Pricing

Rating

Developer

Actor stats

Categories

Share

Structured Data Extractor

Extract structured JSON from any webpage using a Groq-compatible LLM.

Provide a URL + a JSON Schema → get back validated, structured data. Works with Groq (free), OpenAI, Together AI, Fireworks AI, and Ollama.

👁 Apify Actor
👁 PPE Pricing

What It Does

1. Scrapes the page at your URL using a real browser-grade crawler (CheerioCrawler)
2. Strips all HTML, navigation, scripts, and boilerplate → clean plain text
3. Prompts a Groq-compatible LLM to extract data matching your schema
4. Validates the response with AJV (JSON Schema validator)
5. Retries up to 3 times if the LLM returns invalid JSON, injecting the error back into the prompt
6. Returns validated structured data in the Apify dataset

Charge: $0.05 per successful extraction. Nothing charged on failure.

Input Schema

Usage Examples

Example 1: Groq (default, free tier)

Get a free API key at console.groq.com.

{
"url":"https://example.com/product/widget-pro",
"groq_api_key":"gsk_YOUR_GROQ_KEY_HERE",
"output_schema":{
"type":"object",
"required":["name","price"],
"properties":{
"name":{"type":"string"},
"price":{"type":"number"},
"description":{"type":"string"},
"in_stock":{"type":"boolean"}
}
}
}

Output:

{
"url":"https://example.com/product/widget-pro",
"extracted":{
"name":"Widget Pro",
"price":29.99,
"description":"The best widget on the market.",
"in_stock":true
},
"model":"llama-3.3-70b-versatile",
"attempts":1
}

Example 2: OpenAI-compatible endpoint (Together AI, Fireworks AI)

Use any OpenAI-compatible provider by setting base_url:

{
"url":"https://jobs.lever.co/anthropic/engineer",
"groq_api_key":"YOUR_TOGETHER_AI_KEY",
"base_url":"https://api.together.xyz/v1",
"model":"meta-llama/Llama-3.3-70B-Instruct-Turbo",
"output_schema":{
"type":"object",
"required":["title","company","location","salary_range"],
"properties":{
"title":{"type":"string"},
"company":{"type":"string"},
"location":{"type":"string"},
"salary_range":{"type":"string"},
"remote":{"type":"boolean"},
"requirements":{
"type":"array",
"items":{"type":"string"}
}
}
}
}

Other compatible endpoints:

• Fireworks AI: https://api.fireworks.ai/inference/v1
• OpenAI: https://api.openai.com/v1

Example 3: Ollama (local, completely free)

Run models locally at zero cost with Ollama:

# Start Ollama with a model
ollama serve
ollama pull llama3.3

{
"url":"https://news.ycombinator.com/item?id=12345",
"groq_api_key":"ollama",
"base_url":"http://localhost:11434/v1",
"model":"llama3.3",
"output_schema":{
"type":"object",
"required":["title","score","comments_count"],
"properties":{
"title":{"type":"string"},
"score":{"type":"integer"},
"comments_count":{"type":"integer"},
"author":{"type":"string"},
"url":{"type":"string"}
}
}
}

Note: When running the Actor on Apify cloud, Ollama requires a remote endpoint. For local testing, use apify run with localhost.

Common Use Cases

How Retry Logic Works

The actor uses the same retry-with-feedback pattern as constrained.py from the DagPipe core library:

1. Attempt 1: Send text + schema → LLM responds → AJV validates
2. On failure: Inject the exact AJV error message into the next prompt → retry
3. Attempt 2: LLM receives error and corrects → validate again
4. After 3 failures: Throw with a descriptive error message

This approach reliably extracts valid structured data even from smaller/cheaper models.

Pricing

• $0.05 per successful extraction (Pay-Per-Event)
• Free if extraction fails — you're never charged for failed attempts
• Groq's free tier provides 30 requests/minute at zero cost to you

Technical Details

• Scraper: CheerioCrawler (zero-JS, fast, reliable)
• Validation: AJV v8 + ajv-formats (JSON Schema Draft-07/2019/2020 compatible)
• LLM client: OpenAI SDK (works with any OpenAI-compatible endpoint)
• Retry strategy: Error-feedback prompting (same pattern as DagPipe constrained.py)
• Language: TypeScript, Node.js 20+
• Tests: 9 vitest tests (100% passing)

Built With

DagPipe — Zero-cost, crash-proof LLM pipeline orchestrator.

$pip install dagpipe-core