feat: New Search Bundle (#8146)

* delete data and transfer data to dataframe

* [autofix.ci] apply automated fixes

* create a new bundle for search

* fix type for dataframe

* add data_to_dataframe function

* [autofix.ci] apply automated fixes

* fix test because of files movement

* delete message and text

* json update

* fix search yahoo test

* fix run_model output type

* fix test errors

* fix test errors

* fix test error

* try fix frontend tests

* test fix

* [autofix.ci] apply automated fixes

* move serp search

* fix test

* fix test

* fix test to pass ruff style check

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Edwin Jose <edwin.jose@datastax.com>
Co-authored-by: Mike Fortman <michael.fortman@datastax.com>

src/backend/base/langflow/base/langchain_utilities/model.py

@@ -4,7 +4,7 @@ from collections.abc import Sequence
 from langflow.custom import Component
 from langflow.field_typing import Tool
 from langflow.io import Output
-from langflow.schema import Data
+from langflow.schema import Data, DataFrame
 
 
 class LCToolComponent(Component):
@@ -26,7 +26,7 @@ class LCToolComponent(Component):
                 raise ValueError(msg)
 
     @abstractmethod
-    def run_model(self) -> Data | list[Data]:
+    def run_model(self) -> Data | list[Data] | DataFrame:
         """Run model and return the output."""
 
     @abstractmethod

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

@@ -0,0 +1,29 @@
+from .arxiv import ArXivComponent
+from .bing_search_api import BingSearchAPIComponent
+from .duck_duck_go_search_run import DuckDuckGoSearchComponent
+from .exa_search import ExaSearchToolkit
+from .glean_search_api import GleanSearchAPISchema
+from .google_search_api_core import GoogleSearchAPICore
+from .google_serper_api_core import GoogleSerperAPICore
+from .search import SearchComponent
+from .serp import SerpComponent
+from .wikidata import WikidataComponent
+from .wikipedia import WikipediaComponent
+from .wolfram_alpha_api import WolframAlphaAPIComponent
+from .yahoo import YahooFinanceSchema
+
+__all__ = [
+    "ArXivComponent",
+    "BingSearchAPIComponent",
+    "DuckDuckGoSearchComponent",
+    "ExaSearchToolkit",
+    "GleanSearchAPISchema",
+    "GoogleSearchAPICore",
+    "GoogleSerperAPICore",
+    "SearchComponent",
+    "SerpComponent",
+    "WikidataComponent",
+    "WikipediaComponent",
+    "WolframAlphaAPIComponent",
+    "YahooFinanceSchema",
+]

src/backend/base/langflow/components/search/arxiv.py

@@ -5,6 +5,7 @@ from xml.etree.ElementTree import Element
 from defusedxml.ElementTree import fromstring
 
 from langflow.custom import Component
+from langflow.helpers.data import data_to_dataframe
 from langflow.io import DropdownInput, IntInput, MessageTextInput, Output
 from langflow.schema import Data, DataFrame
 
@@ -37,8 +38,7 @@ class ArXivComponent(Component):
     ]
 
     outputs = [
-        Output(display_name="Data", name="data", method="search_papers"),
-        Output(display_name="DataFrame", name="dataframe", method="as_dataframe"),
+        Output(display_name="DataFrame", name="dataframe", method="search_papers_dataframe"),
     ]
 
     def build_query_url(self) -> str:
@@ -105,6 +105,9 @@ class ArXivComponent(Component):
         cat = element.find("arxiv:primary_category", ns)
         return cat.get("term") if cat is not None else None
 
+    def run_model(self) -> DataFrame:
+        return self.search_papers_dataframe()
+
     def search_papers(self) -> list[Data]:
         """Search arXiv and return results."""
         try:
@@ -150,13 +153,11 @@ class ArXivComponent(Component):
         else:
             return results
 
-    def as_dataframe(self) -> DataFrame:
+    def search_papers_dataframe(self) -> DataFrame:
         """Convert the Arxiv search results to a DataFrame.
 
         Returns:
             DataFrame: A DataFrame containing the search results.
         """
         data = self.search_papers()
-        if isinstance(data, list):
-            return DataFrame(data=[d.data for d in data])
-        return DataFrame(data=[data.data])
+        return data_to_dataframe(data)

src/backend/base/langflow/components/search/bing_search_api.py

@@ -5,8 +5,10 @@ from langchain_community.utilities import BingSearchAPIWrapper
 
 from langflow.base.langchain_utilities.model import LCToolComponent
 from langflow.field_typing import Tool
+from langflow.helpers.data import data_to_dataframe
 from langflow.inputs import IntInput, MessageTextInput, MultilineInput, SecretStrInput
-from langflow.schema import Data
+from langflow.io import Output
+from langflow.schema import Data, DataFrame
 
 
 class BingSearchAPIComponent(LCToolComponent):
@@ -25,7 +27,15 @@ class BingSearchAPIComponent(LCToolComponent):
         IntInput(name="k", display_name="Number of results", value=4, required=True),
     ]
 
-    def run_model(self) -> list[Data]:
+    outputs = [
+        Output(display_name="DataFrame", name="dataframe", method="fetch_content_dataframe"),
+        Output(display_name="Tool", name="tool", method="build_tool"),
+    ]
+
+    def run_model(self) -> DataFrame:
+        return self.fetch_content_dataframe()
+
+    def fetch_content(self) -> list[Data]:
         if self.bing_search_url:
             wrapper = BingSearchAPIWrapper(
                 bing_search_url=self.bing_search_url, bing_subscription_key=self.bing_subscription_key
@@ -37,6 +47,10 @@ class BingSearchAPIComponent(LCToolComponent):
         self.status = data
         return data
 
