diff --git a/.github/workflows/components_instructor_embedders.yml b/.github/workflows/components_instructor_embedders.yml
index 710776d12..0aa0bb30d 100644
--- a/.github/workflows/components_instructor_embedders.yml
+++ b/.github/workflows/components_instructor_embedders.yml
@@ -34,6 +34,10 @@ jobs:
       run: |
         pip install -e .[dev]
 
-    - name: Run tests
+    - name: Run unit tests
       run: |
-        pytest
+        pytest -v -m unit
+
+    - name: Run integration tests
+      run: |
+        pytest -v -m integration   
diff --git a/components/instructor-embedders/instructor_embedders/embedding_backend/__init__.py b/components/instructor-embedders/instructor_embedders/embedding_backend/__init__.py
new file mode 100644
index 000000000..e873bc332
--- /dev/null
+++ b/components/instructor-embedders/instructor_embedders/embedding_backend/__init__.py
@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
diff --git a/components/instructor-embedders/instructor_embedders/embedding_backend/instructor_backend.py b/components/instructor-embedders/instructor_embedders/embedding_backend/instructor_backend.py
new file mode 100644
index 000000000..c3ff3a79b
--- /dev/null
+++ b/components/instructor-embedders/instructor_embedders/embedding_backend/instructor_backend.py
@@ -0,0 +1,45 @@
+from typing import ClassVar, Dict, List, Optional, Union
+
+from haystack.preview.lazy_imports import LazyImport
+
+with LazyImport(message="Run 'pip install InstructorEmbedding'") as instructor_embeddings_import:
+    from InstructorEmbedding import INSTRUCTOR
+
+
+class _InstructorEmbeddingBackendFactory:
+    """
+    Factory class to create instances of INSTRUCTOR embedding backends.
+    """
+
+    _instances: ClassVar[Dict[str, "_InstructorEmbeddingBackend"]] = {}
+
+    @staticmethod
+    def get_embedding_backend(
+        model_name_or_path: str, device: Optional[str] = None, use_auth_token: Union[bool, str, None] = None
+    ):
+        embedding_backend_id = f"{model_name_or_path}{device}{use_auth_token}"
+
+        if embedding_backend_id in _InstructorEmbeddingBackendFactory._instances:
+            return _InstructorEmbeddingBackendFactory._instances[embedding_backend_id]
+
+        embedding_backend = _InstructorEmbeddingBackend(
+            model_name_or_path=model_name_or_path, device=device, use_auth_token=use_auth_token
+        )
+        _InstructorEmbeddingBackendFactory._instances[embedding_backend_id] = embedding_backend
+        return embedding_backend
+
+
+class _InstructorEmbeddingBackend:
+    """
+    Class to manage INSTRUCTOR embeddings.
+    """
+
+    def __init__(
+        self, model_name_or_path: str, device: Optional[str] = None, use_auth_token: Union[bool, str, None] = None
+    ):
+        instructor_embeddings_import.check()
+        self.model = INSTRUCTOR(model_name_or_path=model_name_or_path, device=device, use_auth_token=use_auth_token)
+
+    def embed(self, data: List[List[str]], **kwargs) -> List[List[float]]:
+        embeddings = self.model.encode(data, **kwargs).tolist()
+        return embeddings
diff --git a/components/instructor-embedders/instructor_embedders/instructor_document_embedder.py b/components/instructor-embedders/instructor_embedders/instructor_document_embedder.py
new file mode 100644
index 000000000..7fd369cd2
--- /dev/null
+++ b/components/instructor-embedders/instructor_embedders/instructor_document_embedder.py
@@ -0,0 +1,136 @@
+from typing import Any, Dict, List, Optional, Union
+
+from haystack.preview import Document, component, default_from_dict, default_to_dict
+
+from instructor_embedders.embedding_backend.instructor_backend import _InstructorEmbeddingBackendFactory
+
+
+@component
+class InstructorDocumentEmbedder:
+    """
+    A component for computing Document embeddings using INSTRUCTOR embedding models.
+    The embedding of each Document is stored in the `embedding` field of the Document.
+    """
+
+    def __init__(
+        self,
+        model_name_or_path: str = "hkunlp/instructor-base",
+        device: Optional[str] = None,
+        use_auth_token: Union[bool, str, None] = None,
+        instruction: str = "Represent the document",
+        batch_size: int = 32,
+        progress_bar: bool = True,
+        normalize_embeddings: bool = False,
+        metadata_fields_to_embed: Optional[List[str]] = None,
+        embedding_separator: str = "\n",
+    ):
+        """
+        Create an InstructorDocumentEmbedder component.
+
+        :param model_name_or_path: Local path or name of the model in Hugging Face's model hub,
+            such as ``'hkunlp/instructor-base'``.
