Gen AI

Agents generate useful code quickly when the project is simple, documented, and predictable. Rails helps because it has strong conventions. MongoDB helps when the data already exists and the app does not need SQL migrations. The main rule is still KISS: complexity is the enemy. Use README as the Source of Truth The best optimization… more

Retrieval-Augmented Generation (RAG) promises to combine external knowledge sources with the capabilities of large language models. In theory, the concept is simple: retrieve the right information, provide it to the model, and generate an answer. In practice, many implementations fail to deliver the expected results. The problem is rarely the model itself. It is rarely… more

Multimodal RAG lets you search an image database with text or images, then generate intelligent responses. It combines three technologies: embedding model, vector database, and multimodal LLM. How the Landscape Changed in 7 Years Around 2019, we built data processing systems RAG with numpy, scikit-learn, RabbitMQ, and PostgreSQL. Today, the ecosystem shifted completely – instead… more

The legal industry faces a digital transformation challenge. Generative AI models offer tremendous potential – from automating document analysis to supporting legal opinion preparation. However, standard solutions like ChatGPT or public models carry risks that law firms cannot afford. A proprietary LLM/RAG system is the answer to these challenges. Why It’s Worth Investing in Your… more

I built my first RAG in 2019. The task was to create a product that worked like this: send a photo of clothing, the application suggests 10 most similar products and links to various stores. I needed to gather a database of stores, their products, and photos, then transform those images into vectors and embed… more