZt2aHNIb4leqFDhVMU3Uho,4910
-qdrant_haystack-6.0.0.dist-info/METADATA,sha256=2EO3rBoGCI7Umy8XPhXj9eE8bSbYLDXUErdtA9yqmtQ,1863
-qdrant_haystack-6.0.0.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-qdrant_haystack-6.0.0.dist-info/licenses/LICENSE.txt,sha256=B05uMshqTA74s-0ltyHKI6yoPfJ3zYgQbvcXfDVGFf8,10280
-qdrant_haystack-6.0.0.dist-info/RECORD,,
+qdrant_haystack-8.0.0.dist-info/METADATA,sha256=PorUoQRLkK0yhoMEifdBakszFFneNjT7KEkKIxvJ6Fg,1863
+qdrant_haystack-8.0.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+qdrant_haystack-8.0.0.dist-info/licenses/LICENSE.txt,sha256=B05uMshqTA74s-0ltyHKI6yoPfJ3zYgQbvcXfDVGFf8,10280
+qdrant_haystack-8.0.0.dist-info/RECORD,,

{qdrant_haystack-6.0.0.dist-info → qdrant_haystack-8.0.0.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.25.0
+Generator: hatchling 1.27.0
 Root-Is-Purelib: true
 Tag: py3-none-any