+        :param device: Device (like 'cuda' / 'cpu') that should be used for computation.
+            If None, checks if a GPU can be used.
+        :param use_auth_token: An API token used to download private models from Hugging Face.
+            If this parameter is set to `True`, then the token generated when running
+            `transformers-cli login` (stored in ~/.huggingface) will be used.
+        :param instruction: The instruction string to be used while computing domain-specific embeddings.
+            The instruction follows the unified template of the form:
+            "Represent the 'domain' 'text_type' for 'task_objective'", where:
+            - "domain" is optional, and it specifies the domain of the text, e.g., science, finance, medicine, etc.
+            - "text_type" is required, and it specifies the encoding unit, e.g., sentence, document, paragraph, etc.
+            - "task_objective" is optional, and it specifies the objective of embedding, e.g., retrieve a document,
+             classify the sentence, etc.
+            Check some examples of instructions here: https://github.com/xlang-ai/instructor-embedding#use-cases.
+        :param batch_size: Number of strings to encode at once.
+        :param progress_bar: If true, displays progress bar during embedding.
+        :param normalize_embeddings: If set to true, returned vectors will have the length of 1.
+        :param metadata_fields_to_embed: List of meta fields that should be embedded along with the Document content.
+        :param embedding_separator: Separator used to concatenate the meta fields to the Document content.
+        """
+
+        self.model_name_or_path = model_name_or_path
+        # TODO: remove device parameter and use Haystack's device management once migrated
+        self.device = device or "cpu"
+        self.use_auth_token = use_auth_token
+        self.instruction = instruction
+        self.batch_size = batch_size
+        self.progress_bar = progress_bar
+        self.normalize_embeddings = normalize_embeddings
+        self.metadata_fields_to_embed = metadata_fields_to_embed or []
+        self.embedding_separator = embedding_separator
+
+    def to_dict(self) -> Dict[str, Any]:
+        """
+        Serialize this component to a dictionary.
+        """
+        return default_to_dict(
+            self,
+            model_name_or_path=self.model_name_or_path,
+            device=self.device,
+            use_auth_token=self.use_auth_token,
+            instruction=self.instruction,
+            batch_size=self.batch_size,
+            progress_bar=self.progress_bar,
+            normalize_embeddings=self.normalize_embeddings,
+            metadata_fields_to_embed=self.metadata_fields_to_embed,
+            embedding_separator=self.embedding_separator,
+        )
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "InstructorDocumentEmbedder":
+        """
+        Deserialize this component from a dictionary.
+        """
+        return default_from_dict(cls, data)
+
+    def warm_up(self):
+        """
+        Load the embedding backend.
+        """
+        if not hasattr(self, "embedding_backend"):
+            self.embedding_backend = _InstructorEmbeddingBackendFactory.get_embedding_backend(
+                model_name_or_path=self.model_name_or_path, device=self.device, use_auth_token=self.use_auth_token
+            )
+
+    @component.output_types(documents=List[Document])
+    def run(self, documents: List[Document]):
+        """
+        Embed a list of Documents.
+        The embedding of each Document is stored in the `embedding` field of the Document.
+        """
+        if not isinstance(documents, list) or documents and not isinstance(documents[0], Document):
+            msg = ("InstructorDocumentEmbedder expects a list of Documents as input. "
+                   "In case you want to embed a list of strings, please use the InstructorTextEmbedder.")
+            raise TypeError(msg)
+        if not hasattr(self, "embedding_backend"):
+            msg = "The embedding model has not been loaded. Please call warm_up() before running."
+            raise RuntimeError(msg)
+
+        # TODO: once non textual Documents are properly supported, we should also prepare them for embedding here
+
+        texts_to_embed = []
+        for doc in documents:
+            meta_values_to_embed = [
+                str(doc.metadata[key])
+                for key in self.metadata_fields_to_embed
+                if key in doc.metadata and doc.metadata[key] is not None
+            ]
+            text_to_embed = [self.instruction, self.embedding_separator.join([*meta_values_to_embed, doc.text or ""])]
+            texts_to_embed.append(text_to_embed)
+
+        embeddings = self.embedding_backend.embed(
+            texts_to_embed,
+            batch_size=self.batch_size,
+            show_progress_bar=self.progress_bar,
+            normalize_embeddings=self.normalize_embeddings,
+        )
+
+        documents_with_embeddings = []
+        for doc, emb in zip(documents, embeddings):
+            doc_as_dict = doc.to_dict()
+            doc_as_dict["embedding"] = emb
+            del doc_as_dict["id"]
+            documents_with_embeddings.append(Document.from_dict(doc_as_dict))
+
+        return {"documents": documents_with_embeddings}
diff --git a/components/instructor-embedders/instructor_embedders/instructor_text_embedder.py b/components/instructor-embedders/instructor_embedders/instructor_text_embedder.py
new file mode 100644
index 000000000..dd0ec48c3
--- /dev/null
+++ b/components/instructor-embedders/instructor_embedders/instructor_text_embedder.py
@@ -0,0 +1,105 @@
+from typing import Any, Dict, List, Optional, Union
+
+from haystack.preview import component, default_from_dict, default_to_dict
+
+from instructor_embedders.embedding_backend.instructor_backend import _InstructorEmbeddingBackendFactory
+
+
+@component
+class InstructorTextEmbedder:
+    """
+    A component for embedding strings using Sentence Transformers models.
