feat: Enhance Data Components and Add SelectData Functionality (#3715)

## Changes Overview

This PR introduces several enhancements to our data handling components and removes some legacy code:

1. **CreateData and UpdateData Components**:
   - Added text key name validation
   - Enhanced UpdateData to support updating and appending multiple data points
   - Implemented optional text key validator for dynamically loaded data
   - Updated component names, descriptions, and default values

2. **New SelectData Component**:
   - Implemented SelectDataComponent for data selection from a list
   - Added inputs for data list and index selection
   - Implemented error handling for out-of-range index selection

3. **Code Cleanup**:
   - Removed legacy post_code_processing methods from CreateDataComponent and UpdateDataComponent
   - Removed corresponding test cases

4. **Testing**:
   - Added unit tests for CreateData and UpdateData components
   - Updated test file names for consistency

src/backend/base/langflow/components/prototypes/CreateData.py

@@ -1,7 +1,7 @@
 from typing import Any
 
 from langflow.custom import Component
-from langflow.inputs.inputs import IntInput, MessageTextInput, DictInput
+from langflow.inputs.inputs import IntInput, MessageTextInput, DictInput, BoolInput
 from langflow.io import Output
 
 from langflow.field_typing.range_spec import RangeSpec
@@ -20,10 +20,21 @@ class CreateDataComponent(Component):
             display_name="Number of Fields",
             info="Number of fields to be added to the record.",
             real_time_refresh=True,
-            value=0,
+            value=1,
             range_spec=RangeSpec(min=1, max=15, step=1, step_type="int"),
         ),
-        MessageTextInput(name="text_key", display_name="Text Key", info="Key to be used as text.", advanced=True),
+        MessageTextInput(
+            name="text_key",
+            display_name="Text Key",
+            info="Key that identifies the field to be used as the text content.",
+            advanced=True,
+        ),
+        BoolInput(
+            name="text_key_validator",
+            display_name="Text Key Validator",
+            advanced=True,
+            info="If enabled, checks if the given 'Text Key' is present in the given 'Data'.",
+        ),
     ]
 
     outputs = [
@@ -32,7 +43,7 @@ class CreateDataComponent(Component):
 
     def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None):
         if field_name == "number_of_fields":
-            default_keys = ["code", "_type", "number_of_fields", "text_key"]
+            default_keys = ["code", "_type", "number_of_fields", "text_key", "text_key_validator"]
             try:
                 field_value_int = int(field_value)
             except ValueError:
@@ -65,6 +76,15 @@ class CreateDataComponent(Component):
         return build_config
 
     async def build_data(self) -> Data:
+        data = self.get_data()
+        return_data = Data(data=data, text_key=self.text_key)
+        self.status = return_data
+        if self.text_key_validator:
+            self.validate_text_key()
+        return return_data
+
+    def get_data(self):
+        """Function to get the Data from the attributes"""
         data = {}
         for value_dict in self._attributes.values():
             if isinstance(value_dict, dict):
@@ -73,17 +93,11 @@ class CreateDataComponent(Component):
                     key: value.get_text() if isinstance(value, Data) else value for key, value in value_dict.items()
                 }
                 data.update(value_dict)
-        return_data = Data(data=data, text_key=self.text_key)
+        return data
-        self.status = return_data
-        return return_data
 
-    def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):
+    def validate_text_key(self):
-        """
+        """This function validates that the Text Key is one of the keys in the Data"""
-        This function is called after the code validation is done.
+        data_keys = self.get_data().keys()
-        """
+        if self.text_key not in data_keys and self.text_key != "":
-        frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)
+            formatted_data_keys = ", ".join(data_keys)
-        frontend_node["template"] = self.update_build_config(
+            raise ValueError(f"Text Key: '{self.text_key}' not found in the Data keys: '{formatted_data_keys}'")
-            frontend_node["template"], frontend_node["template"]["number_of_fields"]["value"], "number_of_fields"
-        )
-        frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)
-        return frontend_node

