From Resume to Cowl Letter Utilizing AI and LLM, with Python and Streamlit -

DISCLAIMER: The thought of doing Cowl Letter and even Resume with AI doesn’t clearly begin with me. Lots of people have achieved this earlier than (very efficiently) and have constructed web sites and even corporations from the concept. That is only a tutorial on easy methods to construct your personal Cowl Letter AI Generator App utilizing Python and some strains of code. All of the code you’ll say on this weblog put up could be present in my public Github folder. Take pleasure in. 🙂

Pep Guardiola is a (very profitable) Manchester Metropolis soccer coach. Throughout Barcelona’s Leo Messi years, he invented a manner of taking part in soccer often known as “Tiki-Taka”. Because of this as quickly as you obtain the ball, you go the ball, instantly, with out even controlling it. You may go the ball 30–40 occasions earlier than scoring a aim.

Greater than a decade later, we are able to see how the way in which of taking part in soccer made Guardiola and his Barcelona well-known is gone. When you take a look at a Manchester Metropolis match, they take the ball and instantly search for the striker or the winger. You solely want a number of, vertical passes, instantly on the lookout for the chance. It’s extra predictable, however you do it so many occasions that you’ll finally discover the house to hit the goal.

I believe that the job market has someway gone in the identical path.

Earlier than you had the chance to go to the corporate, hand in your resume, discuss to them, be round them, schedule an interview, and actively discuss to individuals. You’ll spend weeks making ready for that journey, sprucing your resume, and reviewing questions and solutions.

For a lot of, this old school technique nonetheless works, and I consider it. In case you have a superb networking alternative, or the appropriate time and place, the handing the resume factor works very effectively. We love the human connection, and it is rather efficient to truly know somebody.

You will need to think about that there’s a complete different strategy as effectively. Corporations like LinkedIn, Certainly, and even normally the web fully modified the sport. You may ship so many resumes to so many corporations and discover a job out of statistics. AI is altering this sport somewhat bit additional. There are numerous AI instruments to tailor your resume for the particular firm, make your resume extra spectacular, or construct the job particular cowl letter. There are certainly many corporations that promote this type of companies to individuals which can be on the lookout for jobs.

Now, consider me, I’ve obtained nothing towards these corporations, in any respect, however the AI that they’re utilizing it’s probably not “their AI”. What I imply by that’s that when you use ChatGPT, Gemini, or the tremendous new DeepSeek to do the precise process you’ll very probably not get a worse response than the (paid) software that you’re utilizing on their web site. You might be actually paying for the “commodity” of getting a backend API that does what we must do by way of ChatGPT. And that’s truthful.

Nonetheless, I need to present you that it’s certainly quite simple and low cost to make your personal “resume assistant” utilizing Massive Language Fashions. Specifically, I need to concentrate on cowl letters. You give me your resume and the job description, and I offer you your cowl letter you’ll be able to copy and paste to LinkedIn, Certainly, or your e mail.

In a single picture, it is going to appear like this:

Picture made by the writer, credit on the picture

Now, Massive Language Fashions (LLMs) are particular AI fashions that produce textual content. Extra particularly, they’re HUGE Machine Studying fashions (even the small ones are very massive).

Because of this constructing your personal LLM or coaching one from scratch could be very, very costly. We received’t do something like that. We are going to use a wonderfully working LLM and we’ll well instruct it to carry out our process. Extra particularly, we’ll do this in Python and utilizing some APIs. Formally, it’s a paid API. Nonetheless, since I began the entire venture (with all of the trial and error course of) I spent lower than 30 cents. You’ll probably spend 4 or 5 cents on it.

Moreover, we’ll make a working internet app that may can help you have your cowl letter in a number of clicks. It will likely be an effort of a pair hundred strains of code (with areas 🙂).

