Build components with Langflow Assistant

Langflow Assistant is an in-app virtual assistant pane within the Playground.

It can answer questions about the application and help you get more out of Langflow.

Langflow Assistant understands the structure of the Langflow graph, so it can create components from natural language prompts.

Behind the scenes, Langflow Assistant runs a built-in Langflow flow on your Langflow server each time you send a message. This flow is distinct from the flow that is open in the canvas, and has its own language model. The language model in Langflow Assistant only has the currently opened flow in your workspace for context. To give Langflow Assistant context for a different flow, switch to that flow in your workspace, and open Langflow Assistant.

Prerequisites

• Connect an LLM provider in the Global model providers page for Langflow Assistant to use

Create a custom component with Langflow Assistant

In this example, you'll prompt Langflow Assistant to create a custom component that validates and normalizes a list of URLs.

You'll then iterate on the code based on the results in the Playground.

1. In the Playground, click the Langflow icon. The Langflow Assistant pane opens.

2. Optionally, ask What can you help me with? for a list of Langflow Assistant's capabilities.

3. Prompt Langflow Assistant to generate a custom component. For example:

   
   

   _10

   Create a custom component URLTitleExtractor with:

   _10

   input: text

   _10

   output: list of {url, title, status}

   _10

   timeout handling + per-URL error handling

   _10

   clean docstring and typed methods.”

   
   

4. Langflow Assistant generates component code from your prompt. Because generation is model-driven, your code may differ from the example below.

   Python component code

   
   

   _124

   import html

   _124

   import re

   _124

   from typing import Any

   _124

   from urllib.error import HTTPError, URLError

   _124

   from urllib.request import Request, urlopen

   _124

   _124

   from lfx.custom import Component

   _124

   from lfx.io import FloatInput, MessageTextInput, Output

   _124

   from lfx.schema import DataFrame

   _124

   _124

   _124

   class URLTitleExtractor(Component):

   _124

   """Extract URLs from text, fetch each page, and return URL/title/status rows."""

   _124

   _124

   display_name = "URLTitleExtractor"

   _124

   description = "Extracts URLs from input text and fetches page titles with per-URL status handling."

   _124

   icon = "Link"

   _124

   _124

   inputs = [

   _124

   MessageTextInput(

   _124

   name="text",

   _124

   display_name="Text",

   _124

   info="Text that may contain one or more URLs.",

   _124

   required=True,

   _124

   ),

   _124

   FloatInput(

   _124

   name="timeout",

   _124

   display_name="Timeout",

   _124

   value=5.0,

   _124

   info="HTTP request timeout in seconds for each URL.",

   _124

   range_spec={"min": 0.1, "max": 60.0, "step": 0.1, "step_type": "float"},

   _124

   ),

   _124

   ]

   _124

   _124

   outputs = [

   _124

   Output(

   _124

   name="dataframe",

   _124

   display_name="DataFrame",

   _124

   method="build_dataframe",

   _124

   ),

   _124

   ]

   _124

   _124

   URL_PATTERN = re.compile(r"https?://[^\s<>\]\"'`{}|\\^]+", re.IGNORECASE)

   _124

   TITLE_PATTERN = re.compile(r"<title\b[^>]*>(.*?)</title>", re.IGNORECASE | re.DOTALL)

   _124

   _124

   def build_dataframe(self) -> DataFrame:

   _124

   """Build a DataFrame containing URL, extracted title, and request status."""

   _124

   urls = self._extract_urls(self.text)

   _124

   rows = [self._process_url(url, self.timeout) for url in urls]

   _124

   return DataFrame(rows)

   _124

   _124

   def _extract_urls(self, text: str) -> list[str]:

   _124

   """Extract unique URLs from text using a conservative regex."""

   _124

   if not text:

   _124

   return []

   _124

   _124

   matches = self.URL_PATTERN.findall(text)

   _124

   cleaned_urls: list[str] = []

   _124

   seen: set[str] = set()

   _124

   _124

   for url in matches:

   _124

   cleaned = url.rstrip(".,);:!?]}")

   _124

   if cleaned and cleaned not in seen:

   _124

   seen.add(cleaned)

   _124

   cleaned_urls.append(cleaned)

   _124

   _124

   return cleaned_urls

   _124

   _124

   def _process_url(self, url: str, timeout: float) -> dict[str, Any]:

   _124

   """Fetch a URL and return a row with url, title, and status."""