src/backend/base/langflow/components/prototypes/SelectData.py

@@ -0,0 +1,47 @@
+from langflow.custom import Component
+from langflow.inputs.inputs import DataInput, IntInput
+from langflow.io import Output
+
+from langflow.field_typing.range_spec import RangeSpec
+from langflow.schema import Data
+
+
+class SelectDataComponent(Component):
+    display_name: str = "Select Data"
+    description: str = "Select a single data from a list of data."
+    name: str = "SelectData"
+    icon = "prototypes"
+
+    inputs = [
+        DataInput(
+            name="data_list",
+            display_name="Data List",
+            info="List of data to select from.",
+            is_list=True,  # Specify that this input takes a list of Data objects
+        ),
+        IntInput(
+            name="data_index",
+            display_name="Data Index",
+            info="Index of the data to select.",
+            value=0,  # Will be populated dynamically based on the length of data_list
+            range_spec=RangeSpec(min=0, max=15, step=1, step_type="int"),
+        ),
+    ]
+
+    outputs = [
+        Output(display_name="Selected Data", name="selected_data", method="select_data"),
+    ]
+
+    async def select_data(self) -> Data:
+        # Retrieve the selected index from the dropdown
+        selected_index = int(self.data_index)
+        # Get the data list
+
+        # Validate that the selected index is within bounds
+        if selected_index < 0 or selected_index >= len(self.data_list):
+            raise ValueError(f"Selected index {selected_index} is out of range.")
+
+        # Return the selected Data object
+        selected_data = self.data_list[selected_index]
+        self.status = selected_data  # Update the component status to reflect the selected data
+        return selected_data

src/backend/base/langflow/components/prototypes/UpdateData.py

@@ -1,40 +1,109 @@
-from langflow.custom import CustomComponent
+from typing import Any
+
+from langflow.custom import Component
+from langflow.inputs.inputs import IntInput, MessageTextInput, DictInput, DataInput, BoolInput
+from langflow.io import Output
+
+from langflow.field_typing.range_spec import RangeSpec
 from langflow.schema import Data
+from langflow.schema.dotdict import dotdict
 
 
-class UpdateDataComponent(CustomComponent):
+class UpdateDataComponent(Component):
-    display_name = "Update Data"
+    display_name: str = "Update data"
-    description = "Update Data with text-based key/value pairs, similar to updating a Python dictionary."
+    description: str = "Dynamically update or append data with the specified fields."
-    name = "UpdateData"
+    name: str = "UpdateData"
 
-    def build_config(self):
+    inputs = [
-        return {
+        DataInput(
-            "data": {
+            name="old_data",
-                "display_name": "Data",
+            display_name="Data",
-                "info": "The record to update.",
+            info="The record to update.",
-            },
+            is_list=False,
-            "new_data": {
+        ),
-                "display_name": "New Data",
+        IntInput(
-                "info": "The new data to update the record with.",
+            name="number_of_fields",
-                "input_types": ["Text"],
+            display_name="Number of Fields",
-            },
+            info="Number of fields to be added to the record.",
-        }
+            real_time_refresh=True,
+            value=0,
+            range_spec=RangeSpec(min=1, max=15, step=1, step_type="int"),
+        ),
+        MessageTextInput(
+            name="text_key",
+            display_name="Text Key",
+            info="Key that identifies the field to be used as the text content.",
+            advanced=True,
+        ),
+        BoolInput(
+            name="text_key_validator",
+            display_name="Text Key Validator",
+            advanced=True,
+            info="If enabled, checks if the given 'Text Key' is present in the given 'Data'.",
+        ),
+    ]
 
-    def build(
+    outputs = [
-        self,
+        Output(display_name="Data", name="data", method="build_data"),
-        data: Data,
+    ]
-        new_data: dict,
-    ) -> Data:
-        """
-        Updates a record with new data.
 
-        Args:
+    def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None):
-            record (Data): The record to update.
+        if field_name == "number_of_fields":
-            new_data (dict): The new data to update the record with.
+            default_keys = ["code", "_type", "number_of_fields", "text_key", "old_data", "text_key_validator"]
+            try:
+                field_value_int = int(field_value)
+            except ValueError:
+                return build_config
+            existing_fields = {}
+            if field_value_int > 15:
+                build_config["number_of_fields"]["value"] = 15
+                raise ValueError("Number of fields cannot exceed 15. Try using a Component to combine two Data.")
+            if len(build_config) > len(default_keys):
+                # back up the existing template fields
+                for key in build_config.copy():
+                    if key not in default_keys:
+                        existing_fields[key] = build_config.pop(key)
 
