Michał Żarnecki

php-rag. This application uses LLMs like DeepSeek, GPT-5, Claude, Gemini or Llama, Mixtral (locally) in order to generate text based on the user input. The user input is used to retrieve relevant information from the database and then the retrieved information is used to generate the text. This approach combines power of LLMs and access to source documen

course_llm_agent_apps_with_langchain_and_langgraph. AI apps development in LangChain & LangGraph - tutorial notebooks

supervised-machine-learning-full-examples. This repository contains notebooks with full analysis and machine learning process for different types of datasets including: prices prediction, numeric and categorical data classification and natural language text classification

ai-codebase-expert. Introducing tool to solve development tasks and bug fix tickets in large projects. This project is using GPT-4o LLM and langchain agents to search the project code base and documentation to support development work and fixing issues.

companyDescriptionClassification. The goal of this projest is to present 3 different approaches for text classification (trained ML model, zer-shot transformer, RAG).

llm-chatbot-rag-langchain. RAG (Retrieval-augmented generation) and langchain chat bot example

course-generative-ai-python. Course Generative AI with LLM in Python that consists of of Jupyter notebooks demonstrating the use of LlamaIndex, LangChain, Ollama, and the Transformers library for building generative AI applications use cases in Python.

time-series-analysis. This repository contains a collection of notebooks presenting different approaches to sequential data analysis, feature extraction, and the development of predictive and classification models. These materials can be used as examples for lectures, exercises, or self-study.

php-llm-evaluation. Evaluate results generated by Large Language Models in PHP

ml-in-php-start-templates. This project is supposed to be a starting template for replacing business logic in PHP projects with machine learning models. I add here common use cases of how to use machine learning models in PHP projects. In order to use it in your projects you need to replace the data with your dataset and adjust data import and feature engineering stages.

self-driving-car-raspberry. Raspberry Pi self driving car using tensor flow convolutional neuron networks model.

aws-ai-services-example. Jupyter Notebook

speech-recognition-api-example. Simple example for building program in Python with speech recording and recognition using speech_recognition library

train-ner-model-with-spacy. Custom training NER model with spacy library and annotaded dataset in JSON