Flowise

Flowise is a drag-and-drop builder over LangChain. Use the Custom Tool node to expose /distill to any chain or agent on the canvas.

Create the Custom Tool

Tools → Custom Tool → Add new

• Tool name: read_url
• Tool description: Fetch a URL and return clean Markdown for the agent to read.
• Input schema (JSON):

{
  "type": "object",
  "required": ["url"],
  "properties": {
    "url":        { "type": "string" },
    "renderMode": { "type": "string", "enum": ["basic", "advanced"], "default": "basic" }
  }
}

• JavaScript function:

const res = await fetch('https://openapi.thunderbit.com/openapi/v1/distill', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${$vars.THUNDERBIT_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({ url: $url, renderMode: $renderMode || 'basic' }),
});
const json = await res.json();
return json.data.markdown;

Store the API key under Variables as THUNDERBIT_API_KEY so it's not hard-coded.

Wire into a chain

Drop the read_url tool into an Agent or Tool Agent node alongside your LLM (OpenAI, Anthropic, Ollama). The agent picks it up automatically.

Tips

• For RAG ingestion, pair with the Document Loader family — call read_url in a custom node, feed the Markdown into a Recursive Character Text Splitter, then a vector store
• Long pages can blow the agent's context — truncate to ~8k chars in the Custom Tool before returning

Related

• LangChain — Flowise is built on it
• Agent Read-URL Tool
• Dify