+    def fetch_content_dataframe(self) -> DataFrame:
+        data = self.fetch_content()
+        return data_to_dataframe(data)
+
     def build_tool(self) -> Tool:
         if self.bing_search_url:
             wrapper = BingSearchAPIWrapper(

src/backend/base/langflow/components/search/duck_duck_go_search_run.py

@@ -1,10 +1,10 @@
 from langchain_community.tools import DuckDuckGoSearchRun
 
 from langflow.custom import Component
+from langflow.helpers.data import data_to_dataframe
 from langflow.inputs import IntInput, MessageTextInput
 from langflow.io import Output
-from langflow.schema import Data
-from langflow.schema.message import Message
+from langflow.schema import Data, DataFrame
 
 
 class DuckDuckGoSearchComponent(Component):
@@ -42,16 +42,15 @@ class DuckDuckGoSearchComponent(Component):
     ]
 
     outputs = [
-        Output(display_name="Data", name="data", method="fetch_content"),
-        Output(display_name="Text", name="text", method="fetch_content_text"),
+        Output(display_name="DataFrame", name="dataframe", method="fetch_content_dataframe"),
     ]
 
     def _build_wrapper(self) -> DuckDuckGoSearchRun:
         """Build the DuckDuckGo search wrapper."""
         return DuckDuckGoSearchRun()
 
-    def run_model(self) -> list[Data]:
-        return self.fetch_content()
+    def run_model(self) -> DataFrame:
+        return self.fetch_content_dataframe()
 
     def fetch_content(self) -> list[Data]:
         """Execute the search and return results as Data objects."""
@@ -83,9 +82,11 @@ class DuckDuckGoSearchComponent(Component):
             self.status = data_results
             return data_results
 
-    def fetch_content_text(self) -> Message:
-        """Return search results as a single text message."""
+    def fetch_content_dataframe(self) -> DataFrame:
+        """Convert the search results to a DataFrame.
+
+        Returns:
+            DataFrame: A DataFrame containing the search results.
+        """
         data = self.fetch_content()
-        result_string = "\n".join(item.text for item in data)
-        self.status = result_string
-        return Message(text=result_string)
+        return data_to_dataframe(data)

src/backend/base/langflow/components/search/glean_search_api.py

@@ -9,6 +9,7 @@ from pydantic.v1 import Field
 
 from langflow.base.langchain_utilities.model import LCToolComponent
 from langflow.field_typing import Tool
+from langflow.helpers.data import data_to_dataframe
 from langflow.inputs import IntInput, MultilineInput, NestedDictInput, SecretStrInput, StrInput
 from langflow.io import Output
 from langflow.schema import Data, DataFrame
@@ -104,8 +105,7 @@ class GleanSearchAPIComponent(LCToolComponent):
     icon: str = "Glean"
 
     outputs = [
-        Output(display_name="Data", name="data", method="run_model"),
-        Output(display_name="DataFrame", name="dataframe", method="as_dataframe"),
+        Output(display_name="DataFrame", name="dataframe", method="fetch_content_dataframe"),
     ]
 
     inputs = [
@@ -133,7 +133,10 @@ class GleanSearchAPIComponent(LCToolComponent):
 
         return tool
 
-    def run_model(self) -> list[Data]:
+    def run_model(self) -> DataFrame:
+        return self.fetch_content_dataframe()
+
+    def fetch_content(self) -> list[Data]:
         tool = self.build_tool()
 
         results = tool.run(
@@ -160,13 +163,11 @@ class GleanSearchAPIComponent(LCToolComponent):
             glean_access_token=glean_access_token,
         )
 
-    def as_dataframe(self) -> DataFrame:
+    def fetch_content_dataframe(self) -> DataFrame:
         """Convert the Glean search results to a DataFrame.
 
         Returns:
             DataFrame: A DataFrame containing the search results.
         """
-        data = self.run_model()
-        if isinstance(data, list):
-            return DataFrame(data=[d.data for d in data])
-        return DataFrame(data=[data.data])
+        data = self.fetch_content()
+        return data_to_dataframe(data)

src/backend/base/langflow/components/search/search.py

@@ -3,10 +3,10 @@ from typing import Any
 from langchain_community.utilities.searchapi import SearchApiAPIWrapper
 
 from langflow.custom import Component
+from langflow.helpers.data import data_to_dataframe
 from langflow.inputs import DictInput, DropdownInput, IntInput, MultilineInput, SecretStrInput
 from langflow.io import Output
 from langflow.schema import Data, DataFrame
-from langflow.schema.message import Message
 
 
 class SearchComponent(Component):
@@ -29,16 +29,14 @@ class SearchComponent(Component):
     ]
 
     outputs = [
-        Output(display_name="Data", name="data", method="fetch_content"),
-        Output(display_name="Text", name="text", method="fetch_content_text"),
-        Output(display_name="DataFrame", name="dataframe", method="as_dataframe"),
+        Output(display_name="DataFrame", name="dataframe", method="fetch_content_dataframe"),
     ]
 
     def _build_wrapper(self):
         return SearchApiAPIWrapper(engine=self.engine, searchapi_api_key=self.api_key)
 
-    def run_model(self) -> list[Data]:
-        return self.fetch_content()
+    def run_model(self) -> DataFrame:
+        return self.fetch_content_dataframe()
 
     def fetch_content(self) -> list[Data]:
         wrapper = self._build_wrapper()
@@ -71,19 +69,11 @@ class SearchComponent(Component):
         self.status = results
         return results
 
-    def fetch_content_text(self) -> Message:
-        data = self.fetch_content()
-        result_string = ""
-        for item in data:
-            result_string += item.text + "\n"
-        self.status = result_string
-        return Message(text=result_string)
-
-    def as_dataframe(self) -> DataFrame:
+    def fetch_content_dataframe(self) -> DataFrame:
         """Convert the search results to a DataFrame.
 
