{"book":{"title":"AI-Native Vector Databases with PostgreSQL & pgvector","subtitle":"From Zero to Production RAG, Search, and Agent Memory","author":"Muhammad Usman Akbar","basePath":"/pgvector-book","publishedAt":"2026-07-31"},"chapters":[{"position":1,"slug":"about-this-book","title":"About This Book: Your Zero-to-Expert Path","section":"Start Here","description":"Learn how to use this beginner-first pgvector book to progress from one similarity query to evaluated, secure, production AI retrieval systems.","url":"https://muhammadusmanakbar.com/pgvector-book/about-this-book","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/about-this-book","updatedAt":"2026-07-31"},{"position":2,"slug":"ai-native-vector-database","title":"What Is an AI-Native Vector Database?","section":"Start Here","description":"Understand vector databases, embeddings, pgvector, and the full AI retrieval lifecycle before choosing an architecture or writing application code.","url":"https://muhammadusmanakbar.com/pgvector-book/ai-native-vector-database","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/ai-native-vector-database","updatedAt":"2026-07-31"},{"position":3,"slug":"postgresql-first-principles","title":"Relational Databases and PostgreSQL from First Principles","section":"Start Here","description":"Learn tables, rows, keys, constraints, transactions, indexes, schemas, clients, and servers before adding vectors to PostgreSQL.","url":"https://muhammadusmanakbar.com/pgvector-book/postgresql-first-principles","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/postgresql-first-principles","updatedAt":"2026-07-31"},{"position":4,"slug":"install-postgresql-pgvector","title":"Install PostgreSQL, pgvector, Python, and Docker","section":"Start Here","description":"Create a reproducible local pgvector lab with Docker, verify every tool and extension version, and understand native installation alternatives.","url":"https://muhammadusmanakbar.com/pgvector-book/install-postgresql-pgvector","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/install-postgresql-pgvector","updatedAt":"2026-07-31"},{"position":5,"slug":"first-vector-query","title":"Your First Vector Table and Similarity Query","section":"Start Here","description":"Create a pgvector table, insert tiny teaching vectors, run exact cosine and L2 searches, and prove how query direction changes ranking.","url":"https://muhammadusmanakbar.com/pgvector-book/first-vector-query","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/first-vector-query","updatedAt":"2026-07-31"},{"position":6,"slug":"vectors-without-intimidating-math","title":"Vectors Without Intimidating Mathematics","section":"Vectors and Embeddings","description":"Build an intuitive and practical understanding of vector coordinates, magnitude, direction, dimensions, neighborhoods, and high-dimensional limits.","url":"https://muhammadusmanakbar.com/pgvector-book/vectors-without-intimidating-math","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/vectors-without-intimidating-math","updatedAt":"2026-07-31"},{"position":7,"slug":"embeddings-models-tokens-dimensions","title":"Embeddings: Models, Tokens, Dimensions, and Meaning","section":"Vectors and Embeddings","description":"Understand how embedding models transform text and other inputs, why preprocessing and versions matter, and what semantic proximity can and cannot mean.","url":"https://muhammadusmanakbar.com/pgvector-book/embeddings-models-tokens-dimensions","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/embeddings-models-tokens-dimensions","updatedAt":"2026-07-31"},{"position":8,"slug":"distance-metrics","title":"L2, Cosine, Inner Product, L1, Hamming, and Jaccard Distance","section":"Vectors and Embeddings","description":"Choose and implement pgvector distance operators correctly, match metrics to model behavior, and avoid similarity-score and index-operator mistakes.","url":"https://muhammadusmanakbar.com/pgvector-book/distance-metrics","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/distance-metrics","updatedAt":"2026-07-31"},{"position":9,"slug":"normalization-dimensions-precision","title":"Normalization, Dimensions, Precision, and Model Compatibility","section":"Vectors and Embeddings","description":"Control vector shape, numeric precision, normalization, nullability, zero vectors, and embedding-version compatibility in pgvector