qdrant-haystack 3.3.1__tar.gz → 3.4.0__tar.gz

{qdrant_haystack-3.3.1 → qdrant_haystack-3.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: qdrant-haystack
-Version: 3.3.1
+Version: 3.4.0
 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-3.4.0/examples/embedding_retrieval.py

@@ -0,0 +1,52 @@
+# Install required packages for this example, including qdrant-haystack and other libraries needed
+# for Markdown conversion and embeddings generation. Use the following command:
+# pip install qdrant-haystack markdown-it-py mdit_plain sentence-transformers
+
+# Download some Markdown files to index.
+# git clone https://github.com/anakin87/neural-search-pills
+
+import glob
+
+from haystack import Pipeline
+from haystack.components.converters import MarkdownToDocument
+from haystack.components.embedders import SentenceTransformersDocumentEmbedder, SentenceTransformersTextEmbedder
+from haystack.components.preprocessors import DocumentSplitter
+from haystack.components.writers import DocumentWriter
+from haystack_integrations.components.retrievers.qdrant import QdrantEmbeddingRetriever
+from haystack_integrations.document_stores.qdrant import QdrantDocumentStore
+
+# Initialize QdrantDocumentStore: for simplicity, we use an in-memory store here.
+# You can also run a Qdrant instance using Docker or use Qdrant Cloud.
+document_store = QdrantDocumentStore(
+    ":memory:",
+    index="Document",
+    embedding_dim=768,
+    recreate_index=True,
+)
+
+# Create the indexing Pipeline and index some documents
+file_paths = glob.glob("neural-search-pills/pills/*.md")
+
+
+indexing = Pipeline()
+indexing.add_component("converter", MarkdownToDocument())
+indexing.add_component("splitter", DocumentSplitter(split_by="sentence", split_length=2))
+indexing.add_component("embedder", SentenceTransformersDocumentEmbedder())
+indexing.add_component("writer", DocumentWriter(document_store))
+indexing.connect("converter", "splitter")
+indexing.connect("splitter", "embedder")
+indexing.connect("embedder", "writer")
+
+indexing.run({"converter": {"sources": file_paths}})
+
+# Create the querying Pipeline and try a query
+querying = Pipeline()
+querying.add_component("embedder", SentenceTransformersTextEmbedder())
+querying.add_component("retriever", QdrantEmbeddingRetriever(document_store=document_store, top_k=3))
+querying.connect("embedder", "retriever")
+
+results = querying.run({"embedder": {"text": "What is a cross-encoder?"}})
+
+for doc in results["retriever"]["documents"]:
+    print(doc)
+    print("-" * 10)

{qdrant_haystack-3.3.1 → qdrant_haystack-3.4.0}/pyproject.toml

@@ -127,6 +127,8 @@ ban-relative-imports = "parents"
 [tool.ruff.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
 "tests/**/*" = ["PLR2004", "S101", "TID252"]
+# examples can contain "print" commands
+"examples/**/*" = ["T201"]
 
 
 [tool.coverage.run]

qdrant_haystack-3.4.0/src/haystack_integrations/components/retrievers/qdrant/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from .retriever import QdrantEmbeddingRetriever, QdrantSparseEmbeddingRetriever
+
+__all__ = ("QdrantEmbeddingRetriever", "QdrantSparseEmbeddingRetriever")

{qdrant_haystack-3.3.1 → qdrant_haystack-3.4.0}/src/haystack_integrations/components/retrievers/qdrant/retriever.py

@@ -124,13 +124,13 @@ class QdrantEmbeddingRetriever:
 
 
 @component
-class QdrantSparseRetriever:
+class QdrantSparseEmbeddingRetriever:
     """
     A component for retrieving documents from an QdrantDocumentStore using sparse vectors.
 
     Usage example:
     ```python
-    from haystack_integrations.components.retrievers.qdrant import QdrantSparseRetriever
+    from haystack_integrations.components.retrievers.qdrant import QdrantSparseEmbeddingRetriever
     from haystack_integrations.document_stores.qdrant import QdrantDocumentStore
     from haystack.dataclasses.sparse_embedding import SparseEmbedding
 
@@ -140,7 +140,7 @@ class QdrantSparseRetriever:
         return_embedding=True,
         wait_result_from_api=True,
     )
-    retriever = QdrantSparseRetriever(document_store=document_store)
+    retriever = QdrantSparseEmbeddingRetriever(document_store=document_store)
     sparse_embedding = SparseEmbedding(indices=[0, 1, 2, 3], values=[0.1, 0.8, 0.05, 0.33])
     retriever.run(query_sparse_embedding=sparse_embedding)
     ```
@@ -155,7 +155,7 @@ class QdrantSparseRetriever:
         return_embedding: bool = False,
     ):
         """
-        Create a QdrantSparseRetriever component.
+        Create a QdrantSparseEmbeddingRetriever component.
 