+    """
+
+    def __init__(
+        self,
+        model_name_or_path: str = "hkunlp/instructor-base",
+        device: Optional[str] = None,
+        use_auth_token: Union[bool, str, None] = None,
+        instruction: str = "Represent the sentence",
+        batch_size: int = 32,
+        progress_bar: bool = True,
+        normalize_embeddings: bool = False,
+    ):
+        """
+        Create an InstructorTextEmbedder component.
+
+        :param model_name_or_path: Local path or name of the model in Hugging Face's model hub,
+            such as ``'hkunlp/instructor-base'``.
+        :param device: Device (like 'cuda' / 'cpu') that should be used for computation.
+            If None, checks if a GPU can be used.
+        :param use_auth_token: The API token used to download private models from Hugging Face.
+                        If this parameter is set to `True`, then the token generated when running
+                        `transformers-cli login` (stored in ~/.huggingface) will be used.
+        :param instruction: The instruction string to be used while computing domain-specific embeddings.
+            The instruction follows the unified template of the form:
+            "Represent the 'domain' 'text_type' for 'task_objective'", where:
+            - "domain" is optional, and it specifies the domain of the text, e.g., science, finance, medicine, etc.
+            - "text_type" is required, and it specifies the encoding unit, e.g., sentence, document, paragraph, etc.
+            - "task_objective" is optional, and it specifies the objective of embedding, e.g., retrieve a document,
+            classify the sentence, etc.
+            Check some examples of instructions here: https://github.com/xlang-ai/instructor-embedding#use-cases.
+        :param batch_size: Number of strings to encode at once.
+        :param progress_bar: If true, displays progress bar during embedding.
+        :param normalize_embeddings: If set to true, returned vectors will have the length of 1.
+        """
+
+        self.model_name_or_path = model_name_or_path
+        # TODO: remove device parameter and use Haystack's device management once migrated
+        self.device = device or "cpu"
+        self.use_auth_token = use_auth_token
+        self.instruction = instruction
+        self.batch_size = batch_size
+        self.progress_bar = progress_bar
+        self.normalize_embeddings = normalize_embeddings
+
+    def to_dict(self) -> Dict[str, Any]:
+        """
+        Serialize this component to a dictionary.
+        """
+        return default_to_dict(
+            self,
+            model_name_or_path=self.model_name_or_path,
+            device=self.device,
+            use_auth_token=self.use_auth_token,
+            instruction=self.instruction,
+            batch_size=self.batch_size,
+            progress_bar=self.progress_bar,
+            normalize_embeddings=self.normalize_embeddings,
+        )
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "InstructorTextEmbedder":
+        """
+        Deserialize this component from a dictionary.
+        """
+        return default_from_dict(cls, data)
+
+    def warm_up(self):
+        """
+        Load the embedding backend.
+        """
+        if not hasattr(self, "embedding_backend"):
+            self.embedding_backend = _InstructorEmbeddingBackendFactory.get_embedding_backend(
+                model_name_or_path=self.model_name_or_path, device=self.device, use_auth_token=self.use_auth_token
+            )
+
+    @component.output_types(embedding=List[float])
+    def run(self, text: str):
+        """Embed a string."""
+        if not isinstance(text, str):
+            msg = ("InstructorTextEmbedder expects a string as input. "
+                   "In case you want to embed a list of Documents, please use the InstructorDocumentEmbedder.")
+            raise TypeError(msg)
+        if not hasattr(self, "embedding_backend"):
+            msg = "The embedding model has not been loaded. Please call warm_up() before running."
