test: adopt MockTextEmbedder in tests

test/components/retrievers/test_multi_query_embedding_retriever.py

@@ -6,11 +6,10 @@
 from typing import Any
 from unittest.mock import ANY, AsyncMock, Mock
 
-import numpy as np
 import pytest
 
 from haystack import Document, Pipeline, component
-from haystack.components.embedders import OpenAIDocumentEmbedder, OpenAITextEmbedder
+from haystack.components.embedders import MockTextEmbedder, OpenAIDocumentEmbedder, OpenAITextEmbedder
 from haystack.components.generators.chat import OpenAIChatGenerator
 from haystack.components.query import QueryExpander
 from haystack.components.retrievers import InMemoryEmbeddingRetriever, MultiQueryEmbeddingRetriever
@@ -19,13 +18,6 @@
 from haystack.document_stores.types import DuplicatePolicy
 
 
-@component
-class MockQueryEmbedder:
-    @component.output_types(embedding=list[float])
-    def run(self, text: str) -> dict[str, list[float]]:
-        return {"embedding": np.ones(384).tolist()}
-
-
 class TestMultiQueryEmbeddingRetriever:
     @pytest.fixture
     def sample_documents(self):
@@ -74,15 +66,15 @@ def document_store_with_embeddings(self, sample_documents):
 
     def test_init_with_default_parameters(self, in_memory_doc_store):
         embedding_retriever = InMemoryEmbeddingRetriever(document_store=in_memory_doc_store)
-        query_embedder = MockQueryEmbedder()
+        query_embedder = MockTextEmbedder()
         retriever = MultiQueryEmbeddingRetriever(retriever=embedding_retriever, query_embedder=query_embedder)
         assert retriever.retriever == embedding_retriever
         assert retriever.query_embedder == query_embedder
         assert retriever.max_workers == 3
 
     def test_init_with_custom_parameters(self, in_memory_doc_store):
         embedding_retriever = InMemoryEmbeddingRetriever(document_store=in_memory_doc_store)
-        query_embedder = MockQueryEmbedder()
+        query_embedder = MockTextEmbedder()
         retriever = MultiQueryEmbeddingRetriever(
             retriever=embedding_retriever, query_embedder=query_embedder, max_workers=2
         )
@@ -92,15 +84,15 @@ def test_init_with_custom_parameters(self, in_memory_doc_store):
 
     def test_run_with_empty_queries(self, in_memory_doc_store):
         multi_retriever = MultiQueryEmbeddingRetriever(
-            retriever=InMemoryEmbeddingRetriever(document_store=in_memory_doc_store), query_embedder=MockQueryEmbedder()
+            retriever=InMemoryEmbeddingRetriever(document_store=in_memory_doc_store), query_embedder=MockTextEmbedder()
         )
         result = multi_retriever.run(queries=[])
         assert "documents" in result
         assert result["documents"] == []
 
     def test_run_with_empty_results(self, in_memory_doc_store):
         multi_retriever = MultiQueryEmbeddingRetriever(
-            retriever=InMemoryEmbeddingRetriever(document_store=in_memory_doc_store), query_embedder=MockQueryEmbedder()
+            retriever=InMemoryEmbeddingRetriever(document_store=in_memory_doc_store), query_embedder=MockTextEmbedder()
         )
         result = multi_retriever.run(queries=["query"])
         assert "documents" in result
@@ -109,7 +101,7 @@ def test_run_with_empty_results(self, in_memory_doc_store):
     def test_to_dict(self, in_memory_doc_store):
         multi_retriever = MultiQueryEmbeddingRetriever(
             retriever=InMemoryEmbeddingRetriever(document_store=in_memory_doc_store),
-            query_embedder=MockQueryEmbedder(),
+            query_embedder=MockTextEmbedder(),
             max_workers=2,
         )
         result = multi_retriever.to_dict()
@@ -139,8 +131,16 @@ def test_to_dict(self, in_memory_doc_store):
                     },
                 },
                 "query_embedder": {
-                    "type": "retrievers.test_multi_query_embedding_retriever.MockQueryEmbedder",
-                    "init_parameters": {},
+                    "type": "haystack.components.embedders.mock_text_embedder.MockTextEmbedder",
+                    "init_parameters": {
+                        "embedding": None,
+                        "embedding_fn": None,
+                        "dimension": 768,
+                        "model": "mock-model",
+                        "meta": {},
+                        "prefix": "",
+                        "suffix": "",
+                    },
                 },
                 "max_workers": 2,
             },
@@ -219,7 +219,7 @@ def run(
                 return {"documents": [doc3, doc2]}
 