schemas.","url":"https://muhammadusmanakbar.com/pgvector-book/normalization-dimensions-precision","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/normalization-dimensions-precision","updatedAt":"2026-07-31"},{"position":10,"slug":"choose-evaluate-embedding-model","title":"Choose and Evaluate an Embedding Model","section":"Vectors and Embeddings","description":"Select embedding models through workload constraints and labeled retrieval evidence instead of leaderboards, popularity, or one impressive demo.","url":"https://muhammadusmanakbar.com/pgvector-book/choose-evaluate-embedding-model","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/choose-evaluate-embedding-model","updatedAt":"2026-07-31"},{"position":11,"slug":"sql-essentials-ai-engineers","title":"SQL Essentials for AI Engineers","section":"PostgreSQL and pgvector Essentials","description":"Learn the SQL needed for vector applications: selection, parameters, joins, grouping, common table expressions, transactions, and safe query composition.","url":"https://muhammadusmanakbar.com/pgvector-book/sql-essentials-ai-engineers","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/sql-essentials-ai-engineers","updatedAt":"2026-07-31"},{"position":12,"slug":"schema-documents-chunks-metadata","title":"Schema Design for Documents, Chunks, Metadata, and Embeddings","section":"PostgreSQL and pgvector Essentials","description":"Design a durable pgvector schema that separates sources, documents, chunks, permissions, embedding versions, and derived retrieval state.","url":"https://muhammadusmanakbar.com/pgvector-book/schema-documents-chunks-metadata","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/schema-documents-chunks-metadata","updatedAt":"2026-07-31"},{"position":13,"slug":"pgvector-data-types","title":"pgvector Data Types: vector, halfvec, bit, and sparsevec","section":"PostgreSQL and pgvector Essentials","description":"Compare pgvector's dense, half-precision, binary, and sparse representations, their indexed limits, operators, casts, and use cases.","url":"https://muhammadusmanakbar.com/pgvector-book/pgvector-data-types","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/pgvector-data-types","updatedAt":"2026-07-31"},{"position":14,"slug":"exact-nearest-neighbor-search","title":"Exact Nearest-Neighbor Search","section":"PostgreSQL and pgvector Essentials","description":"Use pgvector's index-free exact search as a correctness baseline, add filters and thresholds safely, and understand the cost of scanning candidates.","url":"https://muhammadusmanakbar.com/pgvector-book/exact-nearest-neighbor-search","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/exact-nearest-neighbor-search","updatedAt":"2026-07-31"},{"position":15,"slug":"filters-joins-transactions","title":"Filters, Joins, Transactions, and Referential Integrity","section":"PostgreSQL and pgvector Essentials","description":"Combine vector retrieval with PostgreSQL metadata, joins, authorization predicates, constraints, and atomic writes without confusing filters with security.","url":"https://muhammadusmanakbar.com/pgvector-book/filters-joins-transactions","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/filters-joins-transactions","updatedAt":"2026-07-31"},{"position":16,"slug":"write-and-bulk-copy","title":"Insert, Upsert, Update, Delete, and Bulk COPY","section":"PostgreSQL and pgvector Essentials","description":"Write pgvector data safely with idempotent inserts, conflict handling, scoped updates and deletions, binary COPY, staging tables, and verification.","url":"https://muhammadusmanakbar.com/pgvector-book/write-and-bulk-copy","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/write-and-bulk-copy","updatedAt":"2026-07-31"},{"position":17,"slug":"python-typescript-clients","title":"Connect from Python and TypeScript Safely","section":"PostgreSQL and pgvector Essentials","description":"Use psycopg and node-postgres with registered pgvector types, connection pools, parameters, transactions, timeouts, and explicit application boundaries.","url":"https://muhammadusmanakbar.com/pgvector-book/python-typescript-clients","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/python-typescript-clients","updatedAt":"2026-07-31"},{"position":18,"slug":"extraction-normalization-provenance","title":"Document Extraction, Normalization, and Provenance","section":"Build the Ingestion System","description":"Turn