+            raise RuntimeError(msg)
+
+        text_to_embed = [self.instruction, text]
+        embedding = self.embedding_backend.embed(
+            [text_to_embed],
+            batch_size=self.batch_size,
+            show_progress_bar=self.progress_bar,
+            normalize_embeddings=self.normalize_embeddings,
+        )[0]
+        return {"embedding": embedding}
diff --git a/components/instructor-embedders/pyproject.toml b/components/instructor-embedders/pyproject.toml
index bea7cc53a..efe6cca9e 100644
--- a/components/instructor-embedders/pyproject.toml
+++ b/components/instructor-embedders/pyproject.toml
@@ -87,7 +87,6 @@ select = [
   "E",
   "EM",
   "F",
-  "FBT",
   "I",
   "ICN",
   "ISC",
diff --git a/components/instructor-embedders/tests/test_instructor_backend.py b/components/instructor-embedders/tests/test_instructor_backend.py
new file mode 100644
index 000000000..334e02f6f
--- /dev/null
+++ b/components/instructor-embedders/tests/test_instructor_backend.py
@@ -0,0 +1,44 @@
+from unittest.mock import patch
+
+import pytest
+
+from instructor_embedders.embedding_backend.instructor_backend import _InstructorEmbeddingBackendFactory
+
+
+@pytest.mark.unit
+@patch("instructor_embedders.embedding_backend.instructor_backend.INSTRUCTOR")
+def test_factory_behavior(mock_instructor): # noqa: ARG001
+    embedding_backend = _InstructorEmbeddingBackendFactory.get_embedding_backend(
+        model_name_or_path="hkunlp/instructor-large", device="cpu"
+    )
+    same_embedding_backend = _InstructorEmbeddingBackendFactory.get_embedding_backend("hkunlp/instructor-large", "cpu")
+    another_embedding_backend = _InstructorEmbeddingBackendFactory.get_embedding_backend(
+        model_name_or_path="hkunlp/instructor-base", device="cpu"
+    )
+
+    assert same_embedding_backend is embedding_backend
+    assert another_embedding_backend is not embedding_backend
+
+
+@pytest.mark.unit
+@patch("instructor_embedders.embedding_backend.instructor_backend.INSTRUCTOR")
+def test_model_initialization(mock_instructor):
+    _InstructorEmbeddingBackendFactory.get_embedding_backend(
+        model_name_or_path="hkunlp/instructor-base", device="cpu", use_auth_token="huggingface_auth_token"
+    )
+    mock_instructor.assert_called_once_with(
+        model_name_or_path="hkunlp/instructor-base", device="cpu", use_auth_token="huggingface_auth_token"
+    )
+
+
+@pytest.mark.unit
+@patch("instructor_embedders.embedding_backend.instructor_backend.INSTRUCTOR")
+def test_embedding_function_with_kwargs(mock_instructor):   # noqa: ARG001
+    embedding_backend = _InstructorEmbeddingBackendFactory.get_embedding_backend(
+        model_name_or_path="hkunlp/instructor-base"
+    )
+
+    data = [["instruction", "sentence1"], ["instruction", "sentence2"]]
+    embedding_backend.embed(data=data, normalize_embeddings=True)
+
+    embedding_backend.model.encode.assert_called_once_with(data, normalize_embeddings=True)
diff --git a/components/instructor-embedders/tests/test_instructor_document_embedder.py b/components/instructor-embedders/tests/test_instructor_document_embedder.py
new file mode 100644
index 000000000..faa9d715b
--- /dev/null
+++ b/components/instructor-embedders/tests/test_instructor_document_embedder.py
@@ -0,0 +1,275 @@
+from unittest.mock import MagicMock, patch
+
+import numpy as np
+import pytest
+from haystack.preview import Document
+
+from instructor_embedders.instructor_document_embedder import InstructorDocumentEmbedder
+
+
+class TestInstructorDocumentEmbedder:
+    @pytest.mark.unit
+    def test_init_default(self):
+        """
+        Test default initialization parameters for InstructorDocumentEmbedder.
+        """
+        embedder = InstructorDocumentEmbedder(model_name_or_path="hkunlp/instructor-base")
+        assert embedder.model_name_or_path == "hkunlp/instructor-base"
+        assert embedder.device == "cpu"
+        assert embedder.use_auth_token is None
+        assert embedder.instruction == "Represent the document"
+        assert embedder.batch_size == 32
+        assert embedder.progress_bar is True
+        assert embedder.normalize_embeddings is False
+        assert embedder.metadata_fields_to_embed == []
+        assert embedder.embedding_separator == "\n"
+
+    @pytest.mark.unit
+    def test_init_with_parameters(self):
+        """
+        Test custom initialization parameters for InstructorDocumentEmbedder.