         multi_retriever = MultiQueryEmbeddingRetriever(
-            retriever=MockRetriever(), query_embedder=MockQueryEmbedder(), max_workers=1
+            retriever=MockRetriever(), query_embedder=MockTextEmbedder(), max_workers=1
         )
         result = multi_retriever.run(queries=["query1", "query2"])
 

test/components/retrievers/test_multi_query_embedding_retriever_async.py

@@ -8,27 +8,17 @@
 import pytest
 
 from haystack import Document, Pipeline, component
+from haystack.components.embedders import MockTextEmbedder
 from haystack.components.retrievers import InMemoryEmbeddingRetriever, MultiQueryEmbeddingRetriever
 from haystack.document_stores.in_memory import InMemoryDocumentStore
 
 
-@component
-class MockQueryEmbedder:
-    @component.output_types(embedding=list[float])
-    def run(self, text: str) -> dict[str, list[float]]:
-        return {"embedding": np.ones(384).tolist()}
-
-    @component.output_types(embedding=list[float])
-    async def run_async(self, text: str) -> dict[str, list[float]]:
-        return {"embedding": np.ones(384).tolist()}
-
-
 class TestMultiQueryEmbeddingRetrieverAsync:
     @pytest.mark.asyncio
     async def test_run_async_with_empty_queries(self):
         multi_retriever = MultiQueryEmbeddingRetriever(
             retriever=InMemoryEmbeddingRetriever(document_store=InMemoryDocumentStore()),
-            query_embedder=MockQueryEmbedder(),
+            query_embedder=MockTextEmbedder(),
         )
         result = await multi_retriever.run_async(queries=[])
         assert "documents" in result
@@ -62,7 +52,7 @@ async def run_async(
             ) -> dict[str, list[Document]]:
                 return {"documents": [doc_low, doc_high, doc_mid]}
 
-        multi_retriever = MultiQueryEmbeddingRetriever(retriever=MockRetriever(), query_embedder=MockQueryEmbedder())
+        multi_retriever = MultiQueryEmbeddingRetriever(retriever=MockRetriever(), query_embedder=MockTextEmbedder())
         result = await multi_retriever.run_async(queries=["query1", "query2"])
 
         scores = [doc.score for doc in result["documents"]]
@@ -96,7 +86,7 @@ async def run_async(
             ) -> dict[str, list[Document]]:
                 return {"documents": [doc3, doc2]}
 
-        multi_retriever = MultiQueryEmbeddingRetriever(retriever=MockRetriever(), query_embedder=MockQueryEmbedder())
+        multi_retriever = MultiQueryEmbeddingRetriever(retriever=MockRetriever(), query_embedder=MockTextEmbedder())
         result = await multi_retriever.run_async(queries=["query1", "query2"])
 
         assert "documents" in result
@@ -131,9 +121,7 @@ def run(
             ) -> dict[str, list[Document]]:
                 return {"documents": [Document(content="Solar energy", id="doc1", score=0.9)]}
 
-        multi_retriever = MultiQueryEmbeddingRetriever(
-            retriever=SyncOnlyRetriever(), query_embedder=MockQueryEmbedder()
-        )
+        multi_retriever = MultiQueryEmbeddingRetriever(retriever=SyncOnlyRetriever(), query_embedder=MockTextEmbedder())
         result = await multi_retriever.run_async(queries=["query1", "query2"])
         assert "documents" in result
         assert len(result["documents"]) == 1
@@ -188,7 +176,7 @@ async def test_run_async_with_filters(self, document_store_with_categorized_docs
         in_memory_retriever = InMemoryEmbeddingRetriever(document_store=document_store_with_categorized_docs)
         filters = {"field": "category", "operator": "==", "value": "solar"}
         multi_retriever = MultiQueryEmbeddingRetriever(
-            retriever=in_memory_retriever, query_embedder=MockQueryEmbedder()
+            retriever=in_memory_retriever, query_embedder=MockTextEmbedder(dimension=384)
         )
         result = await multi_retriever.run_async(
             queries=["energy", "sunlight", "photovoltaic"], retriever_kwargs={"filters": filters}
@@ -202,7 +190,7 @@ async def test_run_async_with_filters(self, document_store_with_categorized_docs
     async def test_run_async_with_pipeline(self):
         multi_retriever = MultiQueryEmbeddingRetriever(
             retriever=InMemoryEmbeddingRetriever(document_store=InMemoryDocumentStore()),
-            query_embedder=MockQueryEmbedder(),
+            query_embedder=MockTextEmbedder(),
         )
         pipeline = Pipeline()
         pipeline.add_component("retriever", multi_retriever)