files and records into trustworthy normalized documents while preserving source identity, versions, structure, checksums, permissions, and extraction evidence.","url":"https://muhammadusmanakbar.com/pgvector-book/extraction-normalization-provenance","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/extraction-normalization-provenance","updatedAt":"2026-07-31"},{"position":19,"slug":"chunking-structure-meaning","title":"Chunking by Structure and Meaning","section":"Build the Ingestion System","description":"Design addressable retrieval chunks using headings, paragraphs, tables, code, overlap, token budgets, parent context, and evaluation evidence.","url":"https://muhammadusmanakbar.com/pgvector-book/chunking-structure-meaning","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/chunking-structure-meaning","updatedAt":"2026-07-31"},{"position":20,"slug":"idempotent-pipelines-job-state","title":"Idempotent Embedding Pipelines and Job State","section":"Build the Ingestion System","description":"Build retry-safe ingestion with explicit states, leases, deterministic identities, checksums, optimistic concurrency, dead letters, and reconciliation.","url":"https://muhammadusmanakbar.com/pgvector-book/idempotent-pipelines-job-state","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/idempotent-pipelines-job-state","updatedAt":"2026-07-31"},{"position":21,"slug":"batches-rate-limits-backpressure","title":"Batch APIs, Rate Limits, Retries, and Backpressure","section":"Build the Ingestion System","description":"Control embedding throughput with bounded batches, quotas, adaptive concurrency, retry budgets, circuit breakers, queues, and lag-based backpressure.","url":"https://muhammadusmanakbar.com/pgvector-book/batches-rate-limits-backpressure","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/batches-rate-limits-backpressure","updatedAt":"2026-07-31"},{"position":22,"slug":"change-reembedding-deletion","title":"Change Detection, Re-embedding, Tombstones, and Deletion","section":"Build the Ingestion System","description":"Keep vector retrieval synchronized with changing sources through checksums, versioned visibility, deletion tombstones, reconciliation, and cache invalidation.","url":"https://muhammadusmanakbar.com/pgvector-book/change-reembedding-deletion","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/change-reembedding-deletion","updatedAt":"2026-07-31"},{"position":23,"slug":"model-migrations-zero-downtime","title":"Embedding-Model Migrations Without Downtime","section":"Build the Ingestion System","description":"Migrate embedding models using parallel columns or tables, backfills, separate ANN indexes, shadow evaluation, staged cutover, and reversible cleanup.","url":"https://muhammadusmanakbar.com/pgvector-book/model-migrations-zero-downtime","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/model-migrations-zero-downtime","updatedAt":"2026-07-31"},{"position":24,"slug":"multilingual-multimodal-multivector","title":"Multilingual, Multimodal, and Multi-Vector Records","section":"Build the Ingestion System","description":"Model language-aware text, image and audio embeddings, and multiple vector representations per record without mixing incompatible semantic spaces.","url":"https://muhammadusmanakbar.com/pgvector-book/multilingual-multimodal-multivector","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/multilingual-multimodal-multivector","updatedAt":"2026-07-31"},{"position":25,"slug":"exact-search-quality-baseline","title":"Exact Search as the Quality Baseline","section":"Retrieval Engineering","description":"Construct reproducible exact pgvector result sets, separate approximation recall from relevance, and benchmark filtered queries before ANN tuning.","url":"https://muhammadusmanakbar.com/pgvector-book/exact-search-quality-baseline","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/exact-search-quality-baseline","updatedAt":"2026-07-31"},{"position":26,"slug":"hnsw-indexes","title":"HNSW Indexes from Intuition to Tuning","section":"Retrieval Engineering","description":"Build and tune pgvector HNSW indexes with matching operator classes, construction/search parameters, recall experiments, and operational safeguards.","url":"https://muhammadusmanakbar.com/pgvector-book/hnsw-indexes","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/hnsw-indexes","updatedAt":"2026-07-31"},{"position":27,"slug":"ivfflat-indexes","title":"IVFFlat