+        """
+        embedder = InstructorDocumentEmbedder(
+            model_name_or_path="hkunlp/instructor-base",
+            device="cuda",
+            use_auth_token=True,
+            instruction="Represent the 'domain' 'text_type' for 'task_objective'",
+            batch_size=64,
+            progress_bar=False,
+            normalize_embeddings=True,
+            metadata_fields_to_embed=["test_field"],
+            embedding_separator=" | ",
+        )
+        assert embedder.model_name_or_path == "hkunlp/instructor-base"
+        assert embedder.device == "cuda"
+        assert embedder.use_auth_token is True
+        assert embedder.instruction == "Represent the 'domain' 'text_type' for 'task_objective'"
+        assert embedder.batch_size == 64
+        assert embedder.progress_bar is False
+        assert embedder.normalize_embeddings is True
+        assert embedder.metadata_fields_to_embed == ["test_field"]
+        assert embedder.embedding_separator == " | "
+
+    @pytest.mark.unit
+    def test_to_dict(self):
+        """
+        Test serialization of InstructorDocumentEmbedder to a dictionary, using default initialization parameters.
+        """
+        embedder = InstructorDocumentEmbedder(model_name_or_path="hkunlp/instructor-base")
+        embedder_dict = embedder.to_dict()
+        assert embedder_dict == {
+            "type": "InstructorDocumentEmbedder",
+            "init_parameters": {
+                "model_name_or_path": "hkunlp/instructor-base",
+                "device": "cpu",
+                "use_auth_token": None,
+                "instruction": "Represent the document",
+                "batch_size": 32,
+                "progress_bar": True,
+                "normalize_embeddings": False,
+                "embedding_separator": "\n",
+                "metadata_fields_to_embed": [],
+            },
+        }
+
+    @pytest.mark.unit
+    def test_to_dict_with_custom_init_parameters(self):
+        """
+        Test serialization of InstructorDocumentEmbedder to a dictionary, using custom initialization parameters.
+        """
+        embedder = InstructorDocumentEmbedder(
+            model_name_or_path="hkunlp/instructor-base",
+            device="cuda",
+            use_auth_token=True,
+            instruction="Represent the financial document for retrieval",
+            batch_size=64,
+            progress_bar=False,
+            normalize_embeddings=True,
+            metadata_fields_to_embed=["test_field"],
+            embedding_separator=" | ",
+        )
+        embedder_dict = embedder.to_dict()
+        assert embedder_dict == {
+            "type": "InstructorDocumentEmbedder",
+            "init_parameters": {
+                "model_name_or_path": "hkunlp/instructor-base",
+                "device": "cuda",
+                "use_auth_token": True,
+                "instruction": "Represent the financial document for retrieval",
+                "batch_size": 64,
+                "progress_bar": False,
+                "normalize_embeddings": True,
+                "metadata_fields_to_embed": ["test_field"],
+                "embedding_separator": " | ",
+            },
+        }
+
+    @pytest.mark.unit
+    def test_from_dict(self):
+        """
+        Test deserialization of InstructorDocumentEmbedder from a dictionary, using default initialization parameters.
+        """
+        embedder_dict = {
+            "type": "InstructorDocumentEmbedder",
+            "init_parameters": {
+                "model_name_or_path": "hkunlp/instructor-base",
+                "device": "cpu",
+                "use_auth_token": None,
+                "instruction": "Represent the 'domain' 'text_type' for 'task_objective'",
+                "batch_size": 32,
+                "progress_bar": True,
+                "normalize_embeddings": False,
+                "metadata_fields_to_embed": [],
+                "embedding_separator": "\n",
+            },
+        }
+        embedder = InstructorDocumentEmbedder.from_dict(embedder_dict)
+        assert embedder.model_name_or_path == "hkunlp/instructor-base"
+        assert embedder.device == "cpu"
+        assert embedder.use_auth_token is None
+        assert embedder.instruction == "Represent the 'domain' 'text_type' for 'task_objective'"
+        assert embedder.batch_size == 32
+        assert embedder.progress_bar is True
+        assert embedder.normalize_embeddings is False
+        assert embedder.metadata_fields_to_embed == []
+        assert embedder.embedding_separator == "\n"
+
+    @pytest.mark.unit
+    def test_from_dict_with_custom_init_parameters(self):
+        """
+        Test deserialization of InstructorDocumentEmbedder from a dictionary, using custom initialization parameters.
+        """
+        embedder_dict = {
+            "type": "InstructorDocumentEmbedder",
+            "init_parameters": {
+                "model_name_or_path": "hkunlp/instructor-base",
+                "device": "cuda",
+                "use_auth_token": True,
+                "instruction": "Represent the financial document for retrieval",
+                "batch_size": 64,
+                "progress_bar": False,
+                "normalize_embeddings": True,
+                "metadata_fields_to_embed": ["test_field"],
+                "embedding_separator": " | ",
+            },
+        }
+        embedder = InstructorDocumentEmbedder.from_dict(embedder_dict)
+        assert embedder.model_name_or_path == "hkunlp/instructor-base"
+        assert embedder.device == "cuda"
+        assert embedder.use_auth_token is True
+        assert embedder.instruction == "Represent the financial document for retrieval"
+        assert embedder.batch_size == 64
+        assert embedder.progress_bar is False
+        assert embedder.normalize_embeddings is True
+        assert embedder.metadata_fields_to_embed == ["test_field"]
+        assert embedder.embedding_separator == " | "
+
+    @pytest.mark.unit
+    @patch("instructor_embedders.instructor_document_embedder._InstructorEmbeddingBackendFactory")
+    def test_warmup(self, mocked_factory):
+        """
+        Test for checking embedder instances after warm-up.
