10 тысяч подписчиков
186 видео
The difference between multi-agent and multiple agent systems and when to use them. #short
RAG for Complex PDFs
Production-Ready Optimization Strategies for RAG
OmniScience
Synthetic Data for Enterprise
Drug Alert AI
AI Makerspace is in Toronto!
Fine-Tuning Embeddings for Better Retrieval
Better Agents with LlamaIndex Workflows
The AI Engineering Bootcamp Cohort 4
Healthcare Technology Management LLM (HTM-LLM)
Continued Pretraining and Fine-Tuning with Unsloth
Using synthetic data is about helping us incrementally raise the bar on fine-tuning.
RAG for Complex PDFs with LlamaParse and LlamaIndex v0.10
High-performance RAG with LlamaIndex
DSPy forces you to think about your problem in very simple terms.
Inference & GPU Optimization: GPTQ
Determining which models to use and learning from the history of model performance.
Swarm: Multi-Agent Orchestration
Codex: The Autonomous SWE
How is the Spectrum system useful when training SLM’s?
Spectrum: Training Domain-Adapted SLMs
Is Mixture of Agents (MoA) the same as Mixture of Experts (MoE)?
The difference between multi-agent and multiple agent systems and when to use them.
LangGraph Studio: An
Reinforcement Learning with AI Feedback (RLAIF) | Constitutional AI
Why Spectrum isn’t just another technique to optimize fine-tuning.
01: Introduction to LLM Engineering, [Session 1 of Full Course, LLM Engineering Cohort 3]
Dive into the evolution of AI optimization
Increase efficiency and save money fine-tuning with Unsloth.
OpenAI GPTs: Building Your First No-Code GPT
AWS Agent Squad
When would you choose Spectrum over QLoRA, or when would you combine them?
Building agentic systems using DSPy AvaTar modules.
DSPy is a set of controls at the input level for better outputs
How to Build ChatGPT - Part 3: Agentic Search & Agents SDK
Google ADK: Agent Development Kit
Cursor: An AI Engineer’s Guide to Vibe Coding and Beyond
LlamaIndex: Building RAG Applications with Multiple Data Sources
RAGalicious by Mike Khaw and Jie Zhou
ERROR infinite loop detected!
Fine-Tuning Mistral-7B with LoRA (Low Rank Adaptation)
Multi-Agent Systems for Everyone
DSPy: Advanced Agents?
Multi-Agent RAG with
PydanticAI: From Data Validation to Agents
We can use synthetic data at every layer of the stack!
How do we use DSPy with the AvaTar framework?
AG2: AutoGen, Evolved
Q&A for Fine-Tuning Embeddings for Better Retrieval
What is Context Precision and how does it improve our fine-tuning actions?