         Returns:
             DataFrame: A DataFrame containing the search results.
         """
         data = self.fetch_content()
-        return DataFrame(data)
+        return data_to_dataframe(data)

src/backend/base/langflow/components/search/wikidata.py

@@ -3,10 +3,9 @@ from httpx import HTTPError
 from langchain_core.tools import ToolException
 
 from langflow.custom import Component
-from langflow.helpers.data import data_to_text
+from langflow.helpers.data import data_to_dataframe
 from langflow.io import MultilineInput, Output
-from langflow.schema import Data
-from langflow.schema.message import Message
+from langflow.schema import Data, DataFrame
 
 
 class WikidataComponent(Component):
@@ -25,10 +24,12 @@ class WikidataComponent(Component):
     ]
 
     outputs = [
-        Output(display_name="Data", name="data", method="fetch_content"),
-        Output(display_name="Message", name="text", method="fetch_content_text"),
+        Output(display_name="DataFrame", name="dataframe", method="fetch_content_dataframe"),
     ]
 
+    def run_model(self) -> DataFrame:
+        return self.fetch_content_dataframe()
+
     def fetch_content(self) -> list[Data]:
         try:
             # Define request parameters for Wikidata API
@@ -79,8 +80,6 @@ class WikidataComponent(Component):
         else:
             return data
 
-    def fetch_content_text(self) -> Message:
+    def fetch_content_dataframe(self) -> DataFrame:
         data = self.fetch_content()
-        result_string = data_to_text("{text}", data)
-        self.status = result_string
-        return Message(text=result_string)
+        return data_to_dataframe(data)

src/backend/base/langflow/components/search/wikipedia.py

@@ -1,10 +1,10 @@
 from langchain_community.utilities.wikipedia import WikipediaAPIWrapper
 
 from langflow.custom import Component
+from langflow.helpers.data import data_to_dataframe
 from langflow.inputs import BoolInput, IntInput, MessageTextInput, MultilineInput
 from langflow.io import Output
 from langflow.schema import Data, DataFrame
-from langflow.schema.message import Message
 
 
 class WikipediaComponent(Component):
@@ -27,24 +27,11 @@ class WikipediaComponent(Component):
     ]
 
     outputs = [
-        Output(display_name="Data", name="data", method="fetch_content"),
-        Output(display_name="DataFrame", name="dataframe", method="as_dataframe"),
+        Output(display_name="DataFrame", name="dataframe", method="fetch_content_dataframe"),
     ]
 
-    def fetch_content(self) -> list[Data]:
-        wrapper = self._build_wrapper()
-        docs = wrapper.load(self.input_value)
-        data = [Data.from_document(doc) for doc in docs]
-        self.status = data
-        return data
-
-    def fetch_content_text(self) -> Message:
-        data = self.fetch_content()
-        result_string = ""
-        for item in data:
-            result_string += item.text + "\n"
-        self.status = result_string
-        return Message(text=result_string)
+    def run_model(self) -> DataFrame:
+        return self.fetch_content_dataframe()
 
     def _build_wrapper(self) -> WikipediaAPIWrapper:
         return WikipediaAPIWrapper(
@@ -54,11 +41,13 @@ class WikipediaComponent(Component):
             doc_content_chars_max=self.doc_content_chars_max,
         )
 
-    def as_dataframe(self) -> DataFrame:
-        """Convert the Wikipedia results to a DataFrame.
+    def fetch_content(self) -> list[Data]:
+        wrapper = self._build_wrapper()
+        docs = wrapper.load(self.input_value)
+        data = [Data.from_document(doc) for doc in docs]
+        self.status = data
+        return data
 
-        Returns:
-            DataFrame: A DataFrame containing the Wikipedia results.
-        """
+    def fetch_content_dataframe(self) -> DataFrame:
         data = self.fetch_content()
-        return DataFrame(data)
+        return data_to_dataframe(data)

src/backend/base/langflow/components/search/wolfram_alpha_api.py

@@ -2,6 +2,7 @@ from langchain_community.utilities.wolfram_alpha import WolframAlphaAPIWrapper
 
 from langflow.base.langchain_utilities.model import LCToolComponent
 from langflow.field_typing import Tool
+from langflow.helpers.data import data_to_dataframe
 from langflow.inputs import MultilineInput, SecretStrInput
 from langflow.io import Output
 from langflow.schema import Data, DataFrame
@@ -14,8 +15,7 @@ topics, delivering structured responses."""
     name = "WolframAlphaAPI"
 
     outputs = [
-        Output(display_name="Data", name="data", method="run_model"),
-        Output(display_name="DataFrame", name="dataframe", method="as_dataframe"),
+        Output(display_name="DataFrame", name="dataframe", method="fetch_content_dataframe"),
     ]
 
     inputs = [
@@ -27,12 +27,8 @@ topics, delivering structured responses."""
 
     icon = "WolframAlphaAPI"
 
-    def run_model(self) -> list[Data]:
-        wrapper = self._build_wrapper()
-        result_str = wrapper.run(self.input_value)
-        data = [Data(text=result_str)]
-        self.status = data
-        return data
+    def run_model(self) -> DataFrame:
+        return self.fetch_content_dataframe()
 
     def build_tool(self) -> Tool:
         wrapper = self._build_wrapper()
@@ -41,11 +37,18 @@ topics, delivering structured responses."""
     def _build_wrapper(self) -> WolframAlphaAPIWrapper:
         return WolframAlphaAPIWrapper(wolfram_alpha_appid=self.app_id)
 
-    def as_dataframe(self) -> DataFrame:
+    def fetch_content(self) -> list[Data]:
+        wrapper = self._build_wrapper()
+        result_str = wrapper.run(self.input_value)
+        data = [Data(text=result_str)]
+        self.status = data
+        return data
+
+    def fetch_content_dataframe(self) -> DataFrame:
         """Convert the Wolfram Alpha results to a DataFrame.
 
