feat: add more search parameters to google_serper_api component (#4944)
* feat: add more search parameters to google_serper_api component * [autofix.ci] apply automated fixes * fix: change default value of query_params to None in GoogleSerperAPIComponent * [autofix.ci] apply automated fixes * fix: update query_params type to Optional * [autofix.ci] apply automated fixes * fix: move QuerySchema definition outside the Component * [autofix.ci] apply automated fixes * Update src/backend/base/langflow/components/tools/google_serper_api.py Co-authored-by: Gabriel Luiz Freitas Almeida <gabriel@langflow.org> * fix: format code for better readability in google_serper_api.py * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 2/3) --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: Gabriel Luiz Freitas Almeida <gabriel@langflow.org>
This commit is contained in:
Owein
GitHub
parent
06139ef2df
commit
2dffc5dfd3
4 changed files with 93 additions and 19 deletions
|
|
@ -1,11 +1,31 @@
|
|||
from typing import Any
|
||||
|
||||
from langchain.tools import StructuredTool
|
||||
from langchain_community.utilities.google_serper import GoogleSerperAPIWrapper
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from langflow.base.langchain_utilities.model import LCToolComponent
|
||||
from langflow.field_typing import Tool
|
||||
from langflow.inputs import IntInput, MultilineInput, SecretStrInput
|
||||
from langflow.inputs import (
|
||||
DictInput,
|
||||
DropdownInput,
|
||||
IntInput,
|
||||
MultilineInput,
|
||||
SecretStrInput,
|
||||
)
|
||||
from langflow.schema import Data
|
||||
|
||||
|
||||
class QuerySchema(BaseModel):
|
||||
query: str = Field(..., description="The query to search for.")
|
||||
query_type: str = Field(
|
||||
"search",
|
||||
description="The type of search to perform (e.g., 'news' or 'search').",
|
||||
)
|
||||
k: int = Field(4, description="The number of results to return.")
|
||||
query_params: dict[str, Any] = Field({}, description="Additional query parameters to pass to the API.")
|
||||
|
||||
|
||||
class GoogleSerperAPIComponent(LCToolComponent):
|
||||
display_name = "Google Serper API [DEPRECATED]"
|
||||
description = "Call the Serper.dev Google Search API."
|
||||
|
|
@ -15,27 +35,81 @@ class GoogleSerperAPIComponent(LCToolComponent):
|
|||
inputs = [
|
||||
SecretStrInput(name="serper_api_key", display_name="Serper API Key", required=True),
|
||||
MultilineInput(
|
||||
name="input_value",
|
||||
display_name="Input",
|
||||
name="query",
|
||||
display_name="Query",
|
||||
),
|
||||
IntInput(name="k", display_name="Number of results", value=4, required=True),
|
||||
DropdownInput(
|
||||
name="query_type",
|
||||
display_name="Query Type",
|
||||
required=False,
|
||||
options=["news", "search"],
|
||||
value="search",
|
||||
),
|
||||
DictInput(
|
||||
name="query_params",
|
||||
display_name="Query Params",
|
||||
required=False,
|
||||
value={
|
||||
"gl": "us",
|
||||
"hl": "en",
|
||||
},
|
||||
list=True,
|
||||
),
|
||||
]
|
||||
|
||||
def run_model(self) -> Data | list[Data]:
|
||||
wrapper = self._build_wrapper()
|
||||
results = wrapper.results(query=self.input_value)
|
||||
list_results = results.get("organic", [])
|
||||
data = [Data(data=result, text=result["snippet"]) for result in list_results]
|
||||
self.status = data
|
||||
return data
|
||||
wrapper = self._build_wrapper(self.k, self.query_type, self.query_params)
|
||||
results = wrapper.results(query=self.query)
|
||||
|
||||
# Adjust the extraction based on the `type`
|
||||
if self.query_type == "search":
|
||||
list_results = results.get("organic", [])
|
||||
elif self.query_type == "news":
|
||||
list_results = results.get("news", [])
|
||||
else:
|
||||
list_results = []
|
||||
|
||||
data_list = []
|
||||
for result in list_results:
|
||||
result["text"] = result.pop("snippet", "")
|
||||
data_list.append(Data(data=result))
|
||||
self.status = data_list
|
||||
return data_list
|
||||
|
||||
def build_tool(self) -> Tool:
|
||||
wrapper = self._build_wrapper()
|
||||
return Tool(
|
||||
return StructuredTool.from_function(
|
||||
name="google_search",
|
||||
description="Search Google for recent results.",
|
||||
func=wrapper.run,
|
||||
func=self._search,
|
||||
args_schema=self.QuerySchema,
|
||||
)
|
||||
|
||||
def _build_wrapper(self):
|
||||
return GoogleSerperAPIWrapper(serper_api_key=self.serper_api_key, k=self.k)
|
||||
def _build_wrapper(
|
||||
self,
|
||||
k: int = 5,
|
||||
query_type: str = "search",
|
||||
