codefarm
HomeRoadmapsGuidesQuizzesMentorshipWhiteboardEbooksCodeSmash
Learn
RoadmapsQuizzesBlogsVideosGuides
Simulators
Why API GatewayWhy Load BalancerWhy Circuit BreakerKafka Message FlowKafka Consumer LagKafka RebalanceRate LimitersUptime SLALatency SimulatorCachingConsistent Hashing
Tools
UUID GeneratorDate & Time ToolsJWT DecoderText FormatterMind MapFun PuzzlesKids Learning
Profile
Back to Applied AI Engineering
🔍
Phase 5

Advanced Retrieval & Search Infrastructure

The algorithms that make vector search fast at scale, combining keyword and semantic search with re-ranking, and rewriting queries before they hit the index.

1

Vector Search Internals: HNSW, IVF & Product Quantization

Why exact vector search falls over at scale, and how HNSW, IVF, and Product Quantization trade a little recall for a lot of speed.

hnswivfvector-search
2

Hybrid Search & Re-ranking

Why pure semantic search misses exact error codes and product IDs, and how combining it with keyword search plus a cross-encoder re-ranker fixes it.

hybrid-searchbm25re-ranking
3

Query Rewriting: Expansion, HyDE & Multi-Query

What to do when the user's own words are the problem — rewriting a query before it ever reaches the index, instead of tuning retrieval further.

hydequery-rewritingmulti-query
codefarm

Learn backend engineering with clear roadmaps, practical tools, and interactive quizzes. From zero to production-ready.

Learn

  • Roadmaps
  • Guides
  • Blogs
  • Videos
  • Ebooks

Labs

  • Simulators
  • Quizzes
  • Whiteboard
  • JWT Decoder
  • UUID Generator
  • Toolbox

Simulators

  • Uptime SLA
  • Rate Limiters
  • Kafka Message Flow
  • Kafka Consumer Lag
  • Kafka Rebalance

Community

  • Cohorts
  • Testimonials
  • About
  • Contact

Legal

  • Terms & Conditions
  • Privacy Policy
  • Refund & Cancellation