--- title: "Discussion on \"Transforming Unstructured Documents to Standardized Formats with GPT: Building a Resume Parser\" | Hashnode" description: "Discussion on \"Transforming Unstructured Documents to Standardized Formats with GPT: Building a Resume Parser\". Among its numerous applications, GPT has become a game-changer in the processing and standardization of unstructured documents.\nIn this blog post, we'll explore how you can convert unstructured documents, specifically resumes, into a standardized for..." url: "https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9" --- [Feed](https://hashnode.com/feed) / Discussion # [Transforming Unstructured Documents to Standardized Formats with GPT: Building a Resume Parser](https://blog.seeai.co.uk/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser?utm_source=hashnode&utm_medium=feed) Among its numerous applications, GPT has become a game-changer in the processing and standardization of unstructured documents. In this blog post, we'll explore how you can convert unstructured documents, specifically resumes, into a standardized for... Apr 20, 2023 · 5 min read · blog.seeai.co.uk Read the article - [#gpt-4](https://hashnode.com/tag/gpt-4) - [#gpt3](https://hashnode.com/tag/gpt3) - [#openai](https://hashnode.com/tag/openai) - [#python](https://hashnode.com/tag/python) - [#resumeparsing](https://hashnode.com/tag/resumeparsing) ## Written by [Reo Ogusu](https://hashnode.com/@Seeai) @Seeai · Leeds, UK [View profile](https://hashnode.com/@Seeai) Co-founder / CTO Automate day-to-day operations with Generative AI ## Responses 8 Markdown supported · ⌘↵ to post [sai kiran ganeshna](https://hashnode.com/@saikiran774) [Jan 9, 2024](https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9/comment/659d33c3822347bbc290cd9a) Full code is not available please provide full code [Kiran Sitaram](https://hashnode.com/@Kiran1568) [Dec 29, 2023](https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9/comment/658ef6c1f073040c2d2c25eb) The code provided is not complete. For example you are extracting the text from the pdf but you have included the call to the function in your code. Just for completeness of the article and for first time learners, I would suggest sharing the whole code or providing a link to the whole structures code. [Yuvayogi](https://hashnode.com/@ErrMonk) [Dec 14, 2023](https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9/comment/657afba876f2f92c7f579b64) I want full code for this! [Debasish Garai](https://hashnode.com/@Deba91) [May 31, 2024](https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9/comment/657afba876f2f92c7f579b64#reply-665975c8fb58edf3d83d0e37) Can u please provide the full code for new learners [Kiran Sitaram](https://hashnode.com/@Kiran1568) [Oct 12, 2023](https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9/comment/652818de443b82f5baff6238) Excellent article - illustrated in a very simple manner and very practical as well. I liked it. [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/648933bf06c1659c6d333715) OpenAIChat is deprecated. We need to go with the ChatOpenAI. chatopenai = ChatOpenAI( model\_name="gpt-3.5-turbo") llmchain\_chat = LLMChain(llm=chatopenai, prompt=prompt) [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. [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/64892f110a62399c9d69fae5) Please try to flatten the resume input. A multi-line to single-line conversion will save a ton of tokens and cost involved with the Open AI GPT based models. [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/64892b7806c1659c6d333612) The YAML template which you have specified in the "template" can be simplified by converting the multi-line to single say by using online convertors. It makes a lot of difference as each space and line adds up to the token count. You don't want to exceed the token count nor spend money unnecessarily. [Ranjan Dailata](https://hashnode.com/@ranjancse) [Jun 13, 2023](https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9/comment/64885347a99edc981e1b785e) Great post. One small suggestion on returning the JSON response using pyyaml. [Reo Ogusu](https://hashnode.com/@Seeai) [Jun 13, 2023](https://hashnode.com/posts/transforming-unstructured-documents-to-standardized-formats-with-gpt-building-a-resume-parser/6441716f963b2e281dab76e9/comment/64885347a99edc981e1b785e#reply-648894d50a62399c9d69ef36) Thanks! Yeah I could try that.