Agentic RAG Explained
Agentic RAG is retrieval-augmented generation where an AI agent controls the retrieval process instead of relying on one…
Read moreTopic
LLM Integration
RAG, semantic search, chunking, agents, and embedding models.
Advanced RAG Patterns
Advanced RAG patterns help a retrieval system move beyond one simple vector search followed by one generated answer.…
Read more
HyDE: Hypothetical Document Embeddings for Better Retrieval
HyDE, short for Hypothetical Document Embeddings, is a retrieval technique that asks a language model to generate a…
Read more
Query Rewriting and Expansion for Better AI Database Retrieval
Query rewriting and expansion improve retrieval by transforming a user’s original question into search inputs that better match…
Read more
Re-ranking in RAG Pipelines
Re-ranking improves a RAG pipeline by adding a second retrieval stage that carefully reorders the most promising results…
Read more
Hybrid Search for RAG
Hybrid search for retrieval-augmented generation combines dense vector retrieval with keyword retrieval so a RAG system can find…
Read more
Fine-Tuning Embedding Models for Your Domain
Fine-tuning an embedding model for your domain means teaching a general-purpose model which pieces of text should be…
Read more
Comparing Embedding Models with MTEB
MTEB, short for Massive Text Embedding Benchmark, helps compare embedding models across many tasks such as retrieval, classification,…
Read more
How to Choose an Embedding Model
Choosing an embedding model is a retrieval decision, not just a machine learning decision. The best model for…
Read more
How to Choose Chunk Size and Overlap
Chunk size and overlap determine what an AI database stores, retrieves, and sends into a generation model. Small…
Read more