         Returns:
             DataFrame: A DataFrame containing the query results.
         """
-        data = self.run_model()
-        return DataFrame(data)
+        data = self.fetch_content()
+        return data_to_dataframe(data)

src/backend/base/langflow/components/search/yahoo.py

@@ -8,10 +8,10 @@ from loguru import logger
 from pydantic import BaseModel, Field
 
 from langflow.custom import Component
+from langflow.helpers.data import data_to_dataframe
 from langflow.inputs import DropdownInput, IntInput, MessageTextInput
 from langflow.io import Output
 from langflow.schema import Data, DataFrame
-from langflow.schema.message import Message
 
 
 class YahooFinanceMethod(Enum):
@@ -77,21 +77,11 @@ to access financial data and market information from Yahoo Finance."""
     ]
 
     outputs = [
-        Output(display_name="Data", name="data", method="fetch_content"),
-        Output(display_name="Text", name="text", method="fetch_content_text"),
-        Output(display_name="DataFrame", name="dataframe", method="as_dataframe"),
+        Output(display_name="DataFrame", name="dataframe", method="fetch_content_dataframe"),
     ]
 
-    def run_model(self) -> list[Data]:
-        return self.fetch_content()
-
-    def fetch_content_text(self) -> Message:
-        data = self.fetch_content()
-        result_string = ""
-        for item in data:
-            result_string += item.text + "\n"
-        self.status = result_string
-        return Message(text=result_string)
+    def run_model(self) -> DataFrame:
+        return self.fetch_content_dataframe()
 
     def _fetch_yfinance_data(self, ticker: yf.Ticker, method: YahooFinanceMethod, num_news: int | None) -> str:
         try:
@@ -142,11 +132,6 @@ to access financial data and market information from Yahoo Finance."""
 
         return data_list
 
-    def as_dataframe(self) -> DataFrame:
-        """Convert the Yahoo search results to a DataFrame.
-
-        Returns:
-            DataFrame: A DataFrame containing the search results.
-        """
+    def fetch_content_dataframe(self) -> DataFrame:
         data = self.fetch_content()
-        return DataFrame(data)
+        return data_to_dataframe(data)

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

@@ -2,69 +2,48 @@ import warnings
 
 from langchain_core._api.deprecation import LangChainDeprecationWarning
 
-from .arxiv import ArXivComponent
-from .bing_search_api import BingSearchAPIComponent
 from .calculator import CalculatorToolComponent
 from .calculator_core import CalculatorComponent
-from .duck_duck_go_search_run import DuckDuckGoSearchComponent
-from .exa_search import ExaSearchToolkit
-from .glean_search_api import GleanSearchAPIComponent
 from .google_search_api import GoogleSearchAPIComponent
-from .google_search_api_core import GoogleSearchAPICore
 from .google_serper_api import GoogleSerperAPIComponent
-from .google_serper_api_core import GoogleSerperAPICore
 from .mcp_component import MCPToolsComponent
 from .python_code_structured_tool import PythonCodeStructuredTool
 from .python_repl import PythonREPLToolComponent
 from .python_repl_core import PythonREPLComponent
-from .search import SearchComponent
 from .search_api import SearchAPIComponent
 from .searxng import SearXNGToolComponent
-from .serp import SerpComponent
 from .serp_api import SerpAPIComponent
 from .tavily_extract import TavilyExtractComponent
 from .tavily_search import TavilySearchComponent
 from .tavily_search_tool import TavilySearchToolComponent
-from .wikidata import WikidataComponent
 from .wikidata_api import WikidataAPIComponent
-from .wikipedia import WikipediaComponent
 from .wikipedia_api import WikipediaAPIComponent
-from .wolfram_alpha_api import WolframAlphaAPIComponent
-from .yahoo import YfinanceComponent
 from .yahoo_finance import YfinanceToolComponent
 
 with warnings.catch_warnings():
     warnings.simplefilter("ignore", LangChainDeprecationWarning)
 
 __all__ = [
-    "ArXivComponent",
-    "BingSearchAPIComponent",
+    "AstraDBCQLToolComponent",
+    "AstraDBToolComponent",
     "CalculatorComponent",
     "CalculatorToolComponent",
     "DuckDuckGoSearchComponent",
     "ExaSearchToolkit",
     "GleanSearchAPIComponent",
     "GoogleSearchAPIComponent",
-    "GoogleSearchAPICore",
     "GoogleSerperAPIComponent",
-    "GoogleSerperAPICore",
     "MCPToolsComponent",
     "PythonCodeStructuredTool",
     "PythonREPLComponent",
     "PythonREPLToolComponent",
     "SearXNGToolComponent",
     "SearchAPIComponent",
-    "SearchComponent",
     "SerpAPIComponent",
-    "SerpComponent",
     "TavilyExtractComponent",
     "TavilySearchComponent",
     "TavilySearchToolComponent",
     "WikidataAPIComponent",
-    "WikidataComponent",
     "WikipediaAPIComponent",
-    "WikipediaComponent",
-    "WolframAlphaAPIComponent",
-    "YfinanceComponent",
     "YfinanceToolComponent",
 ]

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

@@ -2,7 +2,7 @@ from collections import defaultdict
 
 from langchain_core.documents import Document
 
-from langflow.schema import Data
+from langflow.schema import Data, DataFrame
 from langflow.schema.message import Message
 
 
@@ -139,3 +139,17 @@ def messages_to_text(template: str, messages: Message | list[Message]) -> str:
 
     formated_messages = [template.format(data=message.model_dump(), **message.model_dump()) for message in messages_]
     return "\n".join(formated_messages)
+
+
+def data_to_dataframe(data: Data | list[Data]) -> DataFrame:
+    """Converts a Data object or a list of Data objects to a DataFrame.
+
+    Args:
+        data (Data | list[Data]): The Data object or list of Data objects to convert.
+
+    Returns:
+        DataFrame: The converted DataFrame.
+    """
+    if isinstance(data, Data):
+        return DataFrame([data.data])
+    return DataFrame(data=[d.data for d in data])

src/backend/base/langflow/initial_setup/starter_projects/Travel Planning Agents.json

