fix: Refactor a few more components to proper folders (#8324)

* fix: Refactor a few more components to proper folders

* Rename action for load files

* [autofix.ci] apply automated fixes

* Update tests for new naming

* Update video_file.py

* Update video_file.py

* Update video_file.py

* Update test_batch_run_component.py

* Move unit tests

* Update test_structured_output_component.py

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Yuqi Tang <yuqi.tang@datastax.com>

src/backend/base/langflow/base/data/base_file.py

@@ -174,7 +174,7 @@ class BaseFileComponent(Component, ABC):
     ]
 
     _base_outputs = [
-        Output(display_name="Loaded Files", name="dataframe", method="load_dataframe"),
+        Output(display_name="Loaded Files", name="dataframe", method="load_files"),
     ]
 
     @abstractmethod
@@ -225,7 +225,7 @@ class BaseFileComponent(Component, ABC):
                     else:
                         file.path.unlink()
 
-    def load_files(self) -> list[Data]:
+    def load_files_core(self) -> list[Data]:
         """Load files and return as Data objects.
 
         Returns:
@@ -236,13 +236,13 @@ class BaseFileComponent(Component, ABC):
             return [Data()]
         return data_list
 
-    def load_dataframe(self) -> DataFrame:
+    def load_files(self) -> DataFrame:
         """Load files and return as DataFrame.
 
         Returns:
             DataFrame: DataFrame containing all file data
         """
-        data_list = self.load_files()
+        data_list = self.load_files_core()
         if not data_list:
             return DataFrame()
 

src/backend/base/langflow/components/helpers/__init__.py

@@ -5,10 +5,8 @@ from .id_generator import IDGeneratorComponent
 from .memory import MemoryComponent
 from .output_parser import OutputParserComponent
 from .store_message import MessageStoreComponent
-from .structured_output import StructuredOutputComponent
 
 __all__ = [
-    "BatchRunComponent",
     "CalculatorComponent",
     "CreateListComponent",
     "CurrentDateComponent",
@@ -16,5 +14,4 @@ __all__ = [
     "MemoryComponent",
     "MessageStoreComponent",
     "OutputParserComponent",
-    "StructuredOutputComponent",
 ]

src/backend/base/langflow/components/processing/__init__.py

@@ -1,4 +1,5 @@
 from .alter_metadata import AlterMetadataComponent
+from .batch_run import BatchRunComponent
 from .combine_text import CombineTextComponent
 from .converter import TypeConverterComponent
 from .create_data import CreateDataComponent
@@ -17,10 +18,12 @@ from .python_repl_core import PythonREPLComponent
 from .regex import RegexExtractorComponent
 from .select_data import SelectDataComponent
 from .split_text import SplitTextComponent
+from .structured_output import StructuredOutputComponent
 from .update_data import UpdateDataComponent
 
 __all__ = [
     "AlterMetadataComponent",
+    "BatchRunComponent",
     "CombineTextComponent",
     "CreateDataComponent",
     "DataFilterComponent",
@@ -39,6 +42,7 @@ __all__ = [
     "RegexExtractorComponent",
     "SelectDataComponent",
     "SplitTextComponent",
+    "StructuredOutputComponent",
     "TypeConverterComponent",
     "UpdateDataComponent",
 ]

src/backend/base/langflow/components/processing/save_file.py

@@ -9,7 +9,7 @@ from fastapi.encoders import jsonable_encoder
 
 from langflow.api.v2.files import upload_user_file
 from langflow.custom import Component
-from langflow.io import DropdownInput, HandleInput, Output, StrInput
+from langflow.io import DropdownInput, HandleInput, StrInput
 from langflow.schema import Data, DataFrame, Message
 from langflow.services.auth.utils import create_user_longterm_token
 from langflow.services.database.models.user.crud import get_user_by_id
@@ -51,14 +51,6 @@ class SaveToFileComponent(Component):
         ),
     ]
 
