RAG systems

Chunking, embeddings, vector stores, and retrieval quality.

11·Free resources

0 of 11 resources completed

Docs35 min
LlamaIndex - RAG introduction
Indexing, querying, and evaluation primitives.
Open resource
Docs45 min
LangChain - RAG from scratch
Loaders, splitters, embeddings, and retrievers end-to-end.
Open resource
Article20 min
Pinecone - What is vector search?
Cosine similarity, ANN indexes, and latency tradeoffs.
Open resource
Article25 min
Chunking strategies for RAG
Sentence, paragraph, and semantic chunking heuristics.
Open resource
Video40 min
Jerry Liu - Building production RAG (LlamaIndex)
Talk on ingestion pipelines and evaluation in the wild.
Open resource
Docs22 min
OpenAI - Embeddings guide
Model choice, dimensions, and batching embeddings.
Open resource
Article30 min
Anthropic - Contextual retrieval
Ideas for reducing hallucinations in long-document RAG.
Open resource
Article20 min
BEIR benchmark overview
How IR metrics translate to RAG quality signals.
Open resource
Docs18 min
Weaviate - Hybrid search
Combining BM25 and vector search for better recall.
Open resource
Docs28 min
Ragas - RAG evaluation framework
Faithfulness and answer-relevance metrics for pipelines.
Open resource
Article15 min
Simon Willison - Embeddings with SQL
Lightweight sqlite+vec pattern for small apps.
Open resource