@@ -1462,7 +1462,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from typing import Any\n\nfrom langchain_community.utilities.searchapi import SearchApiAPIWrapper\n\nfrom langflow.custom import Component\nfrom langflow.inputs import DictInput, DropdownInput, IntInput, MultilineInput, SecretStrInput\nfrom langflow.io import Output\nfrom langflow.schema import Data, DataFrame\nfrom langflow.schema.message import Message\n\n\nclass SearchComponent(Component):\n    display_name: str = \"Search API\"\n    description: str = \"Call the searchapi.io API with result limiting\"\n    documentation: str = \"https://www.searchapi.io/docs/google\"\n    icon = \"SearchAPI\"\n\n    inputs = [\n        DropdownInput(name=\"engine\", display_name=\"Engine\", value=\"google\", options=[\"google\", \"bing\", \"duckduckgo\"]),\n        SecretStrInput(name=\"api_key\", display_name=\"SearchAPI API Key\", required=True),\n        MultilineInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            tool_mode=True,\n        ),\n        DictInput(name=\"search_params\", display_name=\"Search parameters\", advanced=True, is_list=True),\n        IntInput(name=\"max_results\", display_name=\"Max Results\", value=5, advanced=True),\n        IntInput(name=\"max_snippet_length\", display_name=\"Max Snippet Length\", value=100, advanced=True),\n    ]\n\n    outputs = [\n        Output(display_name=\"Data\", name=\"data\", method=\"fetch_content\"),\n        Output(display_name=\"Text\", name=\"text\", method=\"fetch_content_text\"),\n        Output(display_name=\"DataFrame\", name=\"dataframe\", method=\"as_dataframe\"),\n    ]\n\n    def _build_wrapper(self):\n        return SearchApiAPIWrapper(engine=self.engine, searchapi_api_key=self.api_key)\n\n    def run_model(self) -> list[Data]:\n        return self.fetch_content()\n\n    def fetch_content(self) -> list[Data]:\n        wrapper = self._build_wrapper()\n\n        def search_func(\n            query: str, params: dict[str, Any] | None = None, max_results: int = 5, max_snippet_length: int = 100\n        ) -> list[Data]:\n            params = params or {}\n            full_results = wrapper.results(query=query, **params)\n            organic_results = full_results.get(\"organic_results\", [])[:max_results]\n\n            return [\n                Data(\n                    text=result.get(\"snippet\", \"\"),\n                    data={\n                        \"title\": result.get(\"title\", \"\")[:max_snippet_length],\n                        \"link\": result.get(\"link\", \"\"),\n                        \"snippet\": result.get(\"snippet\", \"\")[:max_snippet_length],\n                    },\n                )\n                for result in organic_results\n            ]\n\n        results = search_func(\n            self.input_value,\n            self.search_params or {},\n            self.max_results,\n            self.max_snippet_length,\n        )\n        self.status = results\n        return results\n\n    def fetch_content_text(self) -> Message:\n        data = self.fetch_content()\n        result_string = \"\"\n        for item in data:\n            result_string += item.text + \"\\n\"\n        self.status = result_string\n        return Message(text=result_string)\n\n    def as_dataframe(self) -> DataFrame:\n        \"\"\"Convert the search results to a DataFrame.\n\n        Returns:\n            DataFrame: A DataFrame containing the search results.\n        \"\"\"\n        data = self.fetch_content()\n        return DataFrame(data)\n"
+                "value": "from typing import Any\n\nfrom langchain_community.utilities.searchapi import SearchApiAPIWrapper\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_dataframe\nfrom langflow.inputs import DictInput, DropdownInput, IntInput, MultilineInput, SecretStrInput\nfrom langflow.io import Output\nfrom langflow.schema import Data, DataFrame\n\n\nclass SearchComponent(Component):\n    display_name: str = \"Search API\"\n    description: str = \"Call the searchapi.io API with result limiting\"\n    documentation: str = \"https://www.searchapi.io/docs/google\"\n    icon = \"SearchAPI\"\n\n    inputs = [\n        DropdownInput(name=\"engine\", display_name=\"Engine\", value=\"google\", options=[\"google\", \"bing\", \"duckduckgo\"]),\n        SecretStrInput(name=\"api_key\", display_name=\"SearchAPI API Key\", required=True),\n        MultilineInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            tool_mode=True,\n        ),\n        DictInput(name=\"search_params\", display_name=\"Search parameters\", advanced=True, is_list=True),\n        IntInput(name=\"max_results\", display_name=\"Max Results\", value=5, advanced=True),\n        IntInput(name=\"max_snippet_length\", display_name=\"Max Snippet Length\", value=100, advanced=True),\n    ]\n\n    outputs = [\n        Output(display_name=\"DataFrame\", name=\"dataframe\", method=\"fetch_content_dataframe\"),\n    ]\n\n    def _build_wrapper(self):\n        return SearchApiAPIWrapper(engine=self.engine, searchapi_api_key=self.api_key)\n\n    def run_model(self) -> DataFrame:\n        return self.fetch_content_dataframe()\n\n    def fetch_content(self) -> list[Data]:\n        wrapper = self._build_wrapper()\n\n        def search_func(\n            query: str, params: dict[str, Any] | None = None, max_results: int = 5, max_snippet_length: int = 100\n        ) -> list[Data]:\n            params = params or {}\n            full_results = wrapper.results(query=query, **params)\n            organic_results = full_results.get(\"organic_results\", [])[:max_results]\n\n            return [\n                Data(\n                    text=result.get(\"snippet\", \"\"),\n                    data={\n                        \"title\": result.get(\"title\", \"\")[:max_snippet_length],\n                        \"link\": result.get(\"link\", \"\"),\n                        \"snippet\": result.get(\"snippet\", \"\")[:max_snippet_length],\n                    },\n                )\n                for result in organic_results\n            ]\n\n        results = search_func(\n            self.input_value,\n            self.search_params or {},\n            self.max_results,\n            self.max_snippet_length,\n        )\n        self.status = results\n        return results\n\n    def fetch_content_dataframe(self) -> DataFrame:\n        \"\"\"Convert the search results to a DataFrame.\n\n        Returns:\n            DataFrame: A DataFrame containing the search results.\n        \"\"\"\n        data = self.fetch_content()\n        return data_to_dataframe(data)\n"
               },
               "engine": {
                 "_input_type": "DropdownInput",

