Hello! 👋

TLDR; In this article, we will show how to parse PDF and webpage into Markdown format – which can preserve document structure for better LLM understanding.

LLM is powerful, but it cannot answer questions it doesn’t know before. Thanks to RAG we can inject some knowledge to extend LLM capability. Now let’s build our first RAG!

We moved from in-house training model to hosted models and ready-to-use APIs. With the existence of free LLM APIs, let’s explore how to create our own free chatbot!

Despite of the powerfulness of FastAPI, I found it’s not easy to work with threads and RabbitMQ. Here I’ll share my findings on creating both RMQ based producer and consumer in single FastAPI app.

Autoencoder network designed to learn data representation using its bottleneck network architecture. Now, we will discover autoencoder use case for image restoration.

Generally, there are two popular basic variant of Generative AI: Autoencoders network and Generative Adversarial Network (GAN). In this series, we will discover the former one and leave the latter in another one.

Lately, I was working on a course project where we asked to review one of the modern DL papers from top latest conferences and make an experimental test with our own dataset. So, here I am thrilled to share with you about my exploration!

Sometimes when we are applying for jobs, they ask us to send our portfolio. But instead of sharing your Jupyter Notebook — which they might won’t read it as it requires more effort to open — what if I tell you there are some way to simply export your beloved notebook to PDFs?

Ketika kita berhubungan dengan data teks seperti klasifikasi teks misalnya, kita tentunya harus melakukan transformasi data teks menjadi sekumpulan angka (vektor) terlebih dahulu sebelum melakukan modelling. Nah, 2 metode yang cukup populer diantaranya adalah Bag of Words dan TF-IDF. Mari kita bahas bagaimana mereka bekerja serta apa perbedaannya!