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

**URL:** <https://community.openai.com/t/best-approach-to-extract-key-data-from-a-structured-pdf-with-llm/1229083>\
**Category:** Prompting\
**Tags:** gpt-4, api\
**Created:** [April 10, 2025, 7:42am UTC](https://community.openai.com/t/best-approach-to-extract-key-data-from-a-structured-pdf-with-llm/1229083 "2025-04-10T07:42:45Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![merefield](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/merefield/32/14812_2.png) [@merefield](https://community.openai.com/u/merefield)\
**Post date:** [April 10, 2025, 8:05am UTC](https://community.openai.com/t/best-approach-to-extract-key-data-from-a-structured-pdf-with-llm/1229083/2 "2025-04-10T08:05:29Z")

</div>

> [@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](https://community.openai.com/t/direct-pdf-file-input-now-supported-in-the-api/1146647):
>
> 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://platform.openai.com/docs/guides/pdf-files?api-mode=chat)[https://x.com/OpenAIDevs/status/1902114937624830106](https://x.com/OpenAIDevs/status/1902114937624830106)

---

_[View the full topic](https://community.openai.com/t/best-approach-to-extract-key-data-from-a-structured-pdf-with-llm/1229083)._