-    outputs = [
-        Output(
-            name="confirmation",
-            display_name="Confirmation",
-            method="save_to_file",
-        ),
-    ]
-
     async def save_to_file(self) -> str:
         """Save the input to a file and upload it, returning a confirmation message."""
         # Validate inputs

src/backend/base/langflow/components/twelvelabs/video_file.py

@@ -2,7 +2,7 @@ from pathlib import Path
 
 from langflow.base.data import BaseFileComponent
 from langflow.io import FileInput
-from langflow.schema import Data
+from langflow.schema import Data, DataFrame
 
 
 class VideoFileComponent(BaseFileComponent):
@@ -135,13 +135,13 @@ class VideoFileComponent(BaseFileComponent):
 
         return processed_files
 
-    def load_files(self) -> list[Data]:
+    def load_files(self) -> DataFrame:
         """Load video files and return a list of Data objects."""
         try:
             self.log("DEBUG: Starting video file load")
             if not hasattr(self, "file_path") or not self.file_path:
                 self.log("DEBUG: No video file path provided")
-                return []
+                return DataFrame()
 
             self.log(f"DEBUG: Loading video from path: {self.file_path}")
 
@@ -149,7 +149,7 @@ class VideoFileComponent(BaseFileComponent):
             file_path_obj = Path(self.file_path)
             if not file_path_obj.exists():
                 self.log(f"DEBUG: Video file not found at path: {self.file_path}")
-                return []
+                return DataFrame()
 
             # Verify file size
             file_size = file_path_obj.stat().st_size
@@ -162,18 +162,18 @@ class VideoFileComponent(BaseFileComponent):
             }
 
             self.log(f"DEBUG: Created video data: {video_data}")
-            result = [Data(data=video_data)]
+            result = DataFrame(data=[video_data])
 
             # Log the result to verify it's a proper Data object
             self.log("DEBUG: Returning list with Data objects")
         except (FileNotFoundError, PermissionError, OSError) as e:
             self.log(f"DEBUG: File error in video load_files: {e!s}", "ERROR")
-            return []
+            return DataFrame()
         except ImportError as e:
             self.log(f"DEBUG: Import error in video load_files: {e!s}", "ERROR")
-            return []
+            return DataFrame()
         except (ValueError, TypeError) as e:
             self.log(f"DEBUG: Value or type error in video load_files: {e!s}", "ERROR")
-            return []
+            return DataFrame()
         else:
             return result

src/backend/base/langflow/initial_setup/starter_projects/Document Q&A.json

@@ -804,7 +804,7 @@
                 "cache": true,
                 "display_name": "Loaded Files",
                 "group_outputs": false,
-                "method": "load_dataframe",
+                "method": "load_files",
                 "name": "dataframe",
                 "required_inputs": [],
                 "selected": "DataFrame",

src/backend/base/langflow/initial_setup/starter_projects/Portfolio Website Code Generator.json

@@ -1857,7 +1857,7 @@
                 "cache": true,
                 "display_name": "Loaded Files",
                 "group_outputs": false,
-                "method": "load_dataframe",
+                "method": "load_files",
                 "name": "dataframe",
                 "required_inputs": [],
                 "selected": "DataFrame",

src/backend/base/langflow/initial_setup/starter_projects/Text Sentiment Analysis.json

@@ -266,7 +266,7 @@
                 "cache": true,
                 "display_name": "Loaded Files",
                 "group_outputs": false,
-                "method": "load_dataframe",
+                "method": "load_files",
                 "name": "dataframe",
                 "required_inputs": [],
                 "selected": "DataFrame",

src/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.json

@@ -2447,7 +2447,7 @@
                 "cache": true,
                 "display_name": "Loaded Files",
                 "group_outputs": false,
-                "method": "load_dataframe",
+                "method": "load_files",
                 "name": "dataframe",
                 "required_inputs": [],
                 "selected": "DataFrame",