query_params: dict | None = None,
|
||||
) -> GoogleSerperAPIWrapper:
|
||||
wrapper_args = {
|
||||
"serper_api_key": self.serper_api_key,
|
||||
"k": k,
|
||||
"type": query_type,
|
||||
}
|
||||
|
||||
# Add query_params if provided
|
||||
if query_params:
|
||||
wrapper_args.update(query_params) # Merge with additional query params
|
||||
|
||||
# Dynamically pass parameters to the wrapper
|
||||
return GoogleSerperAPIWrapper(**wrapper_args)
|
||||
|
||||
def _search(
|
||||
self,
|
||||
query: str,
|
||||
k: int = 5,
|
||||
query_type: str = "search",
|
||||
query_params: dict | None = None,
|
||||
) -> dict:
|
||||
wrapper = self._build_wrapper(k, query_type, query_params)
|
||||
return wrapper.results(query=query)
|
||||
|
|
|
|||
|
|
@ -219,7 +219,7 @@
|
|||
"show": true,
|
||||
"title_case": false,
|
||||
"type": "code",
|
||||
"value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Load and retrive data from specified URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n is_list=True,\n tool_mode=True,\n placeholder=\"Enter a URL...\",\n list_add_label=\"Add URL\",\n\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output Format\",\n info=\"Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\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 ensure_url(self, string: str) -> str:\n \"\"\"Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n msg = f\"Invalid URL: {string}\"\n raise ValueError(msg)\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n\n def as_dataframe(self) -> DataFrame:\n return DataFrame(self.fetch_content())\n"
|
||||
"value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Load and retrive data from specified URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n is_list=True,\n tool_mode=True,\n placeholder=\"Enter a URL...\",\n list_add_label=\"Add URL\",\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output Format\",\n info=\"Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\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 ensure_url(self, string: str) -> str:\n \"\"\"Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n msg = f\"Invalid URL: {string}\"\n raise ValueError(msg)\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n\n def as_dataframe(self) -> DataFrame:\n return DataFrame(self.fetch_content())\n"
|
||||
},
|
||||
"format": {
|
||||
"_input_type": "DropdownInput",
|
||||
|
|
|
|||
|
|
@ -1686,7 +1686,7 @@
|
|||
"show": true,
|
||||
"title_case": false,
|
||||
"type": "code",
|
||||
"value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Load and retrive data from specified URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n is_list=True,\n tool_mode=True,\n placeholder=\"Enter a URL...\",\n list_add_label=\"Add URL\",\n\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output Format\",\n info=\"Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\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 ensure_url(self, string: str) -> str:\n \"\"\"Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n msg = f\"Invalid URL: {string}\"\n raise ValueError(msg)\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n\n def as_dataframe(self) -> DataFrame:\n return DataFrame(self.fetch_content())\n"
|
||||
"value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Load and retrive data from specified URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n is_list=True,\n tool_mode=True,\n placeholder=\"Enter a URL...\",\n list_add_label=\"Add URL\",\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output Format\",\n info=\"Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\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 ensure_url(self, string: str) -> str:\n \"\"\"Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n msg = f\"Invalid URL: {string}\"\n raise ValueError(msg)\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n\n def as_dataframe(self) -> DataFrame:\n return DataFrame(self.fetch_content())\n"
|
||||
},
|
||||
"format": {
|
||||
"_input_type": "DropdownInput",
|
||||
|
|
@ -1832,7 +1832,7 @@
|
|||
"show": true,
|
||||
"title_case": false,
|
||||
"type": "code",
|
||||
"value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Load and retrive data from specified URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n is_list=True,\n tool_mode=True,\n placeholder=\"Enter a URL...\",\n list_add_label=\"Add URL\",\n\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output Format\",\n info=\"Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\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 ensure_url(self, string: str) -> str:\n \"\"\"Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n msg = f\"Invalid URL: {string}\"\n raise ValueError(msg)\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n\n def as_dataframe(self) -> DataFrame:\n return DataFrame(self.fetch_content())\n"
