Venelin Valkov Courses

Nanonets OCR Small - Free Model to Turn Your Documents into Data for AI

Explore Nanonets OCR Small, a fine-tuned Qwen2.5-VL model that converts documents to Markdown, extracting tables, equations, signatures, and watermarks for AI applications.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

The Illusion of Thinking - Can We Trust AI's Chain of Thought?

Uncover how AI models fabricate reasoning after choosing answers, creating plausible lies to hide their true decision-making process and why you shouldn't trust their explanations.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

How RAG Finds Answers in Millions of Documents - Embeddings, Vector Databases, LangChain and Supabase

Master building semantic search systems that scale to millions of documents using embeddings, vector databases, and LangChain for powerful RAG applications.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

GPT-OSS - OpenAI Open-Weight Reasoning Models - Ollama Test, Benchmarking, and Safety Analysis

Explore OpenAI's new open-weight reasoning models through benchmarks and Ollama testing to evaluate their real-world performance beyond published metrics.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

Build Local MCP Server for Cursor/VSCode/Claude Code - Convert PDF to Markdown with Docling and MCP

Build a Model Context Protocol server that converts PDF files to Markdown using Docling and Python, then integrate it with Cursor for AI-powered content processing.

• YouTube
• 10 minutes
• Self-Paced
• Free Video

Gemini CLI - First Look and NextJS RAG App Test

Explore Google's free Gemini CLI, an open-source AI terminal agent, and compare it with Claude Code through hands-on NextJS RAG application testing.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Gemini CLI + MCP Tools Deep Dive - Build a Completely Local RAG with Ollama, Context7, and NextJS

Master building a local RAG system using Gemini CLI with MCP tools, Ollama, and NextJS to create a document chat application with file upload capabilities.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

Gemma 3n - Open Multimodal Model by Google - Image, Audio, Video and Text Installation and Testing

Explore Google's Gemma 3n multimodal AI model handling images, audio, video & text. Install, test capabilities, and evaluate performance in Google Colab for mobile deployment.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

Jan-Nano 4B 128k Context - Optimized for Deep Research and MCP - Local MCP Agent with Ollama

Discover how to build a local AI agent using Jan-Nano 4B model with Ollama for deep research tasks and MCP tool calling in just 14 minutes.

• YouTube
• 14 minutes
• Self-Paced
• Free Video

Why Your RAG Gives Wrong Answers and 4 Chunking Strategies to Fix It - LangChain Text Splitters

Discover 4 advanced chunking strategies to fix RAG systems that give wrong answers, including semantic, structure-aware, and LLM-driven approaches with practical implementations.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

Grok 4 - Reasoning AI Model by xAI - Train/Test Compute, Benchmarks, Tool Use, Pricing, API Access

Explore Grok 4, xAI's most powerful reasoning AI model, covering benchmarks, compute capabilities, pricing, API access, and upcoming features in this comprehensive overview.

• YouTube
• 12 minutes
• Self-Paced
• Free Video

FLUX.1 Kontext [dev] Local Test - Image Generation and Edit with HuggingFace Open Weights Model

Explore FLUX.1 Kontext's 12B parameter model for AI image generation and editing with consistent character creation using HuggingFace's open weights implementation.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

Use Any LLM Provider with LiteLLM - Use ChatGPT, Claude, Gemini, Ollama with One API

Master LiteLLM to seamlessly switch between ChatGPT, Claude, Gemini, and Ollama using a unified OpenAI-like API, avoiding vendor lock-in while enabling structured outputs and tool calling.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

Build AI Agent from 0 to Production Deployment - LangChain, Ollama, MLflow and Docker Full Tutorial

Master building AI agents from scratch to production deployment using LangChain, Ollama, MLflow & Docker with tools, tracing, and REST API integration.

• YouTube
• 28 minutes
• Self-Paced
• Free Video

OCRFlux-3B - Local OCR AI Model Test - Turn PDFs into Markdown

Explore OCRFlux-3B, a fine-tuned Qwen2.5-VL model that converts document images to markdown, outperforming competitors on benchmarks through hands-on testing with financial statements and receipts.

• YouTube
• 11 minutes
• Self-Paced
• Free Video