test/components/retrievers/test_text_embedding_retriever.py

@@ -6,24 +6,16 @@
 from typing import Any
 from unittest.mock import ANY, AsyncMock, Mock
 
-import numpy as np
 import pytest
 
 from haystack import Document, component
-from haystack.components.embedders import OpenAIDocumentEmbedder, OpenAITextEmbedder
+from haystack.components.embedders import MockTextEmbedder, OpenAIDocumentEmbedder, OpenAITextEmbedder
 from haystack.components.retrievers import InMemoryEmbeddingRetriever, TextEmbeddingRetriever
 from haystack.components.writers import DocumentWriter
 from haystack.document_stores.in_memory import InMemoryDocumentStore
 from haystack.document_stores.types import DuplicatePolicy
 
 
-@component
-class MockTextEmbedder:
-    @component.output_types(embedding=list[float])
-    def run(self, text: str) -> dict[str, list[float]]:
-        return {"embedding": np.ones(384).tolist()}
-
-
 class TestTextEmbeddingRetriever:
     @pytest.fixture
     def sample_documents(self):
@@ -113,8 +105,16 @@ def test_to_dict(self):
                     },
                 },
                 "text_embedder": {
-                    "type": "retrievers.test_text_embedding_retriever.MockTextEmbedder",
-                    "init_parameters": {},
+                    "type": "haystack.components.embedders.mock_text_embedder.MockTextEmbedder",
+                    "init_parameters": {
+                        "embedding": None,
+                        "embedding_fn": None,
+                        "dimension": 768,
+                        "model": "mock-model",
+                        "meta": {},
+                        "prefix": "",
+                        "suffix": "",
+                    },
                 },
             },
         }

test/components/retrievers/test_text_embedding_retriever_async.py

@@ -8,21 +8,11 @@
 import pytest
 
 from haystack import Document, Pipeline, component
+from haystack.components.embedders import MockTextEmbedder
 from haystack.components.retrievers import InMemoryEmbeddingRetriever, TextEmbeddingRetriever
 from haystack.document_stores.in_memory import InMemoryDocumentStore
 
 
-@component
-class MockTextEmbedder:
-    @component.output_types(embedding=list[float])
-    def run(self, text: str) -> dict[str, list[float]]:
-        return {"embedding": np.ones(384).tolist()}
-
-    @component.output_types(embedding=list[float])
-    async def run_async(self, text: str) -> dict[str, list[float]]:
-        return {"embedding": np.ones(384).tolist()}
-
-
 class TestTextEmbeddingRetrieverAsync:
     @pytest.mark.asyncio
     async def test_run_async_with_empty_document_store(self):
@@ -114,7 +104,7 @@ def document_store_with_categorized_docs(self):
     async def test_run_async_with_filters(self, document_store_with_categorized_docs):
         retriever = TextEmbeddingRetriever(
             retriever=InMemoryEmbeddingRetriever(document_store=document_store_with_categorized_docs),
-            text_embedder=MockTextEmbedder(),
+            text_embedder=MockTextEmbedder(dimension=384),
         )
         filters = {"field": "category", "operator": "==", "value": "solar"}
         result = await retriever.run_async(query="energy", filters=filters)

test/core/pipeline/breakpoints/test_pipeline_breakpoints_rag_hybrid.py

@@ -10,20 +10,14 @@
 from haystack import Document, Pipeline, component
 from haystack.components.builders.answer_builder import AnswerBuilder
 from haystack.components.builders.prompt_builder import PromptBuilder
+from haystack.components.embedders import MockTextEmbedder
 from haystack.components.joiners import DocumentJoiner
 from haystack.components.retrievers.in_memory import InMemoryBM25Retriever, InMemoryEmbeddingRetriever
 from haystack.core.errors import BreakpointException
 from haystack.dataclasses.breakpoints import Breakpoint
 from haystack.document_stores.in_memory import InMemoryDocumentStore
 