|
||||
"value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Load and retrive data from specified URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n is_list=True,\n tool_mode=True,\n placeholder=\"Enter a URL...\",\n list_add_label=\"Add URL\",\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output Format\",\n info=\"Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\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 ensure_url(self, string: str) -> str:\n \"\"\"Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n msg = f\"Invalid URL: {string}\"\n raise ValueError(msg)\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n\n def as_dataframe(self) -> DataFrame:\n return DataFrame(self.fetch_content())\n"
|
||||
},
|
||||
"format": {
|
||||
"_input_type": "DropdownInput",
|
||||
|
|
@ -1984,7 +1984,7 @@
|
|||
"show": true,
|
||||
"title_case": false,
|
||||
"type": "code",
|
||||
"value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Load and retrive data from specified URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n is_list=True,\n tool_mode=True,\n placeholder=\"Enter a URL...\",\n list_add_label=\"Add URL\",\n\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output Format\",\n info=\"Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\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 ensure_url(self, string: str) -> str:\n \"\"\"Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n msg = f\"Invalid URL: {string}\"\n raise ValueError(msg)\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n\n def as_dataframe(self) -> DataFrame:\n return DataFrame(self.fetch_content())\n"
|
||||
"value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Load and retrive data from specified URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n is_list=True,\n tool_mode=True,\n placeholder=\"Enter a URL...\",\n list_add_label=\"Add URL\",\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output Format\",\n info=\"Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\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 ensure_url(self, string: str) -> str:\n \"\"\"Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n msg = f\"Invalid URL: {string}\"\n raise ValueError(msg)\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n\n def as_dataframe(self) -> DataFrame:\n return DataFrame(self.fetch_content())\n"
|
||||
},
|
||||
"format": {
|
||||
"_input_type": "DropdownInput",
|
||||
|
|
|
|||
|
|
@ -2640,7 +2640,7 @@
|
|||
"show": true,
|
||||
"title_case": false,
|
||||
"type": "code",
|
||||
"value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Load and retrive data from specified URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n is_list=True,\n tool_mode=True,\n placeholder=\"Enter a URL...\",\n list_add_label=\"Add URL\",\n\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output Format\",\n info=\"Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\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 ensure_url(self, string: str) -> str:\n \"\"\"Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n msg = f\"Invalid URL: {string}\"\n raise ValueError(msg)\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n\n def as_dataframe(self) -> DataFrame:\n return DataFrame(self.fetch_content())\n"
|
||||
"value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Load and retrive data from specified URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n is_list=True,\n tool_mode=True,\n placeholder=\"Enter a URL...\",\n list_add_label=\"Add URL\",\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output Format\",\n info=\"Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\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 ensure_url(self, string: str) -> str:\n \"\"\"Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n msg = f\"Invalid URL: {string}\"\n raise ValueError(msg)\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n\n def as_dataframe(self) -> DataFrame:\n return DataFrame(self.fetch_content())\n"
|
||||
},
|
||||
"format": {
|
||||
"_input_type": "DropdownInput",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue