fix: change color of output inspector when tool mode, change fuzzy search order, fix image download and some minor issues (#4625)
* Fixed output and input radius and icons colors when on tool mode * Replaced output format to be camel case * Fix expand not appearing after minimize and change code * Refactor chatView component and add FlowRunningSqueleton - Refactor chatView component to import useMemo from react - Add FlowRunningSqueleton component to display flow running indicator - fix gagging on flow running * format code * Fixed fuzzy search order * remove console log --------- Co-authored-by: anovazzi1 <otavio2204@gmail.com> Co-authored-by: Cristhian Zanforlin Lousa <cristhian.lousa@gmail.com> Co-authored-by: Mike Fortman <michael.fortman@datastax.com>
This commit is contained in:
Lucas Oliveira
GitHub
parent
88c059677e
commit
2881346400
13 changed files with 90 additions and 49 deletions
|
|
@ -25,8 +25,8 @@ class URLComponent(Component):
|
|||
),
|
||||
DropdownInput(
|
||||
name="format",
|
||||
display_name="Output format",
|
||||
info="Output format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.",
|
||||
display_name="Output Format",
|
||||
info="Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.",
|
||||
options=["Text", "Raw HTML"],
|
||||
value="Text",
|
||||
),
|
||||
|
|
|
|||
|
|
@ -178,15 +178,15 @@
|
|||
"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.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Fetch content from one or more URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n info=\"Enter one or more URLs, by clicking the '+' button.\",\n is_list=True,\n tool_mode=True,\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 ]\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"
|
||||
"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.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Fetch content from one or more URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n info=\"Enter one or more URLs, by clicking the '+' button.\",\n is_list=True,\n tool_mode=True,\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 ]\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"
|
||||
},
|
||||
"format": {
|
||||
"_input_type": "DropdownInput",
|
||||
"advanced": false,
|
||||
"combobox": false,
|
||||
"display_name": "Output format",
|
||||
"display_name": "Output Format",
|
||||
"dynamic": false,
|
||||
"info": "Output format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.",
|
||||
"info": "Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.",
|
||||
"name": "format",
|
||||
"options": ["Text", "Raw HTML"],
|
||||
"placeholder": "",
|
||||
|
|
|
|||
|
|
@ -1507,15 +1507,15 @@
|
|||
"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.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Fetch content from one or more URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n info=\"Enter one or more URLs, by clicking the '+' button.\",\n is_list=True,\n tool_mode=True,\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 ]\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"
|
||||
"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.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Fetch content from one or more URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n info=\"Enter one or more URLs, by clicking the '+' button.\",\n is_list=True,\n tool_mode=True,\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 ]\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"
|
||||
},
|
||||
"format": {
|
||||
"_input_type": "DropdownInput",
|
||||
"advanced": false,
|
||||
"combobox": false,
|
||||
"display_name": "Output format",
|
||||
"display_name": "Output Format",
|
||||
"dynamic": false,
|
||||
"info": "Output format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.",
|
||||
"info": "Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.",
|
||||
"name": "format",
|
||||
"options": ["Text", "Raw HTML"],
|
||||
"placeholder": "",
|
||||
|
|
@ -1627,15 +1627,15 @@
|
|||
"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.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Fetch content from one or more URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n info=\"Enter one or more URLs, by clicking the '+' button.\",\n is_list=True,\n tool_mode=True,\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 ]\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"
|
||||
"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.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Fetch content from one or more URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n info=\"Enter one or more URLs, by clicking the '+' button.\",\n is_list=True,\n tool_mode=True,\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 ]\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"
|
||||
},
|
||||
"format": {
|
||||
"_input_type": "DropdownInput",
|
||||
"advanced": false,
|
||||
"combobox": false,
|
||||
"display_name": "Output format",
|
||||
"display_name": "Output Format",
|
||||
"dynamic": false,
|
||||
"info": "Output format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.",
|
||||
"info": "Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.",
|
||||
"name": "format",
|
||||
"options": ["Text", "Raw HTML"],
|
||||
"placeholder": "",
|
||||
|
|
@ -1751,15 +1751,15 @@
|
|||
"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.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Fetch content from one or more URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n info=\"Enter one or more URLs, by clicking the '+' button.\",\n is_list=True,\n tool_mode=True,\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 ]\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"
|
||||
"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.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Fetch content from one or more URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n info=\"Enter one or more URLs, by clicking the '+' button.\",\n is_list=True,\n tool_mode=True,\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 ]\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"
|
||||
},
|
||||
"format": {
|
||||
"_input_type": "DropdownInput",
|
||||
"advanced": false,
|
||||
"combobox": false,
|
||||
"display_name": "Output format",
|
||||
"display_name": "Output Format",
|
||||
"dynamic": false,
|
||||
"info": "Output format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.",
|
||||
"info": "Output Format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.",
|
||||
"name": "format",
|
||||
"options": ["Text", "Raw HTML"],
|
||||
"placeholder": "",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue