Structured Data Extracted Using AI

Configure your extraction fields and click 'Extract Data' to see results here

Tips for Better Results

  • Use specific field descriptions to guide the AI accurately
  • Start with more fields and remove unnecessary ones later
  • If results are inaccurate, try rephrasing your field descriptions
  • For multiple text blocks , separate each with a double line break
  • Each text block should contain complete information for all fields you want to extract

Technical Note

To ensure timely results (since this is hosted on a CPU), we utilize gpt-5-mini-2025-08-07 for this demo.

For complete privacy , consider using local open-weight models via chat_ollama() from the ellmer library, which connects to Ollama for running models locally on your machine.

Alternatively, for higher accuracy requirements, users can leverage more performant closed models (e.g., gpt-5.2-2025-12-11 , claude-opus-4-5-20251101 , or gemini-3-pro-preview ) depending on the application needs. Note that Claude models require chat_anthropic() and Gemini models require chat_google_gemini() , each with their respective API keys configured in the R environment.

This demo uses chat_openai() only and does not provide an option to change the gpt-5-mini-2025-08-07 model.