Indexes from Training to Tuning","section":"Retrieval Engineering","description":"Understand pgvector IVFFlat clustering, build timing, lists and probes, training-data distribution, recall tuning, and operational tradeoffs.","url":"https://muhammadusmanakbar.com/pgvector-book/ivfflat-indexes","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/ivfflat-indexes","updatedAt":"2026-07-31"},{"position":28,"slug":"filtered-ann-iterative-scans","title":"Filtered Approximate Search and Iterative Scans","section":"Retrieval Engineering","description":"Make filtered HNSW and IVFFlat searches return useful rows using selectivity analysis, iterative scans, partial indexes, partitioning, and plan tests.","url":"https://muhammadusmanakbar.com/pgvector-book/filtered-ann-iterative-scans","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/filtered-ann-iterative-scans","updatedAt":"2026-07-31"},{"position":29,"slug":"postgresql-full-text-search","title":"PostgreSQL Full-Text Search for Lexical Retrieval","section":"Retrieval Engineering","description":"Build language-aware PostgreSQL lexical search with tsvector, tsquery, GIN indexes, ranking, exact identifiers, and safe query parsing.","url":"https://muhammadusmanakbar.com/pgvector-book/postgresql-full-text-search","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/postgresql-full-text-search","updatedAt":"2026-07-31"},{"position":30,"slug":"hybrid-search-rrf","title":"Hybrid Search with Reciprocal Rank Fusion","section":"Retrieval Engineering","description":"Combine authorized PostgreSQL lexical and pgvector semantic candidates using Reciprocal Rank Fusion, deduplication, diversity, and evaluation.","url":"https://muhammadusmanakbar.com/pgvector-book/hybrid-search-rrf","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/hybrid-search-rrf","updatedAt":"2026-07-31"},{"position":31,"slug":"reranking-query-rewriting","title":"Reranking, Query Rewriting, and Multi-Query Retrieval","section":"Retrieval Engineering","description":"Improve pgvector candidates with controlled query rewriting, decomposition, expansion, cross-encoder reranking, fusion, and latency-aware fallbacks.","url":"https://muhammadusmanakbar.com/pgvector-book/reranking-query-rewriting","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/reranking-query-rewriting","updatedAt":"2026-07-31"},{"position":32,"slug":"metadata-freshness-diversity-rules","title":"Metadata Filters, Freshness, Diversity, and Business Rules","section":"Retrieval Engineering","description":"Blend semantic relevance with typed metadata, freshness, inventory, authority, deduplication, diversity, and explicit product policy.","url":"https://muhammadusmanakbar.com/pgvector-book/metadata-freshness-diversity-rules","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/metadata-freshness-diversity-rules","updatedAt":"2026-07-31"},{"position":33,"slug":"golden-dataset-evaluation","title":"Build a Golden Dataset and Evaluate Retrieval","section":"Retrieval Engineering","description":"Create governed relevance labels and calculate recall, precision, MRR, nDCG, no-result accuracy, latency, and statistical confidence for retrieval.","url":"https://muhammadusmanakbar.com/pgvector-book/golden-dataset-evaluation","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/golden-dataset-evaluation","updatedAt":"2026-07-31"},{"position":34,"slug":"complete-rag-lifecycle","title":"The Complete RAG Request Lifecycle","section":"RAG and Agentic Applications","description":"Understand production RAG from identity and retrieval through context, generation, citation validation, observability, feedback, and deletion.","url":"https://muhammadusmanakbar.com/pgvector-book/complete-rag-lifecycle","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/complete-rag-lifecycle","updatedAt":"2026-07-31"},{"position":35,"slug":"citation-first-rag-api","title":"Build a Citation-First RAG API","section":"RAG and Agentic Applications","description":"Implement a small provider-neutral RAG API with authorized pgvector retrieval, structured outputs, server-validated citations, timeouts, and tests.","url":"https://muhammadusmanakbar.com/pgvector-book/citation-first-rag-api","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/citation-first-rag-api","updatedAt":"2026-07-31"},{"position":36,"slug":"context-budgets-injection-boundaries","title":"Context