diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json b/src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json index 478cc29dd..40b6a7a06 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json @@ -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 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 ),\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", diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Custom Component Maker.json b/src/backend/base/langflow/initial_setup/starter_projects/Custom Component Maker.json index e152c8fd1..976c7bcdc 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Custom Component Maker.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Custom Component Maker.json @@ -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 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 ),\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 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 ),\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 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 ),\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", diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Graph Vector Store RAG.json b/src/backend/base/langflow/initial_setup/starter_projects/Graph Vector Store RAG.json index 1ade22b25..6675ff397 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Graph Vector Store RAG.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Graph Vector Store RAG.json @@ -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 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 ),\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", diff --git a/src/frontend/src/components/core/parameterRenderComponent/components/inputListComponent/components/delete-button-input-list.tsx b/src/frontend/src/components/core/parameterRenderComponent/components/inputListComponent/components/delete-button-input-list.tsx new file mode 100644 index 000000000..ac02009d7 --- /dev/null +++ b/src/frontend/src/components/core/parameterRenderComponent/components/inputListComponent/components/delete-button-input-list.tsx @@ -0,0 +1,45 @@ +import IconComponent from "@/components/common/genericIconComponent"; +import { ICON_STROKE_WIDTH } from "@/constants/constants"; +import { cn } from "@/utils/utils"; +import { getTestId } from "../helpers/get-test-id"; + +export const DeleteButtonInputList = ({ + index, + removeInput, + disabled, + editNode, + componentName, +}: { + index: number; + removeInput: (e: React.MouseEvent) => void; + disabled: boolean; + editNode: boolean; + componentName: string; +}) => { + return ( + + ); +}; + +export default DeleteButtonInputList; diff --git a/src/frontend/src/components/core/parameterRenderComponent/components/inputListComponent/index.tsx b/src/frontend/src/components/core/parameterRenderComponent/components/inputListComponent/index.tsx index 3b7a8dbb1..b7c90b773 100644 --- a/src/frontend/src/components/core/parameterRenderComponent/components/inputListComponent/index.tsx +++ b/src/frontend/src/components/core/parameterRenderComponent/components/inputListComponent/index.tsx @@ -10,6 +10,7 @@ import { GRADIENT_CLASS } from "@/constants/constants"; import { cn } from "../../../../../utils/utils"; import { getPlaceholder } from "../../helpers/get-placeholder-disabled"; import { InputListComponentType, InputProps } from "../../types"; +import { DeleteButtonInputList } from "./components/delete-button-input-list"; export default function InputListComponent({ value = [""], @@ -66,16 +67,16 @@ export default function InputListComponent({ [value, handleOnNewValue], ); - const handleDuplicateInput = useCallback( - (index: number, e: React.MouseEvent | KeyboardEvent) => { - e.preventDefault(); - const newInputList = _.cloneDeep(value); - newInputList.splice(index, 0, newInputList[index]); - handleOnNewValue({ value: newInputList }); - setDropdownOpen(null); - }, - [value, handleOnNewValue], - ); + // const handleDuplicateInput = useCallback( + // (index: number, e: React.MouseEvent | KeyboardEvent) => { + // e.preventDefault(); + // const newInputList = _.cloneDeep(value); + // newInputList.splice(index, 0, newInputList[index]); + // handleOnNewValue({ value: newInputList }); + // setDropdownOpen(null); + // }, + // [value, handleOnNewValue], + // ); return (
@@ -92,16 +93,29 @@ export default function InputListComponent({
{value.map((singleValue, index) => ( -
-
+
+ {focusedIndex !== index && !disabled && ( +