Merge branch 'main' into qdrant-hybrid-retriever

.github/labeler.yml

@@ -119,11 +119,6 @@ integration:unstructured-fileconverter:
       - any-glob-to-any-file: "integrations/unstructured/**/*"
       - any-glob-to-any-file: ".github/workflows/unstructured.yml"
 
-integration:uptrain:
-  - changed-files:
-      - any-glob-to-any-file: "integrations/uptrain/**/*"
-      - any-glob-to-any-file: ".github/workflows/uptrain.yml"
-
 integration:weaviate:
   - changed-files:
       - any-glob-to-any-file: "integrations/weaviate/**/*"

integrations/qdrant/src/haystack_integrations/components/retrievers/qdrant/__init__.py

@@ -2,6 +2,6 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
-from .retriever import QdrantEmbeddingRetriever, QdrantHybridRetriever, QdrantSparseRetriever
+from .retriever import QdrantEmbeddingRetriever, QdrantHybridRetriever, QdrantSparseEmbeddingRetriever
 
-__all__ = ("QdrantEmbeddingRetriever", "QdrantSparseRetriever", "QdrantHybridRetriever")
+__all__ = ("QdrantEmbeddingRetriever", "QdrantSparseEmbeddingRetriever", "QdrantHybridRetriever")

integrations/qdrant/src/haystack_integrations/components/retrievers/qdrant/retriever.py

@@ -126,13 +126,13 @@ def run(
 
 
 @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
 
@@ -146,7 +146,7 @@ class QdrantSparseRetriever:
     doc = Document(content="test", sparse_embedding=SparseEmbedding(indices=[0, 3, 5], values=[0.1, 0.5, 0.12]))
     document_store.write_documents([doc])
 
-    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)
     ```
@@ -161,7 +161,7 @@ def __init__(
         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.
@@ -202,7 +202,7 @@ def to_dict(self) -> Dict[str, Any]:
         return d
 
     @classmethod
-    def from_dict(cls, data: Dict[str, Any]) -> "QdrantSparseRetriever":
+    def from_dict(cls, data: Dict[str, Any]) -> "QdrantSparseEmbeddingRetriever":
         """
         Deserializes the component from a dictionary.
 

integrations/qdrant/tests/test_retriever.py

@@ -9,7 +9,7 @@
 from haystack_integrations.components.retrievers.qdrant import (
     QdrantEmbeddingRetriever,
     QdrantHybridRetriever,
-    QdrantSparseRetriever,
+    QdrantSparseEmbeddingRetriever,
 )
 from haystack_integrations.document_stores.qdrant import QdrantDocumentStore
 
@@ -138,21 +138,21 @@ def test_run_with_sparse_activated(self, filterable_docs: List[Document]):
             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
         assert retriever._return_embedding is False
 
     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",
@@ -205,7 +205,7 @@ def test_to_dict(self):
 
     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"},
@@ -217,7 +217,7 @@ def test_from_dict(self):
                 "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
@@ -233,7 +233,7 @@ def test_run(self, filterable_docs: List[Document]):
             doc.sparse_embedding = SparseEmbedding.from_dict(_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"]

integrations/ragas/pyproject.toml

@@ -21,7 +21,7 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai", "ragas==0.1.1"]
+dependencies = ["haystack-ai", "ragas"]
 
 [project.urls]
 Source = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/ragas"
@@ -152,6 +152,7 @@ module = [
   "haystack.*",
   "pytest.*",
   "ragas.*",
+  "datasets.*",
   "numpy",
   "grpc",
   "haystack_integrations.*",

integrations/ragas/src/haystack_integrations/components/evaluators/ragas/evaluator.py

@@ -1,12 +1,12 @@
 import json
 from typing import Any, Callable, Dict, List, Optional, Union
 
-from datasets import Dataset  # type: ignore
+from datasets import Dataset
 from haystack import DeserializationError, component, default_from_dict, default_to_dict
 
 from ragas import evaluate  # type: ignore
-from ragas.evaluation import Result  # type: ignore
-from ragas.metrics.base import Metric  # type: ignore
+from ragas.evaluation import Result
+from ragas.metrics.base import Metric
 
 from .metrics import (
     METRIC_DESCRIPTORS,

integrations/ragas/src/haystack_integrations/components/evaluators/ragas/metrics.py

@@ -16,7 +16,7 @@
     ContextUtilization,  # type: ignore
     Faithfulness,  # type: ignore
 )
-from ragas.metrics.base import Metric  # type: ignore
+from ragas.metrics.base import Metric
 
 
 class RagasBaseEnum(Enum):