         :param document_store: An instance of QdrantDocumentStore.
         :param filters: A dictionary with filters to narrow down the search space. Default is None.

{qdrant_haystack-3.3.1 → qdrant_haystack-3.4.0}/tests/test_retriever.py

@@ -8,7 +8,7 @@ from haystack.testing.document_store import (
 )
 from haystack_integrations.components.retrievers.qdrant import (
     QdrantEmbeddingRetriever,
-    QdrantSparseRetriever,
+    QdrantSparseEmbeddingRetriever,
 )
 from haystack_integrations.document_stores.qdrant import QdrantDocumentStore
 
@@ -135,10 +135,10 @@ class TestQdrantRetriever(FilterableDocsFixtureMixin):
             assert document.embedding is None
 
 
-class TestQdrantSparseRetriever(FilterableDocsFixtureMixin):
+class TestQdrantSparseEmbeddingRetriever(FilterableDocsFixtureMixin):
     def test_init_default(self):
         document_store = QdrantDocumentStore(location=":memory:", index="test")
-        retriever = QdrantSparseRetriever(document_store=document_store)
+        retriever = QdrantSparseEmbeddingRetriever(document_store=document_store)
         assert retriever._document_store == document_store
         assert retriever._filters is None
         assert retriever._top_k == 10
@@ -146,10 +146,10 @@ class TestQdrantSparseRetriever(FilterableDocsFixtureMixin):
 
     def test_to_dict(self):
         document_store = QdrantDocumentStore(location=":memory:", index="test")
-        retriever = QdrantSparseRetriever(document_store=document_store)
+        retriever = QdrantSparseEmbeddingRetriever(document_store=document_store)
         res = retriever.to_dict()
         assert res == {
-            "type": "haystack_integrations.components.retrievers.qdrant.retriever.QdrantSparseRetriever",
+            "type": "haystack_integrations.components.retrievers.qdrant.retriever.QdrantSparseEmbeddingRetriever",
             "init_parameters": {
                 "document_store": {
                     "type": "haystack_integrations.document_stores.qdrant.document_store.QdrantDocumentStore",
@@ -202,7 +202,7 @@ class TestQdrantSparseRetriever(FilterableDocsFixtureMixin):
 
     def test_from_dict(self):
         data = {
-            "type": "haystack_integrations.components.retrievers.qdrant.retriever.QdrantSparseRetriever",
+            "type": "haystack_integrations.components.retrievers.qdrant.retriever.QdrantSparseEmbeddingRetriever",
             "init_parameters": {
                 "document_store": {
                     "init_parameters": {"location": ":memory:", "index": "test"},
@@ -214,7 +214,7 @@ class TestQdrantSparseRetriever(FilterableDocsFixtureMixin):
                 "return_embedding": True,
             },
         }
-        retriever = QdrantSparseRetriever.from_dict(data)
+        retriever = QdrantSparseEmbeddingRetriever.from_dict(data)
         assert isinstance(retriever._document_store, QdrantDocumentStore)
         assert retriever._document_store.index == "test"
         assert retriever._filters is None
@@ -241,7 +241,7 @@ class TestQdrantSparseRetriever(FilterableDocsFixtureMixin):
             doc.sparse_embedding = SparseEmbedding.from_dict(self._generate_mocked_sparse_embedding(1)[0])
 
         document_store.write_documents(filterable_docs)
-        retriever = QdrantSparseRetriever(document_store=document_store)
+        retriever = QdrantSparseEmbeddingRetriever(document_store=document_store)
         sparse_embedding = SparseEmbedding(indices=[0, 1, 2, 3], values=[0.1, 0.8, 0.05, 0.33])
 
         results: List[Document] = retriever.run(query_sparse_embedding=sparse_embedding)["documents"]

qdrant_haystack-3.3.1/src/haystack_integrations/components/retrievers/qdrant/__init__.py

@@ -1,7 +0,0 @@
-# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
-#
-# SPDX-License-Identifier: Apache-2.0
-
-from .retriever import QdrantEmbeddingRetriever, QdrantSparseRetriever
-
-__all__ = ("QdrantEmbeddingRetriever", "QdrantSparseRetriever")