feat: add support to accept Dataframe as input to split text, and added relevant tests (#6302)

* update to support dataframe

* [autofix.ci] apply automated fixes

* [autofix.ci] apply automated fixes (attempt 2/3)

* Update split_text.py

* [autofix.ci] apply automated fixes

* [autofix.ci] apply automated fixes

* update names

* Update src/backend/base/langflow/schema/dataframe.py

Co-authored-by: Gabriel Luiz Freitas Almeida <gabriel@langflow.org>

* [autofix.ci] apply automated fixes

* update to template

* update review changes

* Update Vector Store RAG.json

* fix lint errors

* fix tests

* 📝 (freeze.spec.ts): update test description to match the actual element being tested for better clarity and accuracy

* ✨ (stop-button-playground.spec.ts): improve test reliability by specifying target position for drag action to prevent flakiness

* ✅ (logs.spec.ts): increase timeout from 1000ms to 3000ms for better test reliability
✅ (stop-building.spec.ts): update test selector from "handle-splittext-shownode-data inputs-left" to "handle-splittext-shownode-input documents-left" for accurate testing
✅ (starter-projects.spec.ts): add a 1000ms timeout before asserting visibility of an element for better test stability

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Gabriel Luiz Freitas Almeida <gabriel@langflow.org>
Co-authored-by: cristhianzl <cristhian.lousa@gmail.com>

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

@@ -15,10 +15,9 @@ class SplitTextComponent(Component):
     inputs = [
         HandleInput(
             name="data_inputs",
-            display_name="Data Inputs",
+            display_name="Input Documents",
             info="The data to split.",
-            input_types=["Data"],
-            is_list=True,
+            input_types=["Data", "DataFrame"],
             required=True,
         ),
         IntInput(
@@ -39,6 +38,13 @@ class SplitTextComponent(Component):
             info="The character to split on. Defaults to newline.",
             value="\n",
         ),
+        MessageTextInput(
+            name="text_key",
+            display_name="Text Key",
+            info="The key to use for the text column.",
+            value="text",
+            advanced=True,
+        ),
     ]
 
     outputs = [
@@ -46,23 +52,57 @@ class SplitTextComponent(Component):
         Output(display_name="DataFrame", name="dataframe", method="as_dataframe"),
     ]
 
-    def _docs_to_data(self, docs):
+    def _docs_to_data(self, docs) -> list[Data]:
         return [Data(text=doc.page_content, data=doc.metadata) for doc in docs]
 
-    def split_text(self) -> list[Data]:
+    def _docs_to_dataframe(self, docs):
+        data_dicts = [{self.text_key: doc.page_content, **doc.metadata} for doc in docs]
+        return DataFrame(data_dicts)
+
+    def split_text_base(self):
         separator = unescape_string(self.separator)
+        if isinstance(self.data_inputs, DataFrame):
+            if not len(self.data_inputs):
+                msg = "DataFrame is empty"
+                raise TypeError(msg)
 
-        documents = [_input.to_lc_document() for _input in self.data_inputs if isinstance(_input, Data)]
+            self.data_inputs.text_key = self.text_key
+            try:
+                documents = self.data_inputs.to_lc_documents()
+            except Exception as e:
+                msg = f"Error converting DataFrame to documents: {e}"
+                raise TypeError(msg) from e
+        else:
+            if not self.data_inputs:
+                msg = "No data inputs provided"
+                raise TypeError(msg)
 
-        splitter = CharacterTextSplitter(
-            chunk_overlap=self.chunk_overlap,
-            chunk_size=self.chunk_size,
-            separator=separator,
-        )
-        docs = splitter.split_documents(documents)
-        data = self._docs_to_data(docs)
-        self.status = data
-        return data
+            documents = []
+            if isinstance(self.data_inputs, Data):
+                self.data_inputs.text_key = self.text_key
+                documents = [self.data_inputs.to_lc_document()]
+            else:
+                try:
+                    documents = [input_.to_lc_document() for input_ in self.data_inputs if isinstance(input_, Data)]
+                    if not documents:
+                        msg = f"No valid Data inputs found in {type(self.data_inputs)}"
+                        raise TypeError(msg)
+                except AttributeError as e:
+                    msg = f"Invalid input type in collection: {e}"
+                    raise TypeError(msg) from e
+        try:
+            splitter = CharacterTextSplitter(
+                chunk_overlap=self.chunk_overlap,
+                chunk_size=self.chunk_size,
+                separator=separator,
+            )
+            return splitter.split_documents(documents)
+        except Exception as e:
+            msg = f"Error splitting text: {e}"
+            raise TypeError(msg) from e
+
+    def split_text(self) -> list[Data]:
+        return self._docs_to_data(self.split_text_base())
 
     def as_dataframe(self) -> DataFrame:
-        return DataFrame(self.split_text())
+        return self._docs_to_dataframe(self.split_text_base())

