Course Outline
Module I: Fundamentals of Large Language Models
1. Mechanisms of LLM operation—tokenization, context window, hallucination issues
2. Prompt engineering techniques for optimal results
3. Communicating with models via the OpenAI API
4. Practical use of the LangChain framework
5. Architecture of Retrieval Augmented Generation systems
Module II: Preparing Text Documents
1. Extracting content from various file formats (PDF, DOCX, TXT)
2. Concept of dividing text into segments (chunking)
3. Document segmentation strategies
4. Impact of chunk size on system quality
Module III: Vectorization and Data Storage
1. Principles of text vector representation (embeddings)
2. Semantic search based on vector similarity
3. Qdrant vector database—configuration and application in RAG
4. Indexing and managing collections of vectors
Module IV: Document Retrieval and Quality Evaluation
1. The retrieval process in RAG systems
3. Context construction for LLM queries
4. Result reranking technique
5. DeepEval framework for evaluating RAG systems
Module V: Web Application for the RAG System
1. Basics of the Streamlit library
2. Implementing the user interface
3. Integrating RAG system components into the web application
Testimonials (5)
The fact of having more practical exercises using more similar data to what we use in our projects (satellite images in raster format)
Matthieu - CS Group
Course - Scaling Data Analysis with Python and Dask
I thought the trainer was very knowledgeable and answered questions with confidence to clarify understanding.
Jenna - TCMT
Course - Machine Learning with Python – 2 Days
Very good preparation and expertise of a trainer, perfect communication in English. The course was practical (exercises + sharing examples of use cases)
Monika - Procter & Gamble Polska Sp. z o.o.
Course - Developing APIs with Python and FastAPI
The explaination
Wei Yang Teo - Ministry of Defence, Singapore
Course - Machine Learning with Python – 4 Days
Trainer develops training based on participant's pace