Advanced Vector Search for LLM Applications
Chapter 1: Approximate Nearest Neighbor Algorithms
Revisiting Vector Embeddings and Search Fundamentals
Hierarchical Navigable Small Worlds (HNSW) Internals
Inverted File Index (IVF) Variations
Product Quantization (PQ) Mechanics
Other Graph-Based ANN Methods (e.g., NSG, Vamana)
Selecting the Right ANN Algorithm: Trade-offs
Hands-on Practical: Implementing and Tuning HNSW
Chapter 2: Optimizing Vector Search Performance and Efficiency
Quantization Techniques: Scalar vs. Product
Implementing Optimized Product Quantization (OPQ)
Binary Hashing and Locality Sensitive Hashing (LSH) Refresher
Advanced Filtering Strategies: Pre vs. Post Filtering
Indexing Metadata Efficiently alongside Vectors
Hardware Acceleration Considerations (CPU SIMD, GPU)
Memory Management and Caching Strategies
Practice: Applying Quantization and Filtering
Chapter 3: Hybrid Search Approaches
Limitations of Pure Vector Search
Integrating Keyword Search (BM25, TF-IDF)
Result Fusion and Ranking Strategies
Reciprocal Rank Fusion (RRF) and Other Fusion Algorithms
Graph-Based Augmentation for Vector Search
Multi-Modal Search Considerations
Hands-on Practical: Building a Hybrid Search Pipeline
Chapter 4: Scaling Vector Search for Production Systems
Distributed Vector Database Architectures
Sharding Strategies for Vector Indexes
Replication and High Availability
Load Balancing Search Queries
Monitoring Vector Search Performance Metrics
Index Updates and Maintenance in Production
Cost Optimization for Large-Scale Deployments
Practice: Configuring a Distributed Setup
Chapter 5: Advanced Tuning and Evaluation
Evaluation Metrics Revisited: Recall, Precision, Latency
Building Ground Truth Datasets for Evaluation
Parameter Sensitivity Analysis (HNSW, IVF)
A/B Testing Frameworks for Search Algorithms
Debugging Search Relevance Issues
Online vs. Offline Evaluation Techniques
Tuning for Specific Application Needs (RAG vs. Semantic Search)
Hands-on Practical: Comprehensive Performance Evaluation
Tuning for Specific Application Needs (RAG vs. Semantic Search)
Build LLM apps faster with Kerb
Cleaner syntax. Built-in debugging. Production-ready from day one.
Built for the AI systems behind ApX Machine Learning
Was this section helpful?
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks, Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela, 2020 NeurIPS, Vol. 33 DOI: 10.48550/arXiv.2005.11401 - Introduces the Retrieval-Augmented Generation (RAG) framework, offering foundational understanding of RAG's goals and the precision requirements for its retrieval component.
- RAGAs: Automated Evaluation of Retrieval-Augmented Generation Systems, Shahul Es, Jithin James, Luis Espinosa-Anke, Steven Schockaert, 2023 arXiv preprint DOI: 10.48550/arXiv.2309.15217 - Presents a framework for automated evaluation of RAG systems, which is highly relevant for understanding and implementing the end-to-end evaluation strategies discussed for RAG.
- Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs, Yu. A. Malkov, D. A. Yashunin, 2020 IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 42 (IEEE Computer Society) DOI: 10.1109/TPAMI.2018.2889473 - Details the HNSW algorithm, a popular vector indexing method. This helps in understanding parameters like
efSearchand the core recall/precision trade-offs in approximate nearest neighbor search. - An Introduction to Information Retrieval, Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, 2008 (Cambridge University Press) - A classic textbook covering fundamental concepts of information retrieval, including evaluation metrics such as Precision@k, Recall@k, MAP, and NDCG, essential for semantic search evaluation.
© 2025 ApX Machine LearningEngineered with