Best Approach to Extract Key Data from a Structured PDF with LLM

[merefield]

@ahmedbhs123

Send the full text in a single prompt to the LLM. Each section is about 1000 tokens, so the total fits within a 4000-token context window.

Hope you’ve seen this Announcements

Direct PDF file input now supported in the API

No need for pre-processing or storing PDF files — send files directly to the Responses and Chat Completions APIs. We extract both text and images from PDFs, and models with vision capabilities (o1, 4o, etc) can generate text with that context. https://platform.openai.com/docs/guides/pdf-files?api-mode=chat https://x.com/OpenAIDevs/status/1902114937624830106