# Could you use the OpenAI integration to analyse documents

**URL:** <https://community.glideapps.com/t/could-you-use-the-openai-integration-to-analyse-documents/63524>\
**Category:** Ask for Help\
**Created:** [July 5, 2023, 1:15pm UTC](https://community.glideapps.com/t/could-you-use-the-openai-integration-to-analyse-documents/63524 "2023-07-05T13:15:33Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Hive\_AI](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/hive_ai/32/57991_2.png) [@Hive\_AI](https://community.glideapps.com/u/Hive_AI)\
**Post date:** [July 5, 2023, 1:15pm UTC](https://community.glideapps.com/t/could-you-use-the-openai-integration-to-analyse-documents/63524/1 "2023-07-05T13:15:33Z")

</div>

Hey Guys, I have a client that is looking at using OpenAI through a custom app (Glide) to analyse large documents…How could one approach this?

---

<div class="post-metadata">

**Author:** ![ThinhDinh](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thinhdinh/32/49_2.png) [@ThinhDinh](https://community.glideapps.com/u/ThinhDinh)\
**Post date:** [July 6, 2023, 12:03am UTC](https://community.glideapps.com/t/could-you-use-the-openai-integration-to-analyse-documents/63524/2 "2023-07-06T00:03:24Z")

</div>

If you’re referring to that as a large document, I’m not sure if these approaches work:

- Somehow taking all the text from that doc and feed that in the prompt to OpenAI. It would exceed the tokens limit.

- Upload the file to Glide and give the link to OpenAI to “browse”. Maybe something worth trying, but they have recently stopped beta testing for the Bing browsing feature. I wonder if they stop the ability for gpt-3.5 and gpt-4 to stop being able to read external links altogether.

The best approach on the market is using vector embeddings, but that is not something that is built directly into Glide.

---

<div class="post-metadata">

**Author:** ![Thibaud\_Dubrule2](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/thibaud_dubrule2/32/61455_2.png) [@Thibaud\_Dubrule2](https://community.glideapps.com/u/Thibaud_Dubrule2)\
**Post date:** [November 6, 2023, 3:58pm UTC](https://community.glideapps.com/t/could-you-use-the-openai-integration-to-analyse-documents/63524/3 "2023-11-06T15:58:54Z")

</div>

Hi @Hive_AI and @ThinhDinh,

Any updates on this topic on your side?

I’m trying to implement something similar to create a database from archives in PDFs. I have a set of key properties I need to extract from each PDF to build my database. Then I’ll be able to create ML model hopefully.

Thanks for any tips or idea on how to approach. Might not even need Glide for the moment but rather an automation workflow via n8n or make

---

<div class="post-metadata">

**Author:** ![Jeff\_Hager](https://sea2.discourse-cdn.com/flex002/user_avatar/community.glideapps.com/jeff_hager/32/43_2.png) [@Jeff\_Hager](https://community.glideapps.com/u/Jeff_Hager)\
**Post date:** [November 6, 2023, 4:20pm UTC](https://community.glideapps.com/t/could-you-use-the-openai-integration-to-analyse-documents/63524/4 "2023-11-06T16:20:29Z")

</div>

> **[Document to Text | Glide Docs](https://www.glideapps.com/docs/automation/ai/document-to-text)**
>
> Extract text from documents.

> [@robotsparkles PDF → Glide AI → Query JSON is MAGIC](https://community.glideapps.com/t/pdf-glide-ai-query-json-is-magic/66944):
>
> wave Hey Fellow Gliders! Glide AI is crazy powerful. With “Document to Text”, you can extract the text from any document in seconds… If that’s not magical enough, you can use AI to format that text as JSON with any structure you define. Then, parse that JSON using Query JSON column to precisely predict and extract the values from the original PDF with almost 100% reliability. The tutorial below showcases two scenarios: Resume PDF → Document to Text → Format as JSON → Extract values and det…