   _124

   request = Request(

   _124

   url,

   _124

   headers={

   _124

   "User-Agent": "Mozilla/5.0 (compatible; Langflow URLTitleExtractor/1.0)"

   _124

   },

   _124

   )

   _124

   _124

   try:

   _124

   with urlopen(request, timeout=float(timeout)) as response:

   _124

   status_code = getattr(response, "status", 200)

   _124

   content_bytes = response.read()

   _124

   content_type = response.headers.get_content_charset() or "utf-8"

   _124

   html_text = content_bytes.decode(content_type, errors="replace")

   _124

   title = self._extract_title(html_text)

   _124

   return {"url": url, "title": title, "status": str(status_code)}

   _124

   _124

   except HTTPError as exc:

   _124

   title = ""

   _124

   try:

   _124

   body = exc.read()

   _124

   charset = exc.headers.get_content_charset() if exc.headers else None

   _124

   if body:

   _124

   html_text = body.decode(charset or "utf-8", errors="replace")

   _124

   title = self._extract_title(html_text)

   _124

   except Exception:

   _124

   title = ""

   _124

   return {"url": url, "title": title, "status": str(exc.code)}

   _124

   _124

   except TimeoutError:

   _124

   return {"url": url, "title": "", "status": "timeout"}

   _124

   _124

   except URLError as exc:

   _124

   reason = getattr(exc, "reason", None)

   _124

   if isinstance(reason, TimeoutError):

   _124

   status = "timeout"

   _124

   else:

   _124

   status = "request_error"

   _124

   return {"url": url, "title": "", "status": status}

   _124

   _124

   except Exception:

   _124

   return {"url": url, "title": "", "status": "request_error"}

   _124

   _124

   def _extract_title(self, html_text: str) -> str:

   _124

   """Extract and normalize the HTML title from a document string."""

   _124

   if not html_text:

   _124

   return ""

   _124

   _124

   match = self.TITLE_PATTERN.search(html_text)

   _124

   if not match:

   _124

   return ""

   _124

   _124

   title = html.unescape(match.group(1))

   _124

   title = re.sub(r"\s+", " ", title).strip()

   _124

   return title

   
   

   To inspect the code, click View Code. To add the component to the canvas, click Add to Canvas.

5. Connect the component to Chat Input and Chat Output components. At this point your flow has three connected components:

   • Chat Input sends the text that contains URLs into the URLTitleExtractor so the flow runs when you chat in the Playground or send a prompt from an app.
   • URLTitleExtractor reads that text, finds URLs, fetches each page, and outputs a Table with url, title, and status columns.
   • Chat Output receives URLTitleExtractor's result and displays the Table back to the user or calling application.

   

6. Open the Playground, and tell Langflow to check a list of URLs. For example:

   
   

   _10

   Check these links: https://langflow.org

   _10

   https://github.com/langflow-ai/langflow

   _10

   https://python.org

   _10

   https://this-domain-should-not-resolve-12345.invalid

   
   

7. Run the flow. The output will be similar to the following, with a Table with one row per URL, including page titles and status codes.

   url	title	status
   https://langflow.org	Langflow | Low-code AI builder for agentic and RAG applications	200
   https://github.com/langflow-ai/langflow	GitHub - langflow-ai/langflow: Langflow is a powerful tool for building and deploying AI-powered agents and workflows. - GitHub	200
   https://python.org	Welcome to Python.org	200
   https://this-domain-should-not-resolve-12345.invalid

8. To iterate further, tell Langflow Assistant what you want. For example, prompt it to Update URLTitleExtractor to add max_urls (default 5) and skip duplicates..

   Langflow Assistant generates an updated URLTitleExtractor component (again, the exact code may differ from a previous run).

9. Replace the old component with the new component. Set max_urls to 3. In the Playground, enter a list that includes a duplicate URL and the invalid URL from before:

   
   

   _10

   Check these links: https://langflow.org

   _10

   https://github.com/langflow-ai/langflow

   _10

   https://python.org

   _10

   https://langflow.org

   _10

   https://this-domain-should-not-resolve-12345.invalid

   
   

10. Run the flow. The output will be similar to the following, with the duplicate https://langflow.org removed and only 3 valid URLs displayed.

    url	title	status
    https://langflow.org	Langflow | Low-code AI builder for agentic and RAG applications	200
    https://github.com/langflow-ai/langflow	GitHub - langflow-ai/langflow: Langflow is a powerful tool for building and deploying AI-powered agents and workflows. - GitHub	200
    https://python.org	Welcome to Python.org	200