Building Dashboards and Applications with Streamlit Training Course

The training has been designed for individuals who want to effectively work with data using Python, leveraging libraries such as Pandas, NumPy, and tools for integration with Excel. Participants will learn both the basics of data manipulation and advanced techniques for code optimization, processing large datasets, and creating compelling reports and visualizations.

Throughout the course, participants will step-by-step learn:

how to import, process, and analyze data using Pandas and NumPy, optimize Python code performance, automate report and chart generation in Excel, and integrate various data sources into a cohesive analytical process.

This instructor-led, live training in Luxembourg is aimed at beginner to intermediate-level engineers, technicians, and automation professionals who wish to use Python to solve technical problems, automate repetitive tasks, and process industrial data.

By the end of this training, participants will be able to:

• Write clear and structured Python scripts for technical use cases
• Apply programming logic to engineering-oriented problems
• Use Python to process data from CSV, logs, and text files
• Automate repetitive engineering and automation workflows

This training allows participants to gradually enter the world of programming in the Python language. The course covers the most important elements of the language—from basic syntax and working with the environment, through data operations and program flow control, up to functions, modules, and the first elements of object-oriented programming.

Participants will become familiar with key constructs used in daily programming work, learn algorithmic thinking, and organize code in a transparent and consistent manner according to best practices. During the training, significant emphasis is placed on writing high-quality code and error analysis.

Upon completion of the training, participants will be able to independently write simple scripts, create functions and classes, organize projects into files, as well as understand, analyze, and run Python code in practical applications.

The training focuses on building a Retrieval Augmented Generation (RAG) system, which combines the capabilities of large language models with information retrieval from local documents. Participants will learn how to create applications that answer questions based on their own data, eliminating the problem of hallucinations and knowledge limitations in LLMs.

The program guides participants through all key stages of creating a RAG system. They will become familiar with communication principles using the OpenAI API and the LangChain framework, which facilitates working with language models. Participants will learn how to process documents in various formats, divide them into optimal segments, and transform them into vector representations. They will also get to know the Qdrant database and mechanisms for semantic search based on embedding similarity.

We place special emphasis on the quality of system performance—participants will implement result reranking techniques and learn how to quantify retrieval effectiveness and generated responses using the DeepEval library. The program also covers practical aspects of prompt engineering and methods for avoiding typical pitfalls when working with LLMs.

The outcome of the training will be a functional web application built in Streamlit, which allows users to ask questions about their own document base. Upon completing the course, participants will be able to independently design and implement a RAG system tailored to their specific business needs.