src/backend/tests/unit/components/data/test_news_search.py

@@ -50,21 +50,21 @@ class TestNewsSearchComponent(ComponentTestBaseWithoutClient):
             component = NewsSearchComponent(query="OpenAI")
             result = component.search_news()
             assert isinstance(result, DataFrame)
-            df = result
-            assert len(df) == 2
-            assert list(df.columns) == ["title", "link", "published", "summary"]
-            assert df.iloc[0]["title"] == "Test News 1"
-            assert df.iloc[1]["title"] == "Test News 2"
+            news_results_df = result
+            assert len(news_results_df) == 2
+            assert list(news_results_df.columns) == ["title", "link", "published", "summary"]
+            assert news_results_df.iloc[0]["title"] == "Test News 1"
+            assert news_results_df.iloc[1]["title"] == "Test News 2"
 
     def test_news_search_error(self):
         with patch("requests.get", side_effect=requests.RequestException("Network error")):
             component = NewsSearchComponent(query="OpenAI")
             result = component.search_news()
             assert isinstance(result, DataFrame)
-            df = result
-            assert len(df) == 1
-            assert df.iloc[0]["title"] == "Error"
-            assert "Network error" in df.iloc[0]["summary"]
+            news_results_df = result
+            assert len(news_results_df) == 1
+            assert news_results_df.iloc[0]["title"] == "Error"
+            assert "Network error" in news_results_df.iloc[0]["summary"]
 
     def test_empty_news_results(self):
         # Mock empty RSS feed
@@ -83,6 +83,6 @@ class TestNewsSearchComponent(ComponentTestBaseWithoutClient):
             component = NewsSearchComponent(query="OpenAI")
             result = component.search_news()
             assert isinstance(result, DataFrame)
-            df = result
-            assert len(df) == 1
-            assert df.iloc[0]["title"] == "No articles found"
+            news_results_df = result
+            assert len(news_results_df) == 1
+            assert news_results_df.iloc[0]["title"] == "No articles found"

src/backend/tests/unit/components/search/test_arxiv_component.py

@@ -8,7 +8,7 @@ from tests.base import ComponentTestBaseWithClient
 class TestArXivComponent(ComponentTestBaseWithClient):
     def test_component_versions(self, default_kwargs, file_names_mapping):
         """Test component compatibility across versions."""
-        from langflow.components.tools.arxiv import ArXivComponent
+        from langflow.components.search.arxiv import ArXivComponent
 
         # Test current version
         component = ArXivComponent(**default_kwargs)
@@ -31,7 +31,7 @@ class TestArXivComponent(ComponentTestBaseWithClient):
 
     @pytest.fixture
     def component_class(self):
-        from langflow.components.tools.arxiv import ArXivComponent
+        from langflow.components.search.arxiv import ArXivComponent
 
         return ArXivComponent
 

src/backend/tests/unit/components/search/test_google_search_api.py

@@ -2,7 +2,7 @@ from unittest.mock import patch
 
 import pandas as pd
 import pytest
-from langflow.components.tools import GoogleSearchAPICore
+from langflow.components.search import GoogleSearchAPICore
 from langflow.schema import DataFrame
 
 from tests.base import ComponentTestBaseWithoutClient

src/backend/tests/unit/components/search/test_google_serper_api_core.py

@@ -1,7 +1,7 @@
 from unittest.mock import MagicMock, patch
 
 import pytest
-from langflow.components.tools import GoogleSerperAPICore
+from langflow.components.search import GoogleSerperAPICore
 from langflow.schema import DataFrame
 
 

src/backend/tests/unit/components/search/test_wikidata_api.py

@@ -3,11 +3,9 @@ from unittest.mock import MagicMock, patch
 import httpx
 import pytest
 from langchain_core.tools import ToolException
-from langflow.components.tools import WikidataComponent
+from langflow.components.search import WikidataComponent
 from langflow.custom import Component
 from langflow.custom.utils import build_custom_component_template
-from langflow.schema import Data
-from langflow.schema.message import Message
 
 # Import the base test class
 from tests.base import ComponentTestBaseWithoutClient
@@ -102,18 +100,3 @@ class TestWikidataComponent(ComponentTestBaseWithoutClient):
 
         with pytest.raises(ToolException):
             component.fetch_content()
-
-    def test_fetch_content_text(self, component_class):
-        component = component_class()
-        component.fetch_content = MagicMock(
-            return_value=[
-                Data(text="First result", data={"label": "Label 1"}),
-                Data(text="Second result", data={"label": "Label 2"}),
-            ]
-        )
-
-        result = component.fetch_content_text()
-
-        assert isinstance(result, Message)
-        assert "First result" in result.text
-        assert "Second result" in result.text

src/backend/tests/unit/components/search/test_wikipedia_api.py

@@ -1,11 +1,9 @@
 from unittest.mock import MagicMock
 
 import pytest
-from langflow.components.tools import WikipediaComponent
+from langflow.components.search import WikipediaComponent
 from langflow.custom import Component
 from langflow.custom.utils import build_custom_component_template
-from langflow.schema import Data
-from langflow.schema.message import Message
 
 # Import the base test class
 from tests.base import ComponentTestBaseWithoutClient
@@ -83,15 +81,6 @@ class TestWikipediaComponent(ComponentTestBaseWithoutClient):
         assert len(result) == 1
         assert result[0].text == "Test content"
 
