Image by author
Most people who lack technical knowledge may think that working with ai or LLM (Large Language Models) is challenging and reserved for experts and engineers. However, what if I told you that all you need is proficiency in Python to create a wide range of LLM projects, from Q&A systems to YouTube recaps? You can even create your own GPT-4o application using multiple open source models and components.
In this project, we will explore interesting and easily doable LLM project ideas that you can create using free or affordable resources. Additionally, each project idea is accompanied by a sample project link that you can examine to better understand how it works.
1. Flame 3 setting and local use
He Flame 3 adjustment and local use It is a proper project with multiple steps and files. The goal is to refine the model on a dataset of conversations between patients and doctors using free resources provided by Kaggle. Once the model is successfully tuned, it can answer medical-related questions in a highly professional manner.
Project image
To use the offline model on your laptop, you can follow these steps:
- Merge the adopter layer with the base model.
- Convert the model to the Llama.cpp format, known as GGUF.
- Reduce the size of the model using the quantization method.
- Finally, use the model on your laptop using the Windows Jan application.
It is important to keep medical conversations between doctors and patients private, so it is necessary to use it locally and ensure privacy.
2. Question and answer retrieval system
If you prefer not to tune the model, you can still build context-aware ai applications locally using tools like LangChain, Chroma DB, and Ollama. This application will use your data set as context before generating the response.
To create the RAG (Recovery Augmented Generation) application, you can follow these steps:
- Upload PDF files: Start by uploading all PDF files from the designated folder.
- Split text: Break text into smaller chunks for efficient processing.
- Convert to embeds: Convert text to embeds and save them to the vector database.
- Building a recovery chain: Build a recovery chain using LangChain.
- Develop a Python application: Create a proper Python application to ensure a seamless chat experience.
Project image
LangChain simplifies the process by providing a high-level API and easy-to-use commands. Following the tutorial on “How to run Llama 3 locally,” can create an intelligent, context-sensitive LLM application.
3. Serve an LLM application as an API endpoint using FastAPI in Python
In this project, you will create an English to French translation API using the OpenAI API and FastAPI. The project will be divided into two main parts: understanding how to use the OpenAI API to ensure that the generated output is always in French, and creating a REST API using FastAPI to receive text and output output using a simple CURL command.
If you are familiar with FastAPI, you can create an even better LLM application that can serve as an API endpoint in 30 minutes.
Project image
For reference, follow the guide “Serve an LLM application as an API endpoint using FastAPI in Python” and try to serve your LLM. It can also be a model that you are running locally.
4. Vacation Planning Assistant
Planning a vacation without a travel agent can be difficult. There are so many moving parts and sometimes people don't even know what to do. So why not create your own travel itinerary app that displays your itinerary on a map and provides detailed plans and various attractions?
In this project, you will create a web application that receives instructions from users about their travel plans and provides itinerary suggestions, displaying them on a map.
Project image
The project requires you to learn some basics about Gradio, the release, and the Google Maps API before diving into the project. You can start by following the “Creating a Smart Travel Itinerary Suggestion with LangChain, Google Maps API and Gradio (Part 1)“tutorial, but if you want to create the Vacation Planning Assistant, you may need to add more components to your application and make it more robust.
5. YouTube Overview
YouTube Summarizer is a beginner-friendly project, perfect for students and newcomers to APIs and natural language processing. The project involves using the YouTube API to extract video transcripts and the OpenAI API to summarize these transcripts. Since some videos can be long and the contextual window of models like ChatGPT can be limited, the project requires breaking the transcription into manageable chunks. Each part is summarized individually and the summarized sections are then combined to produce a coherent summary of the entire video.
Project image
You can follow the “Create your own YouTube video summary app in just 3 easy steps“tutorial and experience the wonder yourself.
Note: The project uses the old API. You can always refer to the OpenAI API documentation to update to the new framework.
6. Web scraping with LLM
Web scraping can be a lucrative business as people can earn up to $200 per day by running a simple script. It is considered lucrative because it can be difficult to bypass certain website structures. In such cases, creating an LLM-powered web scraper using Scrapy and Ollama can help automate or improve web analysis.
Image from books.toscrape.com
Following the guide “Web Scraping with LLM,”, you can learn how to use LLM on each web page to extract specific attributes, such as product name and price. LLM eliminates the need for manual coding to extract these attributes from the web page; all you need to change is the message.e.
7. Build GPT4o using open models
Building an all-in-one ai application typically requires millions of dollars and years of research. What if I told you that you could build your own GPT-4o model using an open source model at no cost and in just one day?
In this project, we will create a comprehensive Open GPT-4o application that can understand audio, image, and text data. It will include a live voice chat feature and video chat capabilities. Additionally, you can use it to generate images and videos. Ultimately, it will be your AGI (Artificial General Intelligence) application.
Please note that the project does not come with a guide or tutorial, so you will have to learn everything by understanding the source code: app.py · KingNish/OpenGPT-4o in main (huggingface.co)
Picture of OpenGPT 4o
Before creating your LLM application, I recommend that you test OpenGPT 4o. Learn the various features and what type of model you are using. Find out how efficient and fast it is.
Final thoughts
Creating an LLM portfolio project can significantly improve your career prospects. If you are a student looking for a job, these 7 projects will help you get a job faster than others. Recruiters and hiring managers are especially impressed by projects that incorporate the latest technologies, such as ai.
To get started, bookmark this page and start building simple projects. As you progress to more complex projects, be sure to consistently showcase your work on LinkedIn. This way, you will soon catch the attention of recruiters.
Abid Ali Awan (@1abidaliawan) is a certified professional data scientist who loves building machine learning models. Currently, he focuses on content creation and writing technical blogs on data science and machine learning technologies. Abid has a master's degree in technology management and a bachelor's degree in telecommunications engineering. His vision is to build an artificial intelligence product using a graph neural network for students struggling with mental illness.
