LangChain Practical Labs
LangChain is a framework for building LLM applications. Learn to connect LLMs to tools, memory, and custom data sources.
Interactive Practice
Less theory. More hands-on understanding.
Hands-on technical tutorials for artificial intelligence engineers. Run local models with Ollama, connect Weaviate vector databases, orchestrate LangChain agent workflows, and evaluate benchmarks.
7 of 7 shown
AI-Native Vector Database with Weaviate & Ollama
Install Weaviate locally with Docker and Ollama, generate embeddings, and build semantic search workflows.
Data Quality Metrics for Large Language Models
A comprehensive framework for assessing and improving the quality of training data for large language models.
Ethical Considerations in Synthetic Data Generation
Addressing privacy, bias, and fairness concerns in the creation and use of synthetic datasets for AI training.
LLM Evaluation Framework
Open source methodology for evaluating large language models across accuracy, reasoning, and domain benchmarks.
Reinforcement Learning Lab
Developing intelligent agents that learn optimal decision-making strategies through interaction with their environment.
ML 101: A Gentle Introduction
Fundamental concepts of machine learning with an accompanying interactive Jupyter notebook for hands-on learning.
No labs matched your search keyword. Clear your query to see all labs.
!
A Good Lab Habit
Always inspect code snippets before running them locally. Use isolated environments like Python virtualenvs (`python -m venv .venv`) or disposable Docker containers to keep your dependencies clean.