Beginner

Vector Databases — Beginner

Foundational five-day path through vector databases, embeddings, knowledge graph basics, LLMs, and a first RAG pipeline.

5 lessons ~300 min total
  1. 1

    Your First Vector Database

    What a vector database actually is, the five operations every vendor exposes, why metadata is the hidden 80% of the job, how to pick between Pinecone, Weaviate, Qdrant, pgvector and Chroma, and the six failure modes that bite first-time users.

    45 minVector DB APIsMetadata FilteringDB Selection
  2. 2

    Understanding Embeddings

    Master the art of converting text, images, and other data into vector embeddings. Learn how embedding models work and how to choose the right one for your use case.

    55 minText EmbeddingsOpenAI ModelsSentence Transformers
  3. 3

    What are Knowledge Graphs?

    Learn how knowledge graphs model entities and relationships as nodes and edges, traverse them with multi-hop queries, and when to reach for a graph instead of a relational or vector database.

    60 minEntitiesRelationshipsMulti-hop Queries
  4. 4

    LLM Fundamentals

    Understand how large language models actually work — transformers, tokenization, prompting, sampling strategies, and the context window constraints that shape every LLM-powered system.

    65 minTransformersTokenizationContext Windows
  5. 5

    Your First RAG System

    The beginner capstone — build a complete Retrieval-Augmented Generation pipeline that combines everything from the last four days: vector search, knowledge graphs, and LLMs working together.

    75 minRAGCapstoneEnd-to-End Pipeline