Getting Started

// src/workflows/summarize_url/workflow.ts
import { workflow, z } from '@outputai/core';
import { scrapeUrl, summarizeContent } from './steps.js';

export default workflow({
  name: 'summarize_url',
  description: 'Scrape a webpage and summarize its content',
  inputSchema: z.object({
    url: z.string().url().describe('The URL to scrape and summarize')
  }),
  outputSchema: z.object({
    title: z.string().describe('Page title'),
    summary: z.string().describe('Summary of the page content'),
    wordCount: z.number().describe('Word count of original content')
  }),
  fn: async input => {
    const { title, content } = await scrapeUrl(input.url);
    const summary = await summarizeContent(content);
    return {
      title,
      summary,
      wordCount: content.split(/\s+/).length
    };
  }
});

// src/workflows/summarize_url/steps.ts
import { step, z } from '@outputai/core';
import { generateText } from '@outputai/llm';
import { jinaClient } from '../../clients/jina.js';  // src/clients/jina.ts

export const scrapeUrl = step({
  name: 'scrapeUrl',
  description: 'Fetch and extract content from a URL using Jina Reader',
  inputSchema: z.string().url(),
  outputSchema: z.object({
    title: z.string(),
    content: z.string()
  }),
  fn: async url => {
    const markdown = await jinaClient.read(url);

    // Extract title from first heading or first line
    const titleMatch = markdown.match(/^#\s+(.+)$/m);
    const title = titleMatch ? titleMatch[1] : 'Untitled';

    return { title, content: markdown };
  }
});

export const summarizeContent = step({
  name: 'summarizeContent',
  description: 'Summarize text content using an LLM',
  inputSchema: z.string(),
  outputSchema: z.string(),
  fn: async content => {
    const truncated = content.slice(0, 10000);

    return generateText({
      prompt: 'summarize@v1',
      variables: { content: truncated }
    });
  }
});

// src/clients/jina.ts
import { httpClient } from '@outputai/http';

const client = httpClient({
  prefixUrl: 'https://r.jina.ai',
  timeout: 30000
});

export const jinaClient = {
  /**
   * Convert a URL to clean markdown using Jina Reader
   */
  read: async (url: string): Promise<string> => {
    const response = await client.get(url);
    return response.text();
  }
};

---
provider: anthropic
model: claude-sonnet-4-20250514
temperature: 0.3
---

<system>
You are a concise summarizer. Create a clear, informative summary of the provided content.
Focus on the main points and key takeaways. Keep the summary to 2-3 paragraphs.
</system>

<user>
Summarize the following content:

{{ content }}
</user>

{
  "url": "https://en.wikipedia.org/wiki/Ada_Lovelace"
}

// src/workflows/summarize_url/workflow.ts
import { workflow, z } from '@outputai/core';
import { scrapeUrl, summarizeContent, generateFaq } from './steps.js';

export default workflow({
  name: 'summarize_url',
  description: 'Scrape a webpage, summarize it, and generate FAQs',
  inputSchema: z.object({
    url: z.string().url().describe('The URL to scrape and summarize')
  }),
  outputSchema: z.object({
    title: z.string().describe('Page title'),
    summary: z.string().describe('Summary of the page content'),
    faqs: z.array(z.object({
      question: z.string(),
      answer: z.string()
    })).describe('Frequently asked questions'),
    wordCount: z.number().describe('Word count of original content')
  }),
  fn: async input => {
    const { title, content } = await scrapeUrl(input.url);

    // Run summarization and FAQ generation in parallel
    const [summary, faqs] = await Promise.all([
      summarizeContent(content),
      generateFaq(content)
    ]);

    return {
      title,
      summary,
      faqs,
      wordCount: content.split(/\s+/).length
    };
  }
});

export const generateFaq = step({
  name: 'generateFaq',
  description: 'Generate FAQs from content using an LLM',
  inputSchema: z.string(),
  outputSchema: z.array(z.object({
    question: z.string(),
    answer: z.string()
  })),
  fn: async content => {
    const truncated = content.slice(0, 10000);

    const { output } = await generateText({
      prompt: 'generate_faq@v1',
      variables: { content: truncated },
      output: Output.array({
        element: z.object({
          question: z.string(),
          answer: z.string()
        })
      })
    });
    return output;
  }
});

---
provider: anthropic
model: claude-sonnet-4-20250514
temperature: 0.3
---

<system>
You are a helpful assistant that generates frequently asked questions.
Create 5 Q&A pairs based on the content. Questions should be what a reader would naturally ask.
Answers should be concise and directly from the content.
</system>

<user>
Generate 5 FAQs from this content:

{{ content }}
</user>