 
-@component
-class FakeEmbedder:
-    @component.output_types(documents=list[Document], embedding=list[float])
-    def run(self, text: str) -> dict[str, list[Document] | list[float]]:
-        return {"embedding": [random() for _ in range(100)]}
-
-
 @component
 class FakeRanker:
     @component.output_types(documents=list[Document])
@@ -67,7 +61,7 @@ def hybrid_rag_pipeline(self, document_store):
 
         pipeline = Pipeline()
         pipeline.add_component("bm25_retriever", InMemoryBM25Retriever(document_store=document_store))
-        pipeline.add_component("query_embedder", FakeEmbedder())
+        pipeline.add_component("query_embedder", MockTextEmbedder(dimension=100))
         pipeline.add_component("embedding_retriever", InMemoryEmbeddingRetriever(document_store=document_store))
         pipeline.add_component("doc_joiner", DocumentJoiner())
         pipeline.add_component("ranker", FakeRanker())

test/core/pipeline/features/test_run.py

@@ -22,6 +22,7 @@
     OutputAdapter,
     TextFileToDocument,
 )
+from haystack.components.embedders import MockTextEmbedder
 from haystack.components.joiners import AnswerJoiner, BranchJoiner, DocumentJoiner, StringJoiner
 from haystack.components.preprocessors import DocumentCleaner, DocumentSplitter
 from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
@@ -1701,12 +1702,6 @@ def run(self, query: str) -> dict[str, str]:
                 return {"INJECTION": query}
             return {"LEGIT": query}
 
-    @component
-    class FakeEmbedder:
-        @component.output_types(embeddings=list[float])
-        def run(self, text: str) -> dict[str, list[float]]:
-            return {"embeddings": [1.0, 2.0, 3.0]}
-
     @component
     class FakeRanker:
         @component.output_types(documents=list[Document])
@@ -1728,7 +1723,7 @@ def run(self, query_embedding: list[float]) -> dict[str, list[Document]]:
             return {"documents": [doc2]}
 
     pipeline.add_component(name="router", instance=FakeRouter())
-    pipeline.add_component(name="text_embedder", instance=FakeEmbedder())
+    pipeline.add_component(name="text_embedder", instance=MockTextEmbedder(embedding=[1.0, 2.0, 3.0]))
     pipeline.add_component(name="retriever", instance=FakeEmbeddingRetriever())
     pipeline.add_component(name="emptyretriever", instance=FakeRetriever())
     pipeline.add_component(name="joinerfinal", instance=DocumentJoiner())
@@ -1752,7 +1747,12 @@ def run(self, query_embedding: list[float]) -> dict[str, list[Document]]:
         [
             PipelineRunData(
                 inputs={"router": {"query": "I'm a legit question"}},
-                expected_outputs={"joinerfinal": {"documents": [doc1, doc2]}},
+                expected_outputs={
+                    "text_embedder": {
+                        "meta": {"model": "mock-model", "usage": {"prompt_tokens": 4, "total_tokens": 4}}
+                    },
+                    "joinerfinal": {"documents": [doc1, doc2]},
+                },
                 expected_component_calls={
                     ("router", 1): {"query": "I'm a legit question"},
                     ("text_embedder", 1): {"text": "I'm a legit question"},

test/core/pipeline/test_pipeline_crash_regular_pipeline_snapshot_is_raised.py

@@ -2,11 +2,11 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
-import numpy as np
 import pytest
 
 from haystack import Document, Pipeline
 from haystack.components.builders import ChatPromptBuilder
+from haystack.components.embedders import MockTextEmbedder
 from haystack.components.joiners import DocumentJoiner
 from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
 from haystack.core.component import component
@@ -31,14 +31,6 @@ def run(self, query_embedding: list[float]) -> dict[str, list[Document]]:
         return 42  # type: ignore[return-value]
 
 
-@component
-class MockTextEmbedder:
-    @component.output_types(embedding=list[float])
-    def run(self, text: str) -> dict[str, list[float]]:
-        embedding = np.ones(384).tolist()  # Mock embedding of size 384
-        return {"embedding": embedding}
-
-
 class TestPipelineOutputsRaisedInException:
     def test_hybrid_rag_pipeline_crash_on_embedding_retriever(self):
         document_store = setup_document_store()