refactor!: remove from_dict overrides that only call default_from_dict from 14 components (#4059)

Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

Author: julian-risch

integrations/amazon_textract/src/haystack_integrations/components/converters/amazon_textract/converter.py

@@ -8,10 +8,10 @@
 import boto3
 from botocore.config import Config
 from botocore.exceptions import BotoCoreError, ClientError
-from haystack import Document, component, default_from_dict, default_to_dict, logging
+from haystack import Document, component, default_to_dict, logging
 from haystack.components.converters.utils import get_bytestream_from_source, normalize_metadata
 from haystack.dataclasses import ByteStream
-from haystack.utils import Secret, deserialize_secrets_inplace
+from haystack.utils import Secret
 
 from .errors import AmazonTextractConfigurationError
 
@@ -253,25 +253,3 @@ def to_dict(self) -> dict[str, Any]:
             store_full_path=self.store_full_path,
             boto3_config=self.boto3_config,
         )
-
-    @classmethod
-    def from_dict(cls, data: dict[str, Any]) -> "AmazonTextractConverter":
-        """
-        Deserializes the component from a dictionary.
-
-        :param data:
-            The dictionary to deserialize from.
-        :returns:
-            The deserialized component.
-        """
-        deserialize_secrets_inplace(
-            data["init_parameters"],
-            keys=[
-                "aws_access_key_id",
-                "aws_secret_access_key",
-                "aws_session_token",
-                "aws_region_name",
-                "aws_profile_name",
-            ],
-        )
-        return default_from_dict(cls, data)

integrations/amazon_textract/tests/test_amazon_textract_converter.py

@@ -8,6 +8,7 @@
 
 import pytest
 from botocore.exceptions import BotoCoreError, ClientError
+from haystack.core.serialization import component_from_dict
 from haystack.dataclasses import ByteStream
 from haystack.utils import Secret
 
@@ -116,28 +117,6 @@ def test_to_dict_default_params(self):
         assert data["init_parameters"]["store_full_path"] is False
         assert data["init_parameters"]["boto3_config"] is None
 
-    def test_from_dict(self):
-        expected_type = "haystack_integrations.components.converters.amazon_textract.converter.AmazonTextractConverter"
-        data = {
-            "type": expected_type,
-            "init_parameters": {
-                "aws_access_key_id": {"type": "env_var", "env_vars": ["AWS_ACCESS_KEY_ID"], "strict": False},
-                "aws_secret_access_key": {"type": "env_var", "env_vars": ["AWS_SECRET_ACCESS_KEY"], "strict": False},
-                "aws_session_token": {"type": "env_var", "env_vars": ["AWS_SESSION_TOKEN"], "strict": False},
-                "aws_region_name": {"type": "env_var", "env_vars": ["AWS_DEFAULT_REGION"], "strict": False},
-                "aws_profile_name": {"type": "env_var", "env_vars": ["AWS_PROFILE"], "strict": False},
-                "feature_types": ["TABLES", "FORMS"],
-                "store_full_path": False,
-                "boto3_config": None,
-            },
-        }
-
-        converter = AmazonTextractConverter.from_dict(data)
-
-        assert converter.feature_types == ["TABLES", "FORMS"]
-        assert converter.store_full_path is False
-        assert converter.boto3_config is None
-
     def test_from_dict_roundtrip(self):
         converter = AmazonTextractConverter(
             aws_access_key_id=Secret.from_env_var("AWS_ACCESS_KEY_ID", strict=False),
@@ -147,11 +126,16 @@ def test_from_dict_roundtrip(self):
         )
 
         data = converter.to_dict()
-        restored = AmazonTextractConverter.from_dict(data)
+        restored = component_from_dict(AmazonTextractConverter, data, name="restored")
 
         assert restored.feature_types == converter.feature_types
         assert restored.store_full_path == converter.store_full_path
         assert restored.boto3_config == converter.boto3_config
+        assert restored.aws_access_key_id == converter.aws_access_key_id
+        assert restored.aws_secret_access_key == converter.aws_secret_access_key
+        assert restored.aws_session_token == converter.aws_session_token
+        assert restored.aws_region_name == converter.aws_region_name
+        assert restored.aws_profile_name == converter.aws_profile_name
 
 
 class TestComponentLifecycle:

integrations/azure_form_recognizer/src/haystack_integrations/components/converters/azure_form_recognizer/converter.py

