In continuation of my last blog post, I’m now set to introduce a feature that allows the chat to utilize information from a loaded PDF while responding to user queries. This feature aptly corresponds to a.k.a. “ChatPDF”. The image below provides a glimpse of the final look once all the…

In this blog post, we’re going to build upon the chat feature I introduced in my previous article. In that piece, I utilized the OpenAI API to enable the chat to respond to my queries. However, this approach had its drawbacks, including the costs associated with API calls and the…

In this brief post, we’ll delve into the specifics of implementing a ChatGPT chat interface using the OpenAI API on your local machine, powered by Streamlit. Only three days ago, Meta introduced a new product: Llama2. Though not technically open-source, for the purpose of this article, we will refer to…

A new concept to make the AI more business-valuable. — Introduction Explainable AI is getting a full bloom. It points a group of AI methods that can be understood by humans and ‘open the black box’ in machine learning; by clarifying what factor makes how much contribution to the machine learning outcome. Responsible AI is a kind of child of Explainable…

EC site coupon distribution planning — Optimization is widely used in the data science field. Implicitly, almost any data models are tuned to minimize the loss function through numeric optimization. The way recently people are getting more attention to is to use the optimization for the purpose of best allocation of the resources in order to…

Bootstrapping on the data having serial correlation — Bootstrap in General “Bootstrapping” in the field of statistics is a model-agnostic methodology to generate synthetic datasets for table data, for the two purposes; First, producing the bagging estimate through aggregation of multiple model results, and Second, getting the distribution of error so that we can also evaluate the certainty of estimate in…

All you use are Python and GCP Cloud Functions or Heroku. — I haven’t trained myself as a mobile app developer, therefore having my own app on my iPhone is beyond my fair dream. …

Before pretending you understand the diagram your smart colleague shows to you. — Introduction Within a company using data to derive business value, although you may not be appreciated with your data science skills all the time, you always are when you manage the data infrastructure well. Everyone wants the data stored in an accessible location, cleaned up…

(Almost) everything you should know to use Facebook Prophet like a pro, with many example Python codes👨🏿‍💻 and cheat sheet🧾 — What is Prophet? “Prophet” is an open-sourced library available on R or Python which helps users analyze and forecast time-series values released in 2017. With developers’ great efforts to make the time-series data analysis be available without expert works, it is highly user-friendly but still highly customizable, even to non-expert users. How lovely!!