+        """
+        embedder = InstructorDocumentEmbedder(model_name_or_path="hkunlp/instructor-base")
+        mocked_factory.get_embedding_backend.assert_not_called()
+        embedder.warm_up()
+        mocked_factory.get_embedding_backend.assert_called_once_with(
+            model_name_or_path="hkunlp/instructor-base", device="cpu", use_auth_token=None
+        )
+
+    @pytest.mark.unit
+    @patch("instructor_embedders.instructor_document_embedder._InstructorEmbeddingBackendFactory")
+    def test_warmup_does_not_reload(self, mocked_factory):
+        """
+        Test for checking backend instances after multiple warm-ups.
+        """
+        embedder = InstructorDocumentEmbedder(model_name_or_path="hkunlp/instructor-base")
+        mocked_factory.get_embedding_backend.assert_not_called()
+        embedder.warm_up()
+        embedder.warm_up()
+        mocked_factory.get_embedding_backend.assert_called_once()
+
+    @pytest.mark.unit
+    def test_embed(self):
+        """
+        Test for checking output dimensions and embedding dimensions.
+        """
+        embedder = InstructorDocumentEmbedder(model_name_or_path="hkunlp/instructor-large")
+        embedder.embedding_backend = MagicMock()
+        embedder.embedding_backend.embed = lambda x, **kwargs: np.random.rand(len(x), 16).tolist()  # noqa: ARG005
+
+        documents = [Document(text=f"Sample-document text {i}") for i in range(5)]
+
+        result = embedder.run(documents=documents)
+
+        assert isinstance(result["documents"], list)
+        assert len(result["documents"]) == len(documents)
+        for doc in result["documents"]:
+            assert isinstance(doc, Document)
+            assert isinstance(doc.embedding, list)
+            assert isinstance(doc.embedding[0], float)
+
+    @pytest.mark.unit
+    def test_embed_incorrect_input_format(self):
+        """
+        Test for checking incorrect input format when creating embedding.
+        """
+        embedder = InstructorDocumentEmbedder(model_name_or_path="hkunlp/instructor-base")
+
+        string_input = "text"
+        list_integers_input = [1, 2, 3]
+
+        with pytest.raises(TypeError, match="InstructorDocumentEmbedder expects a list of Documents as input."):
+            embedder.run(documents=string_input)
+
+        with pytest.raises(TypeError, match="InstructorDocumentEmbedder expects a list of Documents as input."):
+            embedder.run(documents=list_integers_input)
+
+    @pytest.mark.unit
+    def test_embed_metadata(self):
+        """
+        Test for checking output dimensions and embedding dimensions for documents
+        with a custom instruction and metadata.
+        """
+        embedder = InstructorDocumentEmbedder(
+            model_name_or_path="model",
+            instruction="Represent the financial document for retrieval",
+            metadata_fields_to_embed=["meta_field"],
+            embedding_separator="\n",
+        )
+        embedder.embedding_backend = MagicMock()
+
+        documents = [
+            Document(text=f"document-number {i}", metadata={"meta_field": f"meta_value {i}"}) for i in range(5)
+        ]
+
+        embedder.run(documents=documents)
+
+        embedder.embedding_backend.embed.assert_called_once_with(
+            [
+                ["Represent the financial document for retrieval", "meta_value 0\ndocument-number 0"],
+                ["Represent the financial document for retrieval", "meta_value 1\ndocument-number 1"],
+                ["Represent the financial document for retrieval", "meta_value 2\ndocument-number 2"],
+                ["Represent the financial document for retrieval", "meta_value 3\ndocument-number 3"],
+                ["Represent the financial document for retrieval", "meta_value 4\ndocument-number 4"],
+            ],
+            batch_size=32,
+            show_progress_bar=True,
+            normalize_embeddings=False,
+        )
+
+    @pytest.mark.integration
+    def test_run(self):
+        embedder = InstructorDocumentEmbedder(model_name_or_path="hkunlp/instructor-base",
+                                          device="cpu",
+                                          instruction="Represent the Science document for retrieval")
+        embedder.warm_up()
+
+        doc = Document(text="Parton energy loss in QCD matter")
+
+        result = embedder.run(documents=[doc])
+        embedding = result["documents"][0].embedding
+
+        assert isinstance(embedding, list)
+        assert len(embedding) == 768
+        assert all(isinstance(emb, float) for emb in embedding)
diff --git a/components/instructor-embedders/tests/test_instructor_embedders.py b/components/instructor-embedders/tests/test_instructor_embedders.py
index 129c33f3c..1abbe3b32 100644
--- a/components/instructor-embedders/tests/test_instructor_embedders.py
+++ b/components/instructor-embedders/tests/test_instructor_embedders.py
@@ -2,5 +2,6 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
+
 def test_instructor_embedders():
     assert True
diff --git a/components/instructor-embedders/tests/test_instructor_text_embedder.py b/components/instructor-embedders/tests/test_instructor_text_embedder.py
new file mode 100644
index 000000000..e3afe91e8
--- /dev/null
+++ b/components/instructor-embedders/tests/test_instructor_text_embedder.py
@@ -0,0 +1,215 @@
+from unittest.mock import MagicMock, patch
+
+import numpy as np
+import pytest
+
+from instructor_embedders.instructor_text_embedder import InstructorTextEmbedder
+
+
+class TestInstructorTextEmbedder:
+    @pytest.mark.unit
+    def test_init_default(self):
+        """
+        Test default initialization parameters for InstructorTextEmbedder.