@@ -11,10 +11,10 @@
 import networkx as nx
 from azure.ai.formrecognizer import AnalyzeResult, DocumentAnalysisClient, DocumentLine, DocumentParagraph
 from azure.core.credentials import AzureKeyCredential
-from haystack import Document, component, default_from_dict, default_to_dict, logging
+from haystack import Document, component, default_to_dict, logging
 from haystack.components.converters.utils import get_bytestream_from_source, normalize_metadata
 from haystack.dataclasses import ByteStream
-from haystack.utils import Secret, deserialize_secrets_inplace
+from haystack.utils import Secret
 from pandas import DataFrame
 
 logger = logging.getLogger(__name__)
@@ -186,19 +186,6 @@ def to_dict(self) -> dict[str, Any]:
             store_full_path=self.store_full_path,
         )
 
-    @classmethod
-    def from_dict(cls, data: dict[str, Any]) -> "AzureOCRDocumentConverter":
-        """
-        Deserializes the component from a dictionary.
-
-        :param data:
-            The dictionary to deserialize from.
-        :returns:
-            The deserialized component.
-        """
-        deserialize_secrets_inplace(data["init_parameters"], keys=["api_key"])
-        return default_from_dict(cls, data)
-
     def _convert_tables_and_text(self, result: AnalyzeResult, meta: dict[str, Any] | None) -> list[Document]:
         """
         Converts the tables and text extracted by Azure's Document Intelligence service into Haystack Documents.

integrations/azure_form_recognizer/tests/test_azure_ocr_doc_converter.py

@@ -12,6 +12,7 @@
 
 import pytest
 from azure.ai.formrecognizer import AnalyzeResult
+from haystack.core.serialization import component_from_dict
 from haystack.dataclasses.byte_stream import ByteStream
 from haystack.utils import Secret
 
@@ -143,7 +144,7 @@ def test_from_dict(self):
                 "store_full_path": False,
             },
         }
-        component = AzureOCRDocumentConverter.from_dict(data)
+        component = component_from_dict(AzureOCRDocumentConverter, data, name="component")
         assert component.endpoint == "test_endpoint"
         assert component.model_id == "prebuilt-read"
         assert component.api_key == Secret.from_env_var("AZURE_AI_API_KEY")

integrations/google_genai/src/haystack_integrations/components/embedders/google_genai/document_embedder.py

@@ -7,8 +7,8 @@
 
 from google.genai import Client, types
 from google.genai.client import AsyncClient
-from haystack import Document, component, default_from_dict, default_to_dict, logging
-from haystack.utils import Secret, deserialize_secrets_inplace
+from haystack import Document, component, default_to_dict, logging
+from haystack.utils import Secret
 from tqdm import tqdm
 
 from haystack_integrations.common.google_genai.utils import _get_client
@@ -211,19 +211,6 @@ def to_dict(self) -> dict[str, Any]:
             max_retries=self._max_retries,
         )
 
-    @classmethod
-    def from_dict(cls, data: dict[str, Any]) -> "GoogleGenAIDocumentEmbedder":
-        """
-        Deserializes the component from a dictionary.
-
-        :param data:
-            Dictionary to deserialize from.
-        :returns:
-            Deserialized component.
-        """
-        deserialize_secrets_inplace(data["init_parameters"], keys=["api_key"])
-        return default_from_dict(cls, data)
-
     def _prepare_texts_to_embed(self, documents: list[Document]) -> list[str]:
         """
         Prepare the texts to embed by concatenating the Document text with the metadata fields to embed.

integrations/google_genai/src/haystack_integrations/components/embedders/google_genai/multimodal_document_embedder.py

@@ -11,14 +11,14 @@
 from google.genai import Client
 from google.genai.client import AsyncClient
 from google.genai.types import Content, EmbedContentConfig, Part
-from haystack import Document, component, default_from_dict, default_to_dict, logging
+from haystack import Document, component, default_to_dict, logging
 from haystack.components.converters.image.image_utils import (
     _batch_convert_pdf_pages_to_images,
     _encode_image_to_base64,
     _PDFPageInfo,
 )
 from haystack.dataclasses import ByteStream
-from haystack.utils import Secret, deserialize_secrets_inplace
+from haystack.utils import Secret
 from tqdm import tqdm
 from tqdm.asyncio import tqdm as async_tqdm
 from typing_extensions import NotRequired, TypedDict
@@ -321,19 +321,6 @@ def to_dict(self) -> dict[str, Any]:
             max_retries=self._max_retries,
         )
 
