feat: Dynamic outputs for file component (#7005)

* feat: Dynamic outputs for file component

* [autofix.ci] apply automated fixes

* Update base_file.py

* [autofix.ci] apply automated fixes

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

* Update base_file.py

* [autofix.ci] apply automated fixes

* feat: enhance BaseFileComponent with new data loading methods and separator input

- Added `separator` input to specify the separator for concatenated outputs in Message format.
- Refactored output methods: renamed and updated `load_csv`, `load_json`, and `load_others` to `load_data`, `load_dataframe`, and `load_message` respectively.
- Updated JSON configuration files to reflect changes in output types and methods for starter projects.

* Fix file loader

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Ítalo Johnny <italojohnnydosanjos@gmail.com>
Co-authored-by: Rodrigo <rodrigosilvanader@gmail.com>

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

@@ -5,9 +5,12 @@ from pathlib import Path
 from tempfile import TemporaryDirectory
 from zipfile import ZipFile, is_zipfile
 
+import pandas as pd
+
 from langflow.custom import Component
-from langflow.io import BoolInput, FileInput, HandleInput, Output
+from langflow.io import BoolInput, FileInput, HandleInput, Output, StrInput
 from langflow.schema import Data
+from langflow.schema.dataframe import DataFrame
 from langflow.schema.message import Message
 
 
@@ -132,6 +135,14 @@ class BaseFileComponent(Component, ABC):
             is_list=True,
             advanced=True,
         ),
+        StrInput(
+            name="separator",
+            display_name="Separator",
+            value="\n\n",
+            show=True,
+            info="Specify the separator to use between multiple outputs in Message format.",
+            advanced=True,
+        ),
         BoolInput(
             name="silent_errors",
             display_name="Silent Errors",
@@ -161,7 +172,11 @@ class BaseFileComponent(Component, ABC):
         ),
     ]
 
-    _base_outputs = [Output(display_name="Data", name="data", method="load_files")]
+    _base_outputs = [
+        Output(display_name="Data", name="data", method="load_files"),
+        Output(display_name="DataFrame", name="dataframe", method="load_dataframe"),
+        Output(display_name="Message", name="message", method="load_message"),
+    ]
 
     @abstractmethod
     def process_files(self, file_list: list[BaseFile]) -> list[BaseFile]:
@@ -174,7 +189,7 @@ class BaseFileComponent(Component, ABC):
             list[BaseFile]: A list of BaseFile objects with updated `data`.
         """
 
-    def load_files(self) -> list[Data]:
+    def load_files_base(self) -> list[Data]:
         """Loads and parses file(s), including unpacked file bundles.
 
         Returns:
@@ -211,6 +226,80 @@ class BaseFileComponent(Component, ABC):
                     else:
                         file.path.unlink()
 
+    def load_files(self) -> list[Data]:
+        """Load files and return as Data objects.
+
+        Returns:
+            list[Data]: List of Data objects from all files
+        """
+        data_list = self.load_files_base()
+        if not data_list:
+            return [Data()]
+        return data_list
+
+    def load_dataframe(self) -> DataFrame:
+        """Load files and return as DataFrame.
+
+        Returns:
+            DataFrame: DataFrame containing all file data
+        """
+        data_list = self.load_files()
+        if not data_list:
+            return DataFrame()
+
+        # First handle CSV files specially
+        csv_data = []
+        non_csv_rows = []
+
+        for data in data_list:
+            file_path = data.data.get(self.SERVER_FILE_PATH_FIELDNAME)
+            if file_path and str(file_path).lower().endswith(".csv"):
+                try:
+                    csv_data.extend(pd.read_csv(file_path).to_dict("records"))
+                except Exception as e:
+                    self.log(f"Error processing CSV file {file_path}: {e}")
+                    if not self.silent_errors:
+                        raise
+            else:
+                # Handle non-CSV files as before
+                row = dict(data.data) if data.data else {}
+                if data.text:
+                    row["text"] = data.text
+                if file_path:
+                    row["file_path"] = file_path
+                non_csv_rows.append(row)
+
+        # Combine CSV and non-CSV data
+        all_rows = csv_data + non_csv_rows
+        return DataFrame(all_rows)
+
+    def load_message(self) -> Message:
+        """Load files and return as Message with concatenated content.
+
+        Returns:
+            Message: Message containing concatenated file content
+        """
+        data_list = self.load_files()
+        if not data_list:
+            return Message(text="")
+
+        # Concatenate all text content
+        text_content = []
+        for data in data_list:
+            content = data.text if data.text else ""
+            text_content.append(content)
+
+        # Join with separator
+        final_text = self.separator.join(text_content)
+
+        # Create message with all metadata
+        all_data = {}
+        for data in data_list:
+            if data.data:
+                all_data.update(data.data)
+
+        return Message(text=final_text, data=all_data)
+
     @property
     def valid_extensions(self) -> list[str]:
         """Returns valid file extensions for the class.

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

@@ -993,6 +993,34 @@
                   "Data"
                 ],
                 "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "method": "load_dataframe",
+                "name": "dataframe",
+                "required_inputs": [],
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Message",
+                "method": "load_message",
+                "name": "message",
+                "required_inputs": [],
+                "selected": "Message",
+                "tool_mode": true,
+                "types": [
+                  "Message"
+                ],
+                "value": "__UNDEFINED__"
               }
             ],
             "pinned": false,
@@ -1142,6 +1170,25 @@
                 "type": "file",
                 "value": ""
               },
+              "separator": {
+                "_input_type": "StrInput",
+                "advanced": true,
+                "display_name": "Separator",
+                "dynamic": false,
+                "info": "Specify the separator to use between multiple outputs in Message format.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "separator",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "\n\n"
+              },
               "silent_errors": {
                 "_input_type": "BoolInput",
                 "advanced": true,

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

@@ -2149,6 +2149,34 @@
                   "Data"
                 ],
                 "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "method": "load_dataframe",
+                "name": "dataframe",
+                "required_inputs": [],
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Message",
+                "method": "load_message",
+                "name": "message",
+                "required_inputs": [],
+                "selected": "Message",
+                "tool_mode": true,
+                "types": [
+                  "Message"
+                ],
+                "value": "__UNDEFINED__"
               }
             ],
             "pinned": false,
@@ -2309,6 +2337,25 @@
                 "type": "file",
                 "value": ""
               },
+              "separator": {
+                "_input_type": "StrInput",
+                "advanced": true,
+                "display_name": "Separator",
+                "dynamic": false,
+                "info": "Specify the separator to use between multiple outputs in Message format.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "separator",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "\n\n"
+              },
               "silent_errors": {
                 "_input_type": "BoolInput",
                 "advanced": true,

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

@@ -2564,6 +2564,34 @@
                   "Data"
                 ],
                 "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "method": "load_dataframe",
+                "name": "dataframe",
+                "required_inputs": [],
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Message",
+                "method": "load_message",
+                "name": "message",
+                "required_inputs": [],
+                "selected": "Message",
+                "tool_mode": true,
+                "types": [
+                  "Message"
+                ],
+                "value": "__UNDEFINED__"
               }
             ],
             "pinned": false,
@@ -2713,6 +2741,25 @@
                 "type": "file",
                 "value": ""
               },
+              "separator": {
+                "_input_type": "StrInput",
+                "advanced": true,
+                "display_name": "Separator",
+                "dynamic": false,
+                "info": "Specify the separator to use between multiple outputs in Message format.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "separator",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "\n\n"
+              },
               "silent_errors": {
                 "_input_type": "BoolInput",
                 "advanced": true,