Course Overview
Master retrieval-augmented generation to build AI systems that leverage your organization's knowledge. From basic vector search to advanced GraphRAG implementations.
1
Embeddings & Vector Search
Understanding text embeddings, similarity search, and choosing the right embedding model for your use case.
OpenAI Embeddings
Cohere
Cosine Similarity
2
Vector Databases
Pinecone, Weaviate, Chroma, and Qdrant. Indexing strategies, metadata filtering, and scaling considerations.
Pinecone
Weaviate
Chroma
3
RAG Pipeline Design
Chunking strategies, hybrid search, reranking, and handling multi-modal content.
Chunking
Hybrid Search
Reranking
4
GraphRAG & Knowledge Graphs
Combining graph databases with RAG. Entity extraction, relationship modeling, and graph-enhanced retrieval.
Neo4j
GraphRAG
Entity Extraction
Hands-On Exercises
- Build a document Q&A system with LangChain and Pinecone
- Implement semantic chunking strategies for different document types
- Create a hybrid search pipeline combining BM25 and vector search
- Deploy a RAG system with evaluation metrics
- Build a GraphRAG system for complex document relationships
- Optimize retrieval quality with reranking and query expansion
Ready to Transform Your Team?
Contact us to discuss your training needs and schedule a consultation.
Get in Touch