-    def test_fetch_content_text(self, component_class):
-        component = component_class()
-        component.fetch_content = MagicMock(return_value=[Data(text="First result"), Data(text="Second result")])
-
-        result = component.fetch_content_text()
-
-        assert isinstance(result, Message)
-        assert result.text == "First result\nSecond result\n"
-
     def test_wikipedia_error_handling(self, component_class):
         component = component_class()
         # Mock _build_wrapper to raise exception

src/backend/tests/unit/components/search/test_yfinance_tool.py

@@ -2,8 +2,7 @@ from unittest.mock import MagicMock, patch
 
 import pytest
 from langchain_core.tools import ToolException
-from langflow.components.tools import YfinanceComponent
-from langflow.components.tools.yahoo import YahooFinanceMethod
+from langflow.components.search.yahoo import YahooFinanceMethod, YfinanceComponent
 from langflow.custom.utils import build_custom_component_template
 from langflow.schema import Data
 
@@ -38,7 +37,7 @@ class TestYfinanceComponent:
         for input_name in expected_inputs:
             assert input_name in input_names
 
-    @patch("langflow.components.tools.yahoo.yf.Ticker")
+    @patch("langflow.components.search.yahoo.yf.Ticker")
     def test_fetch_info(self, mock_ticker, component_class, default_kwargs):
         component = component_class(**default_kwargs)
 
@@ -53,7 +52,7 @@ class TestYfinanceComponent:
         assert len(result) == 1
         assert "Apple Inc." in result[0].text
 
-    @patch("langflow.components.tools.yahoo.yf.Ticker")
+    @patch("langflow.components.search.yahoo.yf.Ticker")
     def test_fetch_news(self, mock_ticker, component_class):
         component = component_class(symbol="AAPL", method=YahooFinanceMethod.GET_NEWS, num_news=2)
 

src/backend/tests/unit/components/tools/test_serp_api.py

@@ -2,7 +2,7 @@ from unittest.mock import MagicMock, patch
 
 import pytest
 from langchain_core.tools import ToolException
-from langflow.components.tools import SerpComponent
+from langflow.components.search import SerpComponent
 from langflow.custom import Component
 from langflow.custom.utils import build_custom_component_template
 from langflow.schema import Data
@@ -34,7 +34,7 @@ def test_serpapi_template():
         assert input_name in input_names
 
 
-@patch("langflow.components.tools.serp.SerpAPIWrapper")
+@patch("langflow.components.search.serp.SerpAPIWrapper")
 def test_fetch_content(mock_serpapi_wrapper):
     component = SerpComponent()
     component.serpapi_api_key = "test-key"
@@ -81,7 +81,7 @@ def test_error_handling():
     component.serpapi_api_key = "test-key"
     component.input_value = "test query"
 
-    with patch("langflow.components.tools.serp.SerpAPIWrapper") as mock_serpapi:
+    with patch("langflow.components.search.serp.SerpAPIWrapper") as mock_serpapi:
         mock_instance = MagicMock()
         mock_serpapi.return_value = mock_instance
         mock_instance.results.side_effect = Exception("API Error")

src/backend/tests/unit/test_chat_endpoint.py

@@ -165,70 +165,84 @@ async def test_build_flow_polling(client, json_memory_chatbot_no_llm, logged_in_
             self.max_total_events = 50  # Limit to prevent infinite loops
             self.max_empty_polls = 10  # Maximum number of empty polls before giving up
             self.poll_timeout = 3.0  # Timeout for each polling request
+            self._closed = False
 
         async def aiter_lines(self):
+            if self._closed:
+                return
+
             try:
                 empty_polls = 0
                 total_events = 0
                 end_event_found = False
 
                 while (
-                    empty_polls < self.max_empty_polls and total_events < self.max_total_events and not end_event_found
+                    empty_polls < self.max_empty_polls
+                    and total_events < self.max_total_events
+                    and not end_event_found
+                    and not self._closed
                 ):
                     # Add Accept header for NDJSON
                     headers = {**self.headers, "Accept": "application/x-ndjson"}
 
-                    # Set a timeout for the request
-                    response = await asyncio.wait_for(
-                        self.client.get(
-                            f"api/v1/build/{self.job_id}/events?event_delivery=polling",
-                            headers=headers,
-                        ),
-                        timeout=self.poll_timeout,
-                    )
+                    try:
+                        # Set a timeout for the request
+                        response = await asyncio.wait_for(
+                            self.client.get(
+                                f"api/v1/build/{self.job_id}/events?event_delivery=polling",
+                                headers=headers,
+                            ),
+                            timeout=self.poll_timeout,
+                        )
 
-                    assert response.status_code == codes.OK
+                        if response.status_code != codes.OK:
+                            break
 
-                    # Get the NDJSON response as text
-                    text = response.text
+                        # Get the NDJSON response as text
+                        text = response.text
 
-                    # Skip if response is empty
-                    if not text.strip():
-                        empty_polls += 1
-                        await asyncio.sleep(0.1)
-                        continue
-
-                    # Reset empty polls counter since we got data
-                    empty_polls = 0
-
-                    # Process each line as an individual JSON object
-                    line_count = 0
-                    for line in text.splitlines():
-                        if not line.strip():
+                        # Skip if response is empty
+                        if not text.strip():
+                            empty_polls += 1
+                            await asyncio.sleep(0.1)
                             continue
 
-                        line_count += 1
-                        total_events += 1
+                        # Reset empty polls counter since we got data
+                        empty_polls = 0
 
-                        # Check for end event with multiple possible formats
-                        if '"event":"end"' in line or '"event": "end"' in line:
-                            end_event_found = True
+                        # Process each line as an individual JSON object
+                        line_count = 0
+                        for line in text.splitlines():
+                            if not line.strip():
+                                continue
 