To inspire you, listed here are screenshots of the ultimate app:

Fairly cool proper? It took me lower than 5 hours to construct the entire thing from scratch. Consider me: it’s that easy. On this weblog put up, we’ll describe, so as:

The LLM API Technique. This half will assist the reader perceive what LLM Brokers we’re utilizing and the way we’re connecting them.
The LLM Object. That is the implementation of the LLM API technique above utilizing Python.
The Internet App and outcomes. The LLM Object is then transferred into an online app utilizing Streamlit. I’ll present you easy methods to entry it and a few outcomes.

I’ll attempt to be as particular as attainable so that you’ve got every part it’s essential to make it your self, but when these things will get too technical, be at liberty to skip to half 3 and simply benefit from the sundown 🙃.

Let’s get began!

1. LLM API Technique

That is the Machine Studying System Design a part of this venture, which I saved extraordinarily gentle, as a result of I wished to maximise the readability of the entire strategy (and since it actually didn’t should be extra sophisticated than that).

We are going to use two APIs:

A Doc Parser LLM API will learn the Resume and extract all of the significant info. This info will likely be put in a .json file in order that, in manufacturing, we can have the resume already processed and saved someplace in our reminiscence.
A canopy letter LLM API. This API will learn the parsed resume (the output of the earlier API) and the job description and it’ll output the Cowl Letter.

Two details:

What’s the greatest LLM for this process? For textual content extraction and summarization, LLama or Gemma are recognized to be a fairly low cost and environment friendly LLM. As we’re going to use LLama for the summarization process, with a purpose to hold consistency, we are able to undertake it for the opposite API as effectively. If you wish to use one other mannequin, be at liberty to take action.
How can we join the APIs? There are a selection of the way you are able to do that. I made a decision to offer it a attempt to Llama API. The documentation isn’t precisely in depth, but it surely works effectively and it permits you to play with many fashions. You have to to log in, purchase some credit score ($1 is greater than enough for this process), and save your API key. Be at liberty to change to a different answer (like Hugging Face or Langchain) when you really feel prefer it.

Okay, now that we all know what to do, we simply want to truly implement it in Python.

2. LLM Object

The very first thing that we want is the precise LLM prompts. Within the API, the prompts are normally handed utilizing a dictionary. As they are often fairly lengthy, and their construction is all the time comparable, it is sensible to retailer them in .json recordsdata. We are going to learn the JSON recordsdata and use them as inputs for the API name.

2.1 LLM Prompts

On this .json file, you’ll have the mannequin (you’ll be able to name no matter mannequin you want) and the content material which is the instruction for the LLM. In fact, the content material key has a static half, which is the “instruction” and a “dynamic” half, which is the particular enter of the API name. For instance: that is the .json file for the primary API, I referred to as it resume_parser_api.json:

As you’ll be able to see from the “content material” there’s the static name:

“You’re a resume parser. You’ll extract info from this resume and put them in a .json file. The keys of your dictionary will likely be first_name, last_name, location, work_experience, school_experience, expertise. In choosing the knowledge, hold observe of probably the most insightful.”

The keys I need to extract out of my “.json” recordsdata are:

[first_name, last_name, location, work_experience, school_experience, skills]

Be at liberty so as to add something extra info that you just need to be “extracted” out of your resume, however keep in mind that that is stuff that ought to matter solely to your cowl letter. The particular resume will likely be added after this textual content to kind the total name/instruction. Extra on that later.

The order instruction is the cover_letter_api.json:

Now the instruction is that this one:

“You might be an skilled in job searching and a canopy letter author. Given a resume json file, the job description, and the date, write a canopy letter for this candidate. Be persuasive {and professional}. Resume JSON: {resume_json} ; Job Description: {job_description}, Date: {date}”

As you’ll be able to see, there are three placeholders: “Resume_json”, “job_description” and “date”. As earlier than, these placeholders will then get replaced with the proper info to kind the total immediate.

2.2 constants.py

I made a really small constants.py file with the trail of the 2 .json immediate recordsdata and the API that you must generate from LLamaApi (or actually no matter API you might be utilizing). Modify this if you wish to run the file regionally.

2.3 file_loader.py

This file is a group of “loaders” to your resume. Boring stuff however vital.