-        Returns:
+            for i in range(1, field_value_int + 1):
-            Data: The updated record.
+                key = f"field_{i}_key"
-        """
+                if key in existing_fields:
-        data.data.update(new_data)
+                    field = existing_fields[key]
-        self.status = data
+                    build_config[key] = field
+                else:
+                    field = DictInput(
+                        display_name=f"Field {i}",
+                        name=key,
+                        info=f"Key for field {i}.",
+                        input_types=["Text", "Data"],
+                    )
+                    build_config[field.name] = field.to_dict()
+
+            build_config["number_of_fields"]["value"] = field_value_int
+        return build_config
+
+    async def build_data(self) -> Data:
+        new_data = self.get_data()
+        self.old_data.data.update(new_data)
+        if self.text_key:
+            self.old_data.text_key = self.text_key
+        self.status = self.old_data
+        self.validate_text_key(self.old_data)
+        return self.old_data
+
+    def get_data(self):
+        """Function to get the Data from the attributes"""
+        data = {}
+        for value_dict in self._attributes.values():
+            if isinstance(value_dict, dict):
+                # Check if the value of the value_dict is a Data
+                value_dict = {
+                    key: value.get_text() if isinstance(value, Data) else value for key, value in value_dict.items()
+                }
+                data.update(value_dict)
         return data
+
+    def validate_text_key(self, data: Data):
+        """This function validates that the Text Key is one of the keys in the Data"""
+        data_keys = data.data.keys()
+        if self.text_key not in data_keys and self.text_key != "":
+            raise ValueError(f"Text Key: {self.text_key} not found in the Data keys: {','.join(data_keys)}")

src/backend/tests/unit/components/prototypes/test_create_data_component.py

@@ -0,0 +1,117 @@
+import pytest
+from langflow.components.prototypes.CreateData import CreateDataComponent
+from langflow.schema import Data
+
+
+@pytest.fixture
+def create_data_component():
+    return CreateDataComponent()
+
+
+def test_update_build_config(create_data_component):
+    build_config = {
+        "number_of_fields": {
+            "type": "int",
+            "value": 2,
+        },
+        "text_key": {
+            "type": "str",
+            "value": "",
+        },
+        "text_key_validator": {
+            "type": "bool",
+            "value": False,
+        },
+    }
+    updated_config = create_data_component.update_build_config(
+        build_config=build_config, field_value=3, field_name="number_of_fields"
+    )
+
+    assert "field_1_key" in updated_config
+    assert "field_2_key" in updated_config
+    assert "field_3_key" in updated_config
+    assert updated_config["number_of_fields"]["value"] == 3
+
+
+def test_update_build_config_exceed_limit(create_data_component):
+    build_config = {
+        "number_of_fields": {
+            "type": "int",
+            "value": 2,
+        },
+        "text_key": {
+            "type": "str",
+            "value": "",
+        },
+        "text_key_validator": {
+            "type": "bool",
+            "value": False,
+        },
+    }
+    with pytest.raises(
+        ValueError, match="Number of fields cannot exceed 15. Try using a Component to combine two Data."
+    ):
+        create_data_component.update_build_config(build_config, 16, "number_of_fields")
+
+
+@pytest.mark.asyncio
+async def test_build_data(create_data_component):
+    create_data_component._attributes = {
+        "field_1_key": {"key1": "value1"},
+        "field_2_key": {"key2": "value2"},
+    }
+    create_data_component.text_key = "key1"
+    create_data_component.text_key_validator = False
+
+    result = await create_data_component.build_data()
+
+    assert isinstance(result, Data)
+    assert result.data == {"key1": "value1", "key2": "value2"}
+    assert result.text_key == "key1"
+
+
+def test_get_data(create_data_component):
+    create_data_component._attributes = {
+        "field_1_key": {"key1": "value1"},
+        "field_2_key": {"key2": "value2"},
+    }
+
+    result = create_data_component.get_data()
+
+    assert result == {"key1": "value1", "key2": "value2"}
+
+
+def test_validate_text_key_valid(create_data_component):
+    # Arrange
+    create_data_component._attributes = {
+        "field_1_key": {"key1": "value1"},
+        "field_2_key": {"key2": "value2"},
+    }
+    create_data_component.text_key = "key1"
+
+    # Act & Assert
+    try:
+        create_data_component.validate_text_key()
+    except ValueError:
+        pytest.fail("validate_text_key() raised ValueError unexpectedly!")
+
+    # Additional assertions
+    assert create_data_component.text_key == "key1"
+    assert "key1" in create_data_component.get_data()
+
+
+def test_validate_text_key_invalid(create_data_component):
+    # Arrange
+    create_data_component._attributes = {
+        "field_1_key": {"key1": "value1"},
+        "field_2_key": {"key2": "value2"},
+    }
+    create_data_component.text_key = "invalid_key"
+
+    # Act & Assert
+    with pytest.raises(ValueError) as exc_info:
+        create_data_component.validate_text_key()
+
+    # Check for the exact error message
+    expected_error_message = f"Text Key: '{create_data_component.text_key}' not found in the Data keys: '{', '.join(create_data_component.get_data().keys())}'"
+    assert str(exc_info.value) == expected_error_message