Assembly, Token Budgets, and Prompt-Injection Boundaries","section":"RAG and Agentic Applications","description":"Assemble diverse evidence within token budgets while treating retrieved text as untrusted data and defending tool and policy boundaries.","url":"https://muhammadusmanakbar.com/pgvector-book/context-budgets-injection-boundaries","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/context-budgets-injection-boundaries","updatedAt":"2026-07-31"},{"position":37,"slug":"conversation-semantic-memory","title":"Conversation State, Summaries, and Semantic Memory","section":"RAG and Agentic Applications","description":"Separate short-term conversation state from durable semantic memory using explicit consent, salience, versioning, provenance, retrieval, and forgetting.","url":"https://muhammadusmanakbar.com/pgvector-book/conversation-semantic-memory","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/conversation-semantic-memory","updatedAt":"2026-07-31"},{"position":38,"slug":"agent-memory-tools-approval","title":"Agent Memory, Tool Retrieval, and Human Approval","section":"RAG and Agentic Applications","description":"Build policy-bounded agent memory and tool discovery with typed capabilities, least privilege, execution-time authorization, approval, and audit evidence.","url":"https://muhammadusmanakbar.com/pgvector-book/agent-memory-tools-approval","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/agent-memory-tools-approval","updatedAt":"2026-07-31"},{"position":39,"slug":"recommendations-similarity-features","title":"Recommendations and Similarity Features Beyond RAG","section":"RAG and Agentic Applications","description":"Use pgvector for related items, content-based recommendations, duplicate detection, clustering support, and human-reviewed similarity features.","url":"https://muhammadusmanakbar.com/pgvector-book/recommendations-similarity-features","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/recommendations-similarity-features","updatedAt":"2026-07-31"},{"position":40,"slug":"caching-streaming-fallbacks","title":"Caching, Streaming, Fallbacks, and Graceful Degradation","section":"RAG and Agentic Applications","description":"Design secure cache keys, invalidation, streamed responses, stage deadlines, circuit breakers, and evidence-aware fallbacks for AI retrieval systems.","url":"https://muhammadusmanakbar.com/pgvector-book/caching-streaming-fallbacks","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/caching-streaming-fallbacks","updatedAt":"2026-07-31"},{"position":41,"slug":"query-plans-latency-recall-throughput","title":"Measure Query Plans, Latency, Recall, and Throughput","section":"Production PostgreSQL","description":"Read PostgreSQL plans and benchmark pgvector with EXPLAIN ANALYZE BUFFERS, exact recall, warm and cold latency, concurrency, and end-to-end traces.","url":"https://muhammadusmanakbar.com/pgvector-book/query-plans-latency-recall-throughput","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/query-plans-latency-recall-throughput","updatedAt":"2026-07-31"},{"position":42,"slug":"memory-maintenance-vacuum-index-builds","title":"Memory, Maintenance, Vacuum, and Index Builds","section":"Production PostgreSQL","description":"Operate pgvector tables with memory budgets, autovacuum, analyze, HNSW and IVFFlat builds, concurrent indexing, bloat observation, and safe maintenance.","url":"https://muhammadusmanakbar.com/pgvector-book/memory-maintenance-vacuum-index-builds","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/memory-maintenance-vacuum-index-builds","updatedAt":"2026-07-31"},{"position":43,"slug":"connections-pooling-concurrency","title":"Connections, Pooling, Transactions, and Concurrency","section":"Production PostgreSQL","description":"Control PostgreSQL connection cost, pool sizing, transaction scope, timeouts, cancellation, prepared state, and concurrent vector workloads.","url":"https://muhammadusmanakbar.com/pgvector-book/connections-pooling-concurrency","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/connections-pooling-concurrency","updatedAt":"2026-07-31"},{"position":44,"slug":"row-security-multitenancy","title":"Row-Level Security and Multi-Tenant Isolation","section":"Production PostgreSQL","description":"Enforce tenant isolation with PostgreSQL roles, row-level security, transaction-local identity, server-derived policy, tests, and