src/backend/base/langflow/initial_setup/starter_projects/document_qa.py

@@ -23,7 +23,7 @@ Answer:
 """
     file_component = FileComponent()
     parse_data_component = ParserComponent()
-    parse_data_component.set(input_data=file_component.load_dataframe)
+    parse_data_component.set(input_data=file_component.load_files)
 
     chat_input = ChatInput()
     prompt_component = PromptComponent()

src/backend/base/langflow/initial_setup/starter_projects/vector_store_rag.py

@@ -15,7 +15,7 @@ def ingestion_graph():
     # Ingestion Graph
     file_component = FileComponent()
     text_splitter = SplitTextComponent()
-    text_splitter.set(data_inputs=file_component.load_dataframe)
+    text_splitter.set(data_inputs=file_component.load_files)
     openai_embeddings = OpenAIEmbeddingsComponent()
     vector_store = AstraDBVectorStoreComponent()
     vector_store.set(

src/backend/tests/unit/components/processing/test_batch_run_component.py

@@ -1,7 +1,7 @@
 import re
 
 import pytest
-from langflow.components.helpers.batch_run import BatchRunComponent
+from langflow.components.processing.batch_run import BatchRunComponent
 from langflow.schema import DataFrame
 
 from tests.base import ComponentTestBaseWithoutClient

src/backend/tests/unit/components/processing/test_structured_output_component.py

@@ -5,7 +5,7 @@ from unittest.mock import patch
 import openai
 import pytest
 from langchain_openai import ChatOpenAI
-from langflow.components.helpers.structured_output import StructuredOutputComponent
+from langflow.components.processing.structured_output import StructuredOutputComponent
 from langflow.helpers.base_model import build_model_from_schema
 from langflow.inputs.inputs import TableInput
 from pydantic import BaseModel
@@ -53,7 +53,7 @@ class TestStructuredOutputComponent(ComponentTestBaseWithoutClient):
             system_prompt="Test system prompt",
         )
 
-        with patch("langflow.components.helpers.structured_output.get_chat_result", mock_get_chat_result):
+        with patch("langflow.components.processing.structured_output.get_chat_result", mock_get_chat_result):
             result = component.build_structured_output_base()
             assert isinstance(result, list)
             assert result == [{"field": "value"}]
@@ -174,7 +174,7 @@ class TestStructuredOutputComponent(ComponentTestBaseWithoutClient):
         with pytest.raises(ValueError, match="Invalid type: invalid_type"):
             component.build_structured_output()
 
-    @patch("langflow.components.helpers.structured_output.get_chat_result")
+    @patch("langflow.components.processing.structured_output.get_chat_result")
     def test_nested_output_schema(self, mock_get_chat_result):
         class ChildModel(BaseModel):
             child: str = "value"
@@ -208,7 +208,7 @@ class TestStructuredOutputComponent(ComponentTestBaseWithoutClient):
         assert isinstance(result, list)
         assert result == [{"parent": {"child": "value"}}]
 
-    @patch("langflow.components.helpers.structured_output.get_chat_result")
+    @patch("langflow.components.processing.structured_output.get_chat_result")
     def test_large_input_value(self, mock_get_chat_result):
         large_input = "Test input " * 1000
 

src/backend/tests/unit/initial_setup/starter_projects/test_vector_store_rag.py

@@ -24,7 +24,7 @@ def ingestion_graph():
     file_component.set(path="test.txt")
     file_component.set_on_output(name="dataframe", value=Data(text="This is a test file."), cache=True)
     text_splitter = SplitTextComponent(_id="text-splitter-123")
-    text_splitter.set(data_inputs=file_component.load_dataframe)
+    text_splitter.set(data_inputs=file_component.load_files)
     openai_embeddings = OpenAIEmbeddingsComponent(_id="openai-embeddings-123")
     openai_embeddings.set(
         openai_api_key="sk-123", openai_api_base="https://api.openai.com/v1", openai_api_type="openai"