-    @classmethod
-    def from_dict(cls, data: dict[str, Any]) -> "GoogleGenAIMultimodalDocumentEmbedder":
-        """
-        Deserializes the component from a dictionary.
-
-        :param data:
-            Dictionary to deserialize from.
-        :returns:
-            Deserialized component.
-        """
-        deserialize_secrets_inplace(data["init_parameters"], keys=["api_key"])
-        return default_from_dict(cls, data)
-
     def _extract_parts_to_embed(self, documents: list[Document]) -> list[Part]:
         """
         Validates the input documents and extracts the files to embed in the format expected by the Google AI API.

integrations/google_genai/src/haystack_integrations/components/embedders/google_genai/text_embedder.py

@@ -6,8 +6,8 @@
 
 from google.genai import Client, types
 from google.genai.client import AsyncClient
-from haystack import component, default_from_dict, default_to_dict, logging
-from haystack.utils import Secret, deserialize_secrets_inplace
+from haystack import component, default_to_dict, logging
+from haystack.utils import Secret
 
 from haystack_integrations.common.google_genai.utils import _get_client
 
@@ -191,19 +191,6 @@ def to_dict(self) -> dict[str, Any]:
             max_retries=self._max_retries,
         )
 
-    @classmethod
-    def from_dict(cls, data: dict[str, Any]) -> "GoogleGenAITextEmbedder":
-        """
-        Deserializes the component from a dictionary.
-
-        :param data:
-            Dictionary to deserialize from.
-        :returns:
-            Deserialized component.
-        """
-        deserialize_secrets_inplace(data["init_parameters"], keys=["api_key"])
-        return default_from_dict(cls, data)
-
     def _prepare_input(self, text: str) -> dict[str, Any]:
         if not isinstance(text, str):
             error_message_text = (

integrations/google_genai/tests/test_document_embedder.py

@@ -9,6 +9,7 @@
 import numpy as np
 import pytest
 from haystack import Document
+from haystack.core.serialization import component_from_dict
 from haystack.utils.auth import Secret
 
 from haystack_integrations.components.embedders.google_genai import GoogleGenAIDocumentEmbedder, GoogleGenAITextEmbedder
@@ -156,7 +157,7 @@ def test_from_dict(self, monkeypatch):
             },
         }
         monkeypatch.setenv("GOOGLE_API_KEY", "fake-api-key")
-        embedder = GoogleGenAIDocumentEmbedder.from_dict(data)
+        embedder = component_from_dict(GoogleGenAIDocumentEmbedder, data, name="embedder")
         assert embedder._api_key.resolve_value() == "fake-api-key"
         assert embedder._model == "gemini-embedding-001"
         assert embedder._prefix == ""

integrations/google_genai/tests/test_text_embedder.py

@@ -7,6 +7,7 @@
 
 import pytest
 from google.genai.types import ContentEmbedding, EmbedContentResponse
+from haystack.core.serialization import component_from_dict
 from haystack.utils.auth import Secret
 
 from haystack_integrations.components.embedders.google_genai import GoogleGenAITextEmbedder
@@ -111,7 +112,7 @@ def test_from_dict(self, monkeypatch):
                 "max_retries": 3,
             },
         }
-        component = GoogleGenAITextEmbedder.from_dict(data)
+        component = component_from_dict(GoogleGenAITextEmbedder, data, name="component")
         assert component._api_key.resolve_value() == "fake-api-key"
         assert component._model_name == "gemini-embedding-001"
         assert component._prefix == ""

integrations/mistral/src/haystack_integrations/components/converters/mistral/ocr_document_converter.py

@@ -7,13 +7,13 @@
 from pathlib import Path
 from typing import Any, ClassVar
 
-from haystack import Document, component, default_from_dict, default_to_dict, logging
+from haystack import Document, component, default_to_dict, logging
 from haystack.components.converters.utils import (
     get_bytestream_from_source,
     normalize_metadata,
 )
 from haystack.dataclasses import ByteStream
-from haystack.utils import Secret, deserialize_secrets_inplace
+from haystack.utils import Secret
 from mistralai.client import Mistral
 from mistralai.client.models import (
     DocumentURLChunk,
@@ -186,19 +186,6 @@ def to_dict(self) -> dict[str, Any]:
             cleanup_uploaded_files=self.cleanup_uploaded_files,
         )
 
-    @classmethod
-    def from_dict(cls, data: dict[str, Any]) -> "MistralOCRDocumentConverter":
-        """
-        Deserializes the component from a dictionary.
-
-        :param data:
-            Dictionary to deserialize from.
-        :returns:
-            Deserialized component.
-        """
-        deserialize_secrets_inplace(data["init_parameters"], keys=["api_key"])
-        return default_from_dict(cls, data)
-
     @component.output_types(documents=list[Document], raw_mistral_response=list[dict[str, Any]])
     def run(
         self,