operational defense in depth.","url":"https://muhammadusmanakbar.com/pgvector-book/row-security-multitenancy","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/row-security-multitenancy","updatedAt":"2026-07-31"},{"position":45,"slug":"encryption-secrets-privacy-audit","title":"Encryption, Secrets, Privacy, Retention, and Audit","section":"Production PostgreSQL","description":"Protect vector systems with TLS, storage encryption, least privilege, secret rotation, data minimization, retention, deletion, and useful audit records.","url":"https://muhammadusmanakbar.com/pgvector-book/encryption-secrets-privacy-audit","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/encryption-secrets-privacy-audit","updatedAt":"2026-07-31"},{"position":46,"slug":"backup-pitr-replication-ha","title":"Backups, Point-in-Time Recovery, Replication, and High Availability","section":"Production PostgreSQL","description":"Protect pgvector data with tested backups, WAL archiving, point-in-time recovery, replicas, failover, recovery objectives, and index-aware drills.","url":"https://muhammadusmanakbar.com/pgvector-book/backup-pitr-replication-ha","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/backup-pitr-replication-ha","updatedAt":"2026-07-31"},{"position":47,"slug":"observability-slos-drift-incidents","title":"Observability, SLOs, Incident Response, and Quality Drift","section":"Production PostgreSQL","description":"Observe pgvector across database health, ingestion freshness, retrieval quality, RAG stages, privacy, SLOs, alerts, drift, and incident response.","url":"https://muhammadusmanakbar.com/pgvector-book/observability-slos-drift-incidents","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/observability-slos-drift-incidents","updatedAt":"2026-07-31"},{"position":48,"slug":"zero-downtime-releases-rollback","title":"Zero-Downtime Migrations, Releases, and Rollback","section":"Production PostgreSQL","description":"Release pgvector schema, indexes, ingestion, retrieval, and model changes through expand-migrate-contract, feature flags, canaries, and rehearsed rollback.","url":"https://muhammadusmanakbar.com/pgvector-book/zero-downtime-releases-rollback","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/zero-downtime-releases-rollback","updatedAt":"2026-07-31"},{"position":49,"slug":"partition-vectors","title":"Partition Vectors by Tenant, Time, Language, or Model","section":"Scale and Advanced Techniques","description":"Use PostgreSQL partitioning for pruning, lifecycle, isolation, and maintenance only when workload predicates and operational evidence justify complexity.","url":"https://muhammadusmanakbar.com/pgvector-book/partition-vectors","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/partition-vectors","updatedAt":"2026-07-31"},{"position":50,"slug":"quantization-sparse-subvectors","title":"Half Precision, Binary Quantization, Sparse Vectors, and Subvectors","section":"Scale and Advanced Techniques","description":"Reduce pgvector search footprint with halfvec, binary signatures, sparse vectors, and subvectors while preserving full-precision reranking and measured recall.","url":"https://muhammadusmanakbar.com/pgvector-book/quantization-sparse-subvectors","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/quantization-sparse-subvectors","updatedAt":"2026-07-31"},{"position":51,"slug":"two-stage-expression-indexes","title":"Two-Stage Retrieval and Expression Indexes","section":"Scale and Advanced Techniques","description":"Build coarse-to-fine pgvector retrieval with expression indexes, oversampled candidates, exact reranking, materialized ordering, and measurable recall.","url":"https://muhammadusmanakbar.com/pgvector-book/two-stage-expression-indexes","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/two-stage-expression-indexes","updatedAt":"2026-07-31"},{"position":52,"slug":"scaling-replicas-sharding","title":"Vertical Scaling, Read Replicas, Sharding, and Distributed PostgreSQL","section":"Scale and Advanced Techniques","description":"Scale pgvector through measured vertical resources, workload isolation, replicas, partitioning, and sharding while preserving global top-k and consistency.","url":"https://muhammadusmanakbar.com/pgvector-book/scaling-replicas-sharding","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/scaling-replicas-sharding","updatedAt":"2026-07-31"},{"position":53,"slug":"capacity-cost-modeling","title":"Capacity