+        """
+        embedder = InstructorTextEmbedder(model_name_or_path="hkunlp/instructor-base")
+        assert embedder.model_name_or_path == "hkunlp/instructor-base"
+        assert embedder.device == "cpu"
+        assert embedder.use_auth_token is None
+        assert embedder.instruction == "Represent the sentence"
+        assert embedder.batch_size == 32
+        assert embedder.progress_bar is True
+        assert embedder.normalize_embeddings is False
+
+    @pytest.mark.unit
+    def test_init_with_parameters(self):
+        """
+        Test custom initialization parameters for InstructorTextEmbedder.
+        """
+        embedder = InstructorTextEmbedder(
+            model_name_or_path="hkunlp/instructor-base",
+            device="cuda",
+            use_auth_token=True,
+            instruction="Represent the 'domain' 'text_type' for 'task_objective'",
+            batch_size=64,
+            progress_bar=False,
+            normalize_embeddings=True,
+        )
+        assert embedder.model_name_or_path == "hkunlp/instructor-base"
+        assert embedder.device == "cuda"
+        assert embedder.use_auth_token is True
+        assert embedder.instruction == "Represent the 'domain' 'text_type' for 'task_objective'"
+        assert embedder.batch_size == 64
+        assert embedder.progress_bar is False
+        assert embedder.normalize_embeddings is True
+
+    @pytest.mark.unit
+    def test_to_dict(self):
+        """
+        Test serialization of InstructorTextEmbedder to a dictionary, using default initialization parameters.
+        """
+        embedder = InstructorTextEmbedder(model_name_or_path="hkunlp/instructor-base")
+        embedder_dict = embedder.to_dict()
+        assert embedder_dict == {
+            "type": "InstructorTextEmbedder",
+            "init_parameters": {
+                "model_name_or_path": "hkunlp/instructor-base",
+                "device": "cpu",
+                "use_auth_token": None,
+                "instruction": "Represent the sentence",
+                "batch_size": 32,
+                "progress_bar": True,
+                "normalize_embeddings": False,
+            },
+        }
+
+    @pytest.mark.unit
+    def test_to_dict_with_custom_init_parameters(self):
+        """
+        Test serialization of InstructorTextEmbedder to a dictionary, using custom initialization parameters.
+        """
+        embedder = InstructorTextEmbedder(
+            model_name_or_path="hkunlp/instructor-base",
+            device="cuda",
+            use_auth_token=True,
+            instruction="Represent the financial document for retrieval",
+            batch_size=64,
+            progress_bar=False,
+            normalize_embeddings=True,
+        )
+        embedder_dict = embedder.to_dict()
+        assert embedder_dict == {
+            "type": "InstructorTextEmbedder",
+            "init_parameters": {
+                "model_name_or_path": "hkunlp/instructor-base",
+                "device": "cuda",
+                "use_auth_token": True,
+                "instruction": "Represent the financial document for retrieval",
+                "batch_size": 64,
+                "progress_bar": False,
+                "normalize_embeddings": True,
+            },
+        }
+
+    @pytest.mark.unit
+    def test_from_dict(self):
+        """
+        Test deserialization of InstructorTextEmbedder from a dictionary, using default initialization parameters.
