Building a RAG Pipeline with llama.cpp in Python
Using llama.
Detecting & Handling Data Drift in Production
Machine learning models are trained on historical data and deployed in real-world environments.
Quantization in Machine Learning: 5 Reasons Why It Matters More Than You Think
Quantization might sound like a topic reserved for hardware engineers or AI researchers in lab coats.
Applications with Context Vectors
This post is divided into two parts; they are: • Contextual Keyword Extraction • Contextual Text Summarization Contextual keyword extraction is a technique for identifying the most important words in a document based on their contextual relevance.
Generating and Visualizing Context Vectors in Transformers
This post is divided into three parts; they are: • Understanding Context Vectors • Visualizing Context Vectors from Different Layers • Visualizing Attention Patterns Unlike traditional word embeddings (such as Word2Vec or GloVe), which assign a fixed vector to each word regardless of context, transformer models generate dynamic representations that depend on surrounding words.
5 Lessons Learned Building RAG Systems
Retrieval augmented generation (RAG) is one of 2025’s hot topics in the AI landscape.
Understanding RAG Part X: RAG Pipelines in Production
Be sure to check out the previous articles in this series: •
Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)
Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications. However, as LLMs have improved, so have the attacks against them. Prompt injection attack is listed as the #1 threat by OWASP to LLM-integrated applications, where an LLM input contains a trusted prompt (instruction) and an untrusted data. The data may contain injected instructions …
Understanding RAG Part IX: Fine-Tuning LLMs for RAG
Be sure to check out the previous articles in this series: •
How to Perform Scikit-learn Hyperparameter Optimization with Optuna
Optuna is a machine learning framework specifically designed for automating hyperparameter optimization , that is, finding an externally fixed setting of machine learning model hyperparameters that optimizes the model’s performance.