---
title: "Comment by Ranjan Dailata on \"Transforming Unstructured Documents to Standardized Formats with GPT: Building a Resume Parser\" | Hashnode"
description: "Sorry, I am not sure the exact reason why you decided to go with the conversation memory-based approach. However, the good news is that it's not required fo"
url: "https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9/comment/648932e906c1659c6d3336fa"
---

[Discussion](https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9)

Comment [Transforming Unstructured Documents to Standardized Formats with GPT: Building a Resume Parser](https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9)

[Ranjan Dailata](https://hashnode.com/@ranjancse)

[Jun 14, 2023](https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9/comment/648932e906c1659c6d3336fa)

Sorry, I am not sure the exact reason why you decided to go with the conversation memory-based approach. However, the good news is that it's not required for this use case. The reason for optimization is to save cost by reducing the token size. Also improve the overall performance by asking for what is required.