Learn
Newsletter
Roadmaps
New
Search
⌘K
Toggle theme
Toggle theme
Toggle menu
Retrieval-Augmented Generation Roadmap
What is RAG & Why it Matters
Embeddings Overview
Vector Databases Introduction
Foundations
LLMs & Their Limitations (Hallucinations, Context Limits)
Semantic Search vs Keyword Search
Word Embeddings (Word2Vec, GloVe, FastText)
Transformer-based Embeddings (BERT, OpenAI, Cohere)
Embedding Evaluation (Cosine Similarity, Dot Product)
Embeddings
Sentence & Document Embeddings
Dimensionality Reduction (PCA, UMAP, FAISS IVF)
FAISS (Facebook AI Similarity Search)
Weaviate
Chroma
Indexing & Partitioning Strategies
Vector Databases
Pinecone
Milvus
Elasticsearch & OpenSearch for Vectors
Dense vs Sparse Retrieval
Approximate Nearest Neighbor (ANN) Search
Metadata Filtering & Hybrid Queries
Retrieval Techniques
BM25 & Hybrid Search
Chunking Strategies (Fixed, Overlap, Semantic)
RAG Architecture (Retriever + Generator)
Context Window Management
LangChain for RAG
Integration with LLMs
Prompt Engineering for RAG
Chain-of-Thought + RAG
LlamaIndex for RAG
Improving Recall & Precision
Caching & Embedding Store Optimization
Query Expansion Techniques
Optimization
Re-ranking with Cross-Encoders
Dynamic Chunking & Adaptive Retrieval
Serving RAG Pipelines (FastAPI, Flask)
Latency Optimization
Scaling RAG with Distributed Databases
Deployment & Scaling
Vector Index Updates & Rebuilding
Monitoring & Evaluation (Groundedness, Faithfulness)
Document Q&A Bot with RAG
RAG-powered Chatbot for PDFs
RAG API Service with LangChain
Projects
Personal Knowledge Base Search
Hybrid Search System (BM25 + Embeddings)
Enterprise Knowledge Assistant (Multi-Source RAG)
RAG Architecture Q&A
Chunking & Retrieval Strategies
Case Studies (ChatGPT RAG, Enterprise Search)
Interview Preparation
Vector Databases Q&A
Latency vs Accuracy Tradeoffs