+        """
+        embedder_dict = {
+            "type": "InstructorTextEmbedder",
+            "init_parameters": {
+                "model_name_or_path": "hkunlp/instructor-base",
+                "device": "cpu",
+                "use_auth_token": None,
+                "instruction": "Represent the 'domain' 'text_type' for 'task_objective'",
+                "batch_size": 32,
+                "progress_bar": True,
+                "normalize_embeddings": False,
+            },
+        }
+        embedder = InstructorTextEmbedder.from_dict(embedder_dict)
+        assert embedder.model_name_or_path == "hkunlp/instructor-base"
+        assert embedder.device == "cpu"
+        assert embedder.use_auth_token is None
+        assert embedder.instruction == "Represent the 'domain' 'text_type' for 'task_objective'"
+        assert embedder.batch_size == 32
+        assert embedder.progress_bar is True
+        assert embedder.normalize_embeddings is False
+
+    @pytest.mark.unit
+    def test_from_dict_with_custom_init_parameters(self):
+        """
+        Test deserialization of InstructorTextEmbedder from a dictionary, using custom initialization parameters.
+        """
+        embedder_dict = {
+            "type": "InstructorTextEmbedder",
+            "init_parameters": {
+                "model_name_or_path": "hkunlp/instructor-base",
+                "device": "cuda",
+                "use_auth_token": True,
+                "instruction": "Represent the financial document for retrieval",
+                "batch_size": 64,
+                "progress_bar": False,
+                "normalize_embeddings": True,
+            },
+        }
+        embedder = InstructorTextEmbedder.from_dict(embedder_dict)
+        assert embedder.model_name_or_path == "hkunlp/instructor-base"
+        assert embedder.device == "cuda"
+        assert embedder.use_auth_token is True
+        assert embedder.instruction == "Represent the financial document for retrieval"
+        assert embedder.batch_size == 64
+        assert embedder.progress_bar is False
+        assert embedder.normalize_embeddings is True
+
+    @pytest.mark.unit
+    @patch("instructor_embedders.instructor_text_embedder._InstructorEmbeddingBackendFactory")
+    def test_warmup(self, mocked_factory):
+        """
+        Test for checking embedder instances after warm-up.
+        """
+        embedder = InstructorTextEmbedder(model_name_or_path="hkunlp/instructor-base")
+        mocked_factory.get_embedding_backend.assert_not_called()
+        embedder.warm_up()
+        mocked_factory.get_embedding_backend.assert_called_once_with(
+            model_name_or_path="hkunlp/instructor-base", device="cpu", use_auth_token=None
+        )
+
+    @pytest.mark.unit
+    @patch("instructor_embedders.instructor_text_embedder._InstructorEmbeddingBackendFactory")
+    def test_warmup_does_not_reload(self, mocked_factory):
+        """
+        Test for checking backend instances after multiple warm-ups.
+        """
+        embedder = InstructorTextEmbedder(model_name_or_path="hkunlp/instructor-base")
+        mocked_factory.get_embedding_backend.assert_not_called()
+        embedder.warm_up()
+        embedder.warm_up()
+        mocked_factory.get_embedding_backend.assert_called_once()
+
+    @pytest.mark.unit
+    def test_embed(self):
+        """
+        Test for checking output dimensions and embedding dimensions.
+        """
+        embedder = InstructorTextEmbedder(model_name_or_path="hkunlp/instructor-large")
+        embedder.embedding_backend = MagicMock()
+        embedder.embedding_backend.embed = lambda x, **kwargs: np.random.rand(len(x), 16).tolist()  # noqa: ARG005
+
+        text = "Good text to embed"
+
+        result = embedder.run(text=text)
+        embedding = result["embedding"]
+
+        assert isinstance(embedding, list)
+        assert all(isinstance(emb, float) for emb in embedding)
+
+    @pytest.mark.unit
+    def test_run_wrong_incorrect_format(self):
+        """
+        Test for checking incorrect input format when creating embedding.
+        """
+        embedder = InstructorTextEmbedder(model_name_or_path="hkunlp/instructor-large")
+        embedder.embedding_backend = MagicMock()
+
+        list_integers_input = [1, 2, 3]
+
+        with pytest.raises(TypeError, match="InstructorTextEmbedder expects a string as input"):
+            embedder.run(text=list_integers_input)
+
+    @pytest.mark.integration
+    def test_run(self):
+        embedder = InstructorTextEmbedder(model_name_or_path="hkunlp/instructor-base",
+                                          device="cpu",
+                                          instruction="Represent the Science sentence for retrieval")
+        embedder.warm_up()
+
+        text = "Parton energy loss in QCD matter"
+
+        result = embedder.run(text=text)
+        embedding = result["embedding"]
+
+        assert isinstance(embedding, list)
+        assert len(embedding) == 768
+        assert all(isinstance(emb, float) for emb in embedding)