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

@@ -1,6 +1,7 @@
 from typing import cast
 
 import pandas as pd
+from langchain_core.documents import Document
 from pandas import DataFrame as pandas_DataFrame
 
 from langflow.schema.data import Data
@@ -32,9 +33,21 @@ class DataFrame(pandas_DataFrame):
         >>> dataset = DataFrame({"name": ["John", "Jane"], "age": [30, 25]})
     """
 
-    def __init__(self, data: list[dict] | list[Data] | pd.DataFrame | None = None, **kwargs):
+    def __init__(
+        self,
+        data: list[dict] | list[Data] | pd.DataFrame | None = None,
+        text_key: str = "text",
+        default_value: str = "",
+        **kwargs,
+    ):
+        # Initialize pandas DataFrame first without data
+        super().__init__(**kwargs)  # Removed data parameter
+
+        # Store attributes as private members to avoid conflicts with pandas
+        self._text_key = text_key
+        self._default_value = default_value
+
         if data is None:
-            super().__init__(**kwargs)
             return
 
         if isinstance(data, list):
@@ -43,15 +56,36 @@ class DataFrame(pandas_DataFrame):
             elif not all(isinstance(x, dict) for x in data):
                 msg = "List items must be either all Data objects or all dictionaries"
                 raise ValueError(msg)
-            kwargs["data"] = data
-        elif isinstance(data, dict | pd.DataFrame):
-            kwargs["data"] = data
+            self._update(data, **kwargs)
+        elif isinstance(data, dict | pd.DataFrame):  # Fixed type check syntax
+            self._update(data, **kwargs)
 
-        super().__init__(**kwargs)
+    def _update(self, data, **kwargs):
+        """Helper method to update DataFrame with new data."""
+        new_df = pd.DataFrame(data, **kwargs)
+        self._update_inplace(new_df)
+
+    # Update property accessors
+    @property
+    def text_key(self) -> str:
+        return self._text_key
+
+    @text_key.setter
+    def text_key(self, value: str) -> None:
+        self._text_key = value
+
+    @property
+    def default_value(self) -> str:
+        return self._default_value
+
+    @default_value.setter
+    def default_value(self, value: str) -> None:
+        self._default_value = value
 
     def to_data_list(self) -> list[Data]:
         """Converts the DataFrame back to a list of Data objects."""
         list_of_dicts = self.to_dict(orient="records")
+        # suggested change: [Data(**row) for row in list_of_dicts]
         return [Data(data=row) for row in list_of_dicts]
 
     def add_row(self, data: dict | Data) -> "DataFrame":
@@ -103,3 +137,31 @@ class DataFrame(pandas_DataFrame):
         Returns True if the DataFrame has at least one row, False otherwise.
         """
         return not self.empty
+
+    def to_lc_documents(self) -> list[Document]:
+        """Converts the DataFrame to a list of Documents.
+
+        Returns:
+            list[Document]: The converted list of Documents.
+        """
+        list_of_dicts = self.to_dict(orient="records")
+        documents = []
+        for row in list_of_dicts:
+            data_copy = row.copy()
+            text = data_copy.pop(self._text_key, self._default_value)
+            if isinstance(text, str):
+                documents.append(Document(page_content=text, metadata=data_copy))
+            else:
+                documents.append(Document(page_content=str(text), metadata=data_copy))
+        return documents
+
+    def _docs_to_dataframe(self, docs):
+        """Converts a list of Documents to a DataFrame.
+
+        Args:
+            docs: List of Document objects
+
+        Returns:
+            DataFrame: A new DataFrame with the converted Documents
+        """
+        return DataFrame(docs)