feat: adding list of Data output to Parse Data (#4598)

* adding list of Data output to Parse Data

* [autofix.ci] apply automated fixes

* enabling connection from more List outputs

* [autofix.ci] apply automated fixes

* refactor to have single return type

* [autofix.ci] apply automated fixes

* addressing linting comments

* [autofix.ci] apply automated fixes

* apparently lint was missed...

* sigh

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Eric Hare <ericrhare@gmail.com>

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

@@ -1,6 +1,7 @@
 from langflow.custom import Component
-from langflow.helpers.data import data_to_text
+from langflow.helpers.data import data_to_text, data_to_text_list
 from langflow.io import DataInput, MultilineInput, Output, StrInput
+from langflow.schema import Data
 from langflow.schema.message import Message
 
 
@@ -11,7 +12,7 @@ class ParseDataComponent(Component):
     name = "ParseData"
 
     inputs = [
-        DataInput(name="data", display_name="Data", info="The data to convert to text."),
+        DataInput(name="data", display_name="Data", info="The data to convert to text.", is_list=True),
         MultilineInput(
             name="template",
             display_name="Template",
@@ -23,13 +24,36 @@ class ParseDataComponent(Component):
     ]
 
     outputs = [
-        Output(display_name="Text", name="text", method="parse_data"),
+        Output(
+            display_name="Text",
+            name="text",
+            info="Data as a single Message, with each input Data separated by Separator",
+            method="parse_data",
+        ),
+        Output(
+            display_name="Data List",
+            name="data_list",
+            info="Data as a list of new Data, each having `text` formatted by Template",
+            method="parse_data_as_list",
+        ),
     ]
 
-    def parse_data(self) -> Message:
+    def _clean_args(self) -> tuple[list[Data], str, str]:
         data = self.data if isinstance(self.data, list) else [self.data]
         template = self.template
+        sep = self.sep
+        return data, template, sep
 
-        result_string = data_to_text(template, data, sep=self.sep)
+    def parse_data(self) -> Message:
+        data, template, sep = self._clean_args()
+        result_string = data_to_text(template, data, sep)
         self.status = result_string
         return Message(text=result_string)
+
+    def parse_data_as_list(self) -> list[Data]:
+        data, template, _ = self._clean_args()
+        text_list, data_list = data_to_text_list(template, data)
+        for item, text in zip(data_list, text_list, strict=True):
+            item.set_text(text)
+        self.status = data_list
+        return data_list

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

@@ -16,17 +16,31 @@ def docs_to_data(documents: list[Document]) -> list[Data]:
     return [Data.from_document(document) for document in documents]
 
 
-def data_to_text(template: str, data: Data | list[Data], sep: str = "\n") -> str:
-    """Converts a list of Data to a list of texts.
+def data_to_text_list(template: str, data: Data | list[Data]) -> tuple[list[str], list[Data]]:
+    r"""Formats `text` within Data objects based on a given template.
+
+    Converts a Data object or a list of Data objects into a tuple containing a list of formatted strings
+    and a list of Data objects based on a given template.
 
     Args:
-        template (str): The template to use for the conversion.
-        data (list[Data]): The list of Data to convert.
-        sep (str): The separator used to join the data.
+        template (str): The format string template to be used for formatting the data.
+        data (Data | list[Data]): A single Data object or a list of Data objects to be formatted.
 
     Returns:
-        list[str]: The converted list of texts.
+        tuple[list[str], list[Data]]: A tuple containing a list of formatted strings based on the
+                                      provided template and data, and a list of Data objects.
     """
+    if data is None:
+        return [], []
+
+    if template is None:
+        msg = "Template must be a string, but got None."
+        raise ValueError(msg)
+
+    if not isinstance(template, str):
+        msg = f"Template must be a string, but got {type(template)}"
+        raise TypeError(msg)
+
     if isinstance(data, (Data)):
         data = [data]
     # Check if there are any format strings in the template
@@ -36,8 +50,24 @@ def data_to_text(template: str, data: Data | list[Data], sep: str = "\n") -> str
         for value in data
     ]
 
-    formated_data = [template.format(data=value.data, **value.data) for value in _data]
-    return sep.join(formated_data)
+    formatted_text = [template.format(data=value.data, **value.data) for value in _data]
+    return formatted_text, _data
+
+
+def data_to_text(template: str, data: Data | list[Data], sep: str = "\n") -> str:
+    r"""Converts data into a formatted text string based on a given template.
+
+    Args:
+        template (str): The template string used to format each data item.
+        data (Data | list[Data]): A single data item or a list of data items to be formatted.
+        sep (str, optional): The separator to use between formatted data items. Defaults to "\n".
+
+    Returns:
+        str: A string containing the formatted data items separated by the specified separator.
+    """
+    formatted_text, _ = data_to_text_list(template, data)
+    sep = "\n" if sep is None else sep
+    return sep.join(formatted_text)
 
 
 def messages_to_text(template: str, messages: Message | list[Message]) -> str:

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

@@ -54,6 +54,24 @@ class Data(BaseModel):
         """
         return self.data.get(self.text_key, self.default_value)
 
+    def set_text(self, text: str | None) -> str:
+        r"""Sets the text value in the data dictionary.
+
+        The object's `text` value is set to `text parameter as given, with the following modifications:
+
+         - `text` value of `None` is converted to an empty string.
+         - `text` value is converted to `str` type.
+
+        Args:
+            text (str): The text to be set in the data dictionary.
+
+        Returns:
+            str: The text value that was set in the data dictionary.
+        """
+        new_text = "" if text is None else str(text)
+        self.data[self.text_key] = new_text
+        return new_text
+
     @classmethod
     def from_document(cls, document: Document) -> "Data":
         """Converts a Document to a Data.