-                        # Validate it's proper JSON before yielding
-                        try:
-                            json.loads(line)  # Test parse to ensure it's valid JSON
-                            yield line
-                        except json.JSONDecodeError as e:
-                            logger.debug(f"WARNING: Skipping invalid JSON: {line}")
-                            logger.debug(f"Error: {e}")
-                            # Don't yield invalid JSON, but continue processing other lines
+                            line_count += 1
+                            total_events += 1
 
-                    # If we had no events in this batch, count as empty poll
-                    if line_count == 0:
+                            # Check for end event with multiple possible formats
+                            if '"event":"end"' in line or '"event": "end"' in line:
+                                end_event_found = True
+
+                            # Validate it's proper JSON before yielding
+                            try:
+                                json.loads(line)  # Test parse to ensure it's valid JSON
+                                yield line
+                            except json.JSONDecodeError as e:
+                                logger.debug(f"WARNING: Skipping invalid JSON: {line}")
+                                logger.debug(f"Error: {e}")
+                                # Don't yield invalid JSON, but continue processing other lines
+
+                        # If we had no events in this batch, count as empty poll
+                        if line_count == 0:
+                            empty_polls += 1
+
+                        # Add a small delay to prevent tight polling
+                        await asyncio.sleep(0.1)
+
+                    except asyncio.TimeoutError:
+                        logger.debug(f"WARNING: Polling request timed out after {self.poll_timeout}s")
                         empty_polls += 1
-
-                    # Add a small delay to prevent tight polling
-                    await asyncio.sleep(0.1)
+                        continue
 
                 # If we hit the limit without finding the end event, log a warning
                 if total_events >= self.max_total_events:
@@ -241,10 +255,14 @@ async def test_build_flow_polling(client, json_memory_chatbot_no_llm, logged_in_
                         f"WARNING: Reached maximum empty polls ({self.max_empty_polls}) without finding end event"
                     )
 
-            except asyncio.TimeoutError as e:
-                logger.debug(f"ERROR: Polling request timed out after {self.poll_timeout}s")
-                msg = "Build event polling timed out."
-                raise TimeoutError(msg) from e
+            except Exception as e:
+                logger.debug(f"ERROR: Unexpected error during polling: {e!s}")
+                raise
+            finally:
+                self._closed = True
+
+        def close(self):
+            self._closed = True
 
     polling_response = PollingResponse(client, job_id, logged_in_headers)
 

src/frontend/src/utils/styleUtils.ts

@@ -271,6 +271,7 @@ export const SIDEBAR_BUNDLES = [
     name: "homeassistant",
     icon: "HomeAssistant",
   },
+  { display_name: "Search", name: "search", icon: "Search" },
 ];
 
 export const categoryIcons: Record<string, string> = {

src/frontend/tests/core/features/filterSidebar.spec.ts

@@ -125,7 +125,6 @@ test(
     await expect(page.getByTestId("dataAPI Request")).toBeVisible();
     await expect(page.getByTestId("helpersMessage History")).toBeVisible();
     await expect(page.getByTestId("vectorstoresAstra DB")).toBeVisible();
-    await expect(page.getByTestId("toolsSearch API")).toBeVisible();
     await expect(page.getByTestId("logicSub Flow [Deprecated]")).toBeVisible();
 
     await page.getByTestId("sidebar-options-trigger").click();
@@ -137,19 +136,16 @@ test(
     await expect(page.getByTestId("logicSub Flow [Deprecated]")).toBeVisible();
 
     await expect(page.getByTestId("processingSplit Text")).toBeVisible();
-    await expect(page.getByTestId("toolsSearch API")).toBeVisible();
 
     await page.getByTestId("icon-X").first().click();
 
     await expect(page.getByTestId("dataAPI Request")).not.toBeVisible();
     await expect(page.getByTestId("helpersMessage History")).not.toBeVisible();
     await expect(page.getByTestId("vectorstoresAstra DB")).not.toBeVisible();
-    await expect(page.getByTestId("toolsSearch API")).not.toBeVisible();
     await expect(
       page.getByTestId("logicSub Flow [Deprecated]"),
     ).not.toBeVisible();
 
     await expect(page.getByTestId("processingSplit Text")).not.toBeVisible();
-    await expect(page.getByTestId("toolsSearch API")).not.toBeVisible();
   },
 );

src/frontend/tests/extended/integrations/duckduckgo.spec.ts

@@ -11,12 +11,12 @@ test(
     await page.getByTestId("sidebar-search-input").click();
     await page.getByTestId("sidebar-search-input").fill("duck");
 
-    await page.waitForSelector('[data-testid="toolsDuckDuckGo Search"]', {
+    await page.waitForSelector('[data-testid="searchDuckDuckGo Search"]', {
       timeout: 3000,
     });
 
     await page
-      .getByTestId("toolsDuckDuckGo Search")
+      .getByTestId("searchDuckDuckGo Search")
       .hover()
       .then(async () => {
         await page
@@ -44,7 +44,7 @@ test(
         ) ?? false;
 
       await page
-        .getByTestId("output-inspection-data-duckduckgosearchcomponent")
+        .getByTestId("output-inspection-dataframe-duckduckgosearchcomponent")
         .first()
         .click();
 

src/frontend/tests/extended/regression/generalBugs-shard-11.spec.ts

@@ -49,14 +49,14 @@ test(
 
     await page.getByTestId("sidebar-search-input").click();
     await page.getByTestId("sidebar-search-input").fill("search api");
-    await page.waitForSelector('[data-testid="toolsSearch API"]', {
+    await page.waitForSelector('[data-testid="searchSearch API"]', {
       timeout: 1000,
     });
 
     await zoomOut(page, 3);
 
     await page
-      .getByTestId("toolsSearch API")
+      .getByTestId("searchSearch API")
       .dragTo(page.locator('//*[@id="react-flow-id"]'), {
         targetPosition: { x: 100, y: 100 },
       });