src/backend/tests/unit/components/prototypes/test_update_data_component.py

@@ -0,0 +1,105 @@
+import pytest
+from langflow.components.prototypes.UpdateData import UpdateDataComponent
+from langflow.schema import Data
+
+
+@pytest.fixture
+def update_data_component():
+    return UpdateDataComponent()
+
+
+def test_update_build_config(update_data_component):
+    build_config = {
+        "number_of_fields": {
+            "type": "int",
+            "value": 2,
+        },
+        "text_key": {
+            "type": "str",
+            "value": "",
+        },
+        "text_key_validator": {
+            "type": "bool",
+            "value": False,
+        },
+    }
+    updated_config = update_data_component.update_build_config(
+        build_config=build_config, field_value=3, field_name="number_of_fields"
+    )
+
+    assert "field_1_key" in updated_config
+    assert "field_2_key" in updated_config
+    assert "field_3_key" in updated_config
+    assert updated_config["number_of_fields"]["value"] == 3
+
+
+def test_update_build_config_exceed_limit(update_data_component):
+    build_config = {
+        "number_of_fields": {
+            "type": "int",
+            "value": 2,
+        },
+        "text_key": {
+            "type": "str",
+            "value": "",
+        },
+        "text_key_validator": {
+            "type": "bool",
+            "value": False,
+        },
+    }
+    with pytest.raises(
+        ValueError, match="Number of fields cannot exceed 15. Try using a Component to combine two Data."
+    ):
+        update_data_component.update_build_config(build_config, 16, "number_of_fields")
+
+
+@pytest.mark.asyncio
+async def test_build_data(update_data_component):
+    update_data_component._attributes = {
+        "field_1_key": {"key1": "new_value1"},
+        "field_2_key": {"key3": "value3"},
+    }
+    update_data_component.text_key = "key1"
+    update_data_component.text_key_validator = False
+    update_data_component.old_data = Data(data={"key1": "old_value1", "key2": "value2"}, text_key="key2")
+
+    result = await update_data_component.build_data()
+
+    assert isinstance(result, Data)
+    assert result.data == {"key1": "new_value1", "key2": "value2", "key3": "value3"}
+    assert result.text_key == "key1"
+
+
+def test_get_data(update_data_component):
+    update_data_component._attributes = {
+        "field_1_key": {"key1": "value1"},
+        "field_2_key": {"key2": "value2"},
+    }
+
+    result = update_data_component.get_data()
+
+    assert result == {"key1": "value1", "key2": "value2"}
+
+
+def test_validate_text_key_valid(update_data_component):
+    data = Data(data={"key1": "value1", "key2": "value2"}, text_key="key1")
+    update_data_component.text_key = "key1"
+
+    try:
+        update_data_component.validate_text_key(data)
+    except ValueError:
+        pytest.fail("validate_text_key() raised ValueError unexpectedly!")
+
+
+def test_validate_text_key_invalid(update_data_component):
+    data = Data(data={"key1": "value1", "key2": "value2"}, text_key="key1")
+    update_data_component.text_key = "invalid_key"
+
+    with pytest.raises(ValueError) as exc_info:
+        update_data_component.validate_text_key(data)
+
+    expected_error_message = (
+        f"Text Key: {update_data_component.text_key} not found in the Data keys: {','.join(data.data.keys())}"
+    )
+    assert str(exc_info.value) == expected_error_message