2.4 cover_letter.py

The entire implementation of the LLM Technique could be discovered on this object that I referred to as CoverLetterAI. There it’s:

I spent fairly a while attempting to make every part modular and straightforward to learn. I additionally made numerous feedback to all of the features so you’ll be able to see precisely what does what. How can we use this beast?

So the entire code runs in 5 easy strains. Like this:

from cover_letter import CoverLetterAI
cover_letter_AI = CoverLetterAI()
cover_letter_AI.read_candidate_data('path_to_your_resume_file')
cover_letter_AI.profile_candidate()
cover_letter_AI.add_job_description('Insert job description')
cover_letter_AI.write_cover_letter()

So so as:

You name the CoverLetterAI object. It will likely be the star of the present
You give me the trail to your resume. It may be PDF or Phrase and I learn your info and retailer them in a variable.
You name profile_candidate(), and I run my first LLM. This course of the candidate phrase information and creates the .json file we’ll use for the second LLM
You give me the job_description and also you add it to the system. Saved.
You name write_cover_letter() and I run my second LLM that generates, given the job description and the resume .json file, the duvet letter

3. Internet App and Outcomes

So that’s actually it. You noticed all of the technical particulars of this weblog put up within the earlier paragraphs.

Simply to be additional fancy and present you that it really works, I additionally made it an online app, the place you’ll be able to simply add your resume, add your job description and click on generate cowl letter. That is the hyperlink and that is the code.

Now, the cowl letters which can be generated are scary good.

It is a random one:

February 1, 2025

Hiring Supervisor,
[Company I am intentionally blurring]

I’m thrilled to use for the Distinguished AI Engineer place at [Company I am intentionally blurring], the place I can leverage my ardour for constructing accountable and scalable AI methods to revolutionize the banking trade. As a seasoned machine studying engineer and researcher with a powerful background in physics and engineering, I’m assured that my expertise and expertise align with the necessities of this function.

With a Ph.D. in Aerospace Engineering and Engineering Mechanics from the College of Cincinnati and a Grasp’s diploma in Physics of Advanced Methods and Massive Information from the College of Rome Tor Vergata, I possess a novel mix of theoretical and sensible data. My expertise in creating and deploying AI fashions, designing and implementing machine studying algorithms, and dealing with giant datasets has geared up me with the abilities to drive innovation in AI engineering.

As a Analysis and Educating Assistant on the College of Cincinnati, I utilized surrogate fashions to detect and classify cracks in pipes, reaching a 14% enchancment in injury detection experiments. I additionally developed surrogate fashions utilizing deep studying algorithms to speed up Finite Component Strategies (FEM) simulations, leading to a 1M-fold discount in computational time. My expertise in educating and creating programs in sign processing and picture processing for teenagers serious about AI has honed my capacity to speak advanced ideas successfully.

In my earlier roles as a Machine Studying Engineer at Gen 9, Inc., Apex Microdevices, and Accenture, I’ve efficiently designed, developed, and deployed AI-powered options, together with configuring mmWave radar and Jetson units for information assortment, implementing state-of-the-art level cloud algorithms, and main the FastMRI venture to speed up MRI scan occasions. My experience in programming languages akin to Python, TensorFlow, PyTorch, and MATLAB, in addition to my expertise with cloud platforms like AWS, Docker, and Kubernetes, has enabled me to develop and deploy scalable AI options.

I’m significantly drawn to [Company I am intentionally blurring] dedication to creating accountable and dependable AI methods that prioritize buyer expertise and ease. My ardour for staying abreast of the most recent AI analysis and my capacity to judiciously apply novel methods in manufacturing align with the corporate’s imaginative and prescient. I’m excited concerning the alternative to work with a cross-functional staff of engineers, analysis scientists, and product managers to ship AI-powered merchandise that remodel how [Company I am intentionally blurring] serves its clients.

Along with my technical expertise and expertise, I possess glorious communication and presentation expertise, which have been demonstrated by way of my technical writing expertise at In direction of Information Science, the place I’ve written complete articles on machine studying and information science, reaching a broad viewers of 50k+ month-to-month viewers.

