Get AI summaries of any video or article — Sign up free

Venelin Valkov — Channel Summaries — Page 2

AI-powered summaries of 131 videos about Venelin Valkov.

131 summaries

No matches found.

gpt-oss - OpenAI Open-Weight Reasoning Models | Ollama test, Benchmaxing, Safetymaxing?

Venelin Valkov · 3 min read

OpenAI’s newly released open-weight reasoning models—GPT OSS 120B and GPT OSS 20B—sparked hype for matching closed-model performance on popular...

Open-Weight Reasoning ModelsBenchmarksSafety Behavior

Build AI Agent from 0 to Production Deployment | LangChain, Ollama, MLflow & Docker (Full Tutorial)

Venelin Valkov · 3 min read

A unit-conversion AI agent can be built end-to-end—from a single-tool loop to a streaming REST API—then packaged into a Docker container and deployed...

AI AgentsLangChain ToolsStreaming REST API

ML Project Template for 2025 - Build ML Pipelines with Python, uv, DVC, FastAPI, Docker

Venelin Valkov · 3 min read

A ready-to-use machine learning project template is positioned as a 2025 blueprint for taking a model from dataset creation to a production-style...

ML Project TemplateDVC PipelinesFastAPI Inference

AI Agents with LangGraph & Llama 3 | Control the Execution Flow and State of Your Agent Apps

Venelin Valkov · 2 min read

LangGraph is positioned as a way to control both the execution order and the evolving state of agentic applications—down to loops, branching, and...

LangGraphAgent StateTool Schemas

Build an AI Social Media Content Generator in 20 Minutes | AI Agents with LangGraph and Llama 3.1

Venelin Valkov · 2 min read

A LangGraph-based agent loop can turn technical input into platform-ready social posts for both Twitter and LinkedIn—while iterating through multiple...

LangGraph AgentsSocial Media GenerationTwitter vs LinkedIn Prompts

Build Private Chatbot wtih LangChain, Ollama and Qwen 2.5 | Local AI App with Private LLM

Venelin Valkov · 3 min read

A fully local “private chatbot” workflow can be built by combining LangChain’s message orchestration (via LangGraph), Ollama for on-device model...

Local AI ChatbotLangChainLangGraph

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

Venelin Valkov · 2 min read

OCRFlux (3B) is a 3B-parameter visual-language OCR fine-tune aimed at turning document images (including PDFs) into structured Markdown. In local...

OCR to MarkdownTable ExtractionLocal Model Inference

Gemini CLI - FREE? Claude Code by Google | First Look and NextJS RAG App Test

Venelin Valkov · 3 min read

Gemini CLI lands as a free, open-source “developer-terminal” layer for Google’s Gemini Code Assist, pairing a ChatGPT-like coding workflow with a...

Gemini CLIGemini Code AssistNextJS RAG

Build Production-Ready Retrieval RAG Pipeline in LangChain | Hybrid Search (BM25), Re-ranking & HyDE

Venelin Valkov · 2 min read

A production-ready RAG pipeline needs more than embeddings: it must reliably fetch the right chunks, even when users ask for exact numbers. A simple...

RAG PipelinesHybrid SearchBM25

Advanced AI Agents with LangGraph and Llama 3.1 | Analyze Bitcoin, Ethereum and Solana Markets

Venelin Valkov · 3 min read

An AI agent workflow built with LangGraph can generate cryptocurrency market reports by combining three streams of evidence: cached historical price...

LangGraph AgentsCrypto Market AnalysisOpenBB Data

ToDo list Embeddings with TensorFlow in JavaScript

Venelin Valkov · 3 min read

A practical path to “icon suggestions” for a to-do app hinges on turning short task text into numeric embeddings and then measuring similarity...

EmbeddingsText SimilarityTensorFlow.js

Build Local Long-Running AI Agent (Stop Your Agents from Getting Lost) | LangChain, Ollama, Pydantic

Venelin Valkov · 2 min read

Long-running AI agents often lose their footing as tasks stretch across multiple context windows—hallucinations creep in, code can be rewritten or...

Long-Running AgentsCheckpointingLangChain

DeepSeek R1 0528 - Better Coding & Tool Calling | Is It Faster Now?

Venelin Valkov · 3 min read

DeepSeek R1 0528’s update centers on making the model more usable for real-world coding agents by adding support for JSON output and function...

DeepSeek R1 0528Tool CallingJSON Output

Segment Anything by Meta Research: Image Segmentation with the Largest Dataset and Model Yet!

Venelin Valkov · 3 min read

Meta’s Segment Anything (SAM) is built to turn image segmentation into a “promptable” task: users can click, draw boxes, or provide text-like prompts...

Promptable SegmentationSegment AnythingSA-1B Dataset

Build Smarter AI Apps: Memory, Tools, Retrieval & Structured Output with Python, Pydantic & Ollama

Venelin Valkov · 3 min read

AI apps become meaningfully more useful when they’re given four upgrades beyond plain text prompting: memory, structured outputs, tool use, and...