Thanks for contemplating my utility. I’m keen to debate how my expertise and expertise can contribute to the success of the [Company I am intentionally blurring] and [Company I am intentionally blurring]’s mission to deliver humanity and ease to banking by way of AI. I’m assured that my ardour for AI, my technical experience, and my capacity to work collaboratively will make me a invaluable asset to your staff.

Sincerely,

Piero Paialunga

They give the impression of being identical to I might write them for a particular job description. That being mentioned, in 2025, it’s essential to watch out as a result of hiring managers do know that you’re utilizing AI to put in writing them and the “laptop tone” is fairly simple to identify (e.g. phrases like “keen” are very ChatGPT-ish lol). For that reason, I’d prefer to say to use these instruments properly. Certain, you’ll be able to construct your “template” with them, however make sure you add your private contact, in any other case your cowl letter will likely be precisely like the opposite hundreds of canopy letters that the opposite candidates are sending in.

That is the code to construct the online app.

4. Conclusions

On this weblog article, we found easy methods to use LLM to transform your resume and job description into a particular cowl letter. These are the factors we touched:

The usage of AI in job searching. Within the first chapter we mentioned how job searching is now fully revolutionized by AI.
Massive Language Fashions concept. You will need to design the LLM APIs properly. We did that within the second paragraph
LLM API implementation. We used Python to implement the LLM APIs organically and effectively
The Internet App. We used streamlit to construct a Internet App API to show the facility of this strategy.
Limits of this strategy. I believe that AI generated cowl letters are certainly superb. They’re on level, skilled and effectively crafted. Nonetheless, if everybody begins utilizing AI to construct cowl letters, all of them actually look the identical, or a minimum of all of them have the identical tone, which isn’t nice. One thing to consider.

5. References and different sensible implementations

I really feel that’s simply truthful to say numerous sensible those who have had this concept earlier than me and have made this public and obtainable for anybody. That is just a few of them I discovered on-line.

Cowl Letter Craft by Balaji Kesavan is a Streamlit app that implements a really comparable concept of crafting the duvet letter utilizing AI. What we do totally different from that app is that we extract the resume straight from the phrase or PDF, whereas his app requires copy-pasteing. That being mentioned, I believe the man is extremely proficient and really artistic and I like to recommend giving a glance to his portoflio.

Randy Pettus has a comparable concept as effectively. The distinction between his strategy and the one proposed on this tutorial is that he’s very particular within the info, asking questions like “present hiring supervisor” and the temperature of the mannequin. It’s very fascinating (and good) you can clearly see the way in which he’s pondering of Cowl Letters to information the AI to construct it the way in which he likes them. Extremely really helpful.

Juan Esteban Cepeda does an excellent job in his app as effectively. It’s also possible to inform that he was engaged on making it greater than a easy streamlit add as a result of he added the hyperlink to his firm and a bunch of critiques by customers. Nice job and nice hustle. 🙂

6. About me!

Thanks once more to your time. It means so much ❤

My identify is Piero Paialunga and I’m this man right here:

I’m a Ph.D. candidate on the College of Cincinnati Aerospace Engineering Division and a Machine Studying Engineer for Gen 9. I speak about AI, and Machine Studying in my weblog posts and on Linkedin. When you appreciated the article and need to know extra about machine studying and observe my research you’ll be able to:

A. Comply with me on Linkedin, the place I publish all my tales
B. Subscribe to my e-newsletter. It should hold you up to date about new tales and provide the probability to textual content me to obtain all of the corrections or doubts you might have.
C. Change into a referred member, so that you received’t have any “most variety of tales for the month” and you may learn no matter I (and hundreds of different Machine Studying and Information Science prime writers) write concerning the latest expertise obtainable.
D. Need to work with me? Examine my charges and initiatives on Upwork!

If you wish to ask me questions or begin a collaboration, depart a message right here or on Linkedin:

[email protected]

From Resume to Cowl Letter Utilizing AI and LLM, with Python and Streamlit