MemoryStructured OutputTool Use

Advanced RAG Chunking: Contextual & Structural Chunking with LangChain & Ollama (100% Local)

Venelin Valkov · 3 min read

Turning a large, converted PDF markdown into retrieval-ready chunks is often where RAG pipelines lose both speed and accuracy. The core fix here is a...

RAG ChunkingContextual EnrichmentLangChain Splitters

Machine Learning Engineer Mock Interview for Meta (Facebook) with ChatGPT

Venelin Valkov · 3 min read

ChatGPT performs unevenly in a mock machine learning engineer interview for Meta: it delivers strong, technically correct answers on coding and many...

ChatGPT TrainingReinforcement Learning from Human FeedbackMachine Learning Interviewing

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

Venelin Valkov · 2 min read

Black Forest WS’s FLUX.1 Context Dev (open weights) is proving it can do more than image editing: it can also generate photorealistic images from...

FLUX.1 Context DevImage EditingText-to-Image

What is RAG? The Complete Tutorial - From Scratch to Deployed API on Production | LangChain & Ollama

Venelin Valkov · 3 min read

Retrieval-Augmented Generation (RAG) is positioned as the practical fix for a core limitation of “just stuff everything into the prompt” approaches:...

Retrieval-Augmented GenerationTF-IDF RetrievalPDF Ingestion

Situational Awareness: From GPT-4 to AGI | Compute, Algorithms & Unhobbling by OpenAI Ex-Employee

Venelin Valkov · 2 min read

The central claim is that rapid, compounding improvements in “effective compute” and model training methods could make automated AI research—and...

AGI TimelineEffective ComputeAgentic Systems

Deploying Local LLM but It Is Slow? Here's How to Fix It (Hopefully) | LLMOps with vLLM

Venelin Valkov · 2 min read

Deploying a local LLM can feel painfully slow when using the default Hugging Face Transformers inference pipeline, but switching to vLLM can cut...

Local LLM LatencyvLLM vs TransformersPaged Attention

Build 100% Local Advanced RAG System for Financial PDFs with Qwen 3.5 | Docling, LangGraph & Ollama

Venelin Valkov · 3 min read

A fully local “advanced RAG” stack for financial PDFs can be built end-to-end—PDF upload, parsing into citation-ready chunks, hybrid retrieval,...

Local RAGFinancial PDFsDocling Parsing

Build Private AI Assistant That Actually Remembers | Chatbot Memory with Ollama, LangChain & SQLite

Venelin Valkov · 3 min read

A fully local chatbot can keep “memory” across restarts by writing each conversation turn into a local SQL database and re-injecting that history...

Chatbot MemoryOllamaLangChain

Is RAG Dead in 2026? | Build Local RAG from First Principles

Venelin Valkov · 3 min read

Retrieval-Augmented Generation (RAG) is still considered necessary in 2026—not because large language models can’t answer, but because they often...

RAG ArchitectureLocal RAGTF-IDF Retrieval

Getting Started with LangGraph | Build Local Agentic Workflows and AI Agents with Ollama

Venelin Valkov · 2 min read

LangGraph is presented as a practical way to turn brittle, demo-only AI prototypes into maintainable agentic systems by replacing nested if/else...

LangGraph WorkflowsAI AgentsState Graphs

How RAG Finds Answers in Millions of Documents | Embeddings, Vector Databases, LangChain & Supabase

Venelin Valkov · 3 min read

Retrieval in RAG hinges on one practical step: turning a user question into a vector and then finding the most semantically similar document chunks...

RAG RetrievalEmbeddingsCosine Similarity

Llama 4 Test with Groq: Coding, Data Extraction, Data Labelling, Summarization, RAG

Venelin Valkov · 3 min read

Meta’s Llama 4 lineup—Scout (109B), Maverick (400B), and Behemoth (2T, still training)—arrives with headline claims built around huge context windows...

Llama 4Groq APIMixture of Experts

LangChain Tutorial: The Core Building Blocks | LLMs, JSON output, RAGs, Tools and Observability

Venelin Valkov · 3 min read

LangChain’s practical value comes from a small set of reusable building blocks: a unified way to call different LLM providers, structured outputs...

LangChain Building BlocksLLM Provider AbstractionJSON Structured Output

Gemini 2.0 Flash Thinking Test - Coding, Data Extraction, Summarization, Data Labelling, RAG

Venelin Valkov · 3 min read

Gemini 2.0 Flash Thinking is positioned as a fast “thinking-mode” variant that exposes its internal reasoning steps, and hands-on tests suggest that...

Gemini 2.0 Flash ThinkingChain-of-PromptingStructured Output

Build Dataset For Fine-Tuning and Evaluation with LLM | Sentiment Analysis for Financial News

Venelin Valkov · 2 min read

A practical workflow for building a sentiment-labeled dataset from financial news using a fast large language model (LLM) is the core takeaway: take...

Sentiment LabelingFinancial News DatasetLLM Annotation

Gemma 4 Local OCR Test with llama.cpp | How Accurate It Is for PDF Document Understanding (🔴 Live)

Venelin Valkov · 3 min read

Gemma 4 can perform surprisingly strong document understanding for local OCR-style extraction—especially when the goal is to recover layout and...

Local OCRGemma 4llama.cpp