Planning and Cost Modeling","section":"Scale and Advanced Techniques","description":"Estimate pgvector rows, vector storage, indexes, WAL, backups, memory, compute, embedding and generation spend, growth, headroom, and unit economics.","url":"https://muhammadusmanakbar.com/pgvector-book/capacity-cost-modeling","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/capacity-cost-modeling","updatedAt":"2026-07-31"},{"position":54,"slug":"pgvector-vs-specialist-database","title":"When to Choose pgvector Versus a Specialist Vector Database","section":"Scale and Advanced Techniques","description":"Choose pgvector or a specialist vector database through workload evidence, consistency, filters, scale, features, operations, portability, risk, and cost.","url":"https://muhammadusmanakbar.com/pgvector-book/pgvector-vs-specialist-database","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/pgvector-vs-specialist-database","updatedAt":"2026-07-31"},{"position":55,"slug":"docker-development-environment","title":"A Reproducible Docker Development Environment","section":"Deployment and Integration","description":"Build a version-pinned local pgvector stack with health checks, migrations, fixtures, application services, safe secrets, tests, and complete cleanup.","url":"https://muhammadusmanakbar.com/pgvector-book/docker-development-environment","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/docker-development-environment","updatedAt":"2026-07-31"},{"position":56,"slug":"managed-postgresql","title":"Deploy pgvector on Managed PostgreSQL","section":"Deployment and Integration","description":"Evaluate and deploy pgvector on managed PostgreSQL with extension support, networking, identity, backups, replicas, upgrades, observability, and cost controls.","url":"https://muhammadusmanakbar.com/pgvector-book/managed-postgresql","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/managed-postgresql","updatedAt":"2026-07-31"},{"position":57,"slug":"orms-frameworks-boundaries","title":"ORMs, LangChain, LlamaIndex, and Abstraction Boundaries","section":"Deployment and Integration","description":"Use ORMs and AI frameworks without losing pgvector SQL visibility, schema ownership, authorization, migrations, evaluation, or portability.","url":"https://muhammadusmanakbar.com/pgvector-book/orms-frameworks-boundaries","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/orms-frameworks-boundaries","updatedAt":"2026-07-31"},{"position":58,"slug":"cicd-migrations-regression-tests","title":"CI/CD, Migrations, Fixtures, and Retrieval Regression Tests","section":"Deployment and Integration","description":"Deliver pgvector changes with ephemeral PostgreSQL, migration tests, deterministic fixtures, query-plan checks, golden retrieval gates, canaries, and rollback.","url":"https://muhammadusmanakbar.com/pgvector-book/cicd-migrations-regression-tests","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/cicd-migrations-regression-tests","updatedAt":"2026-07-31"},{"position":59,"slug":"semantic-product-search-capstone","title":"Beginner Capstone: Semantic Product Search","section":"Capstones and Reference","description":"Build a complete pgvector product search with exact identifiers, semantic retrieval, filters, hybrid fusion, evaluation, API tests, and a launch review.","url":"https://muhammadusmanakbar.com/pgvector-book/semantic-product-search-capstone","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/semantic-product-search-capstone","updatedAt":"2026-07-31"},{"position":60,"slug":"governed-citation-rag-capstone","title":"AI Capstone: Governed Citation-First RAG","section":"Capstones and Reference","description":"Build and evaluate a multi-tenant citation-first RAG assistant with governed ingestion, hybrid retrieval, RLS, injection defense, and recovery.","url":"https://muhammadusmanakbar.com/pgvector-book/governed-citation-rag-capstone","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/governed-citation-rag-capstone","updatedAt":"2026-07-31"},{"position":61,"slug":"agent-memory-capstone","title":"Agent Capstone: Durable Memory with Approval Gates","section":"Capstones and Reference","description":"Build a consent-aware agent memory and tool system with pgvector retrieval, typed policy, corrections, expiry, approvals, idempotency, and audit.","url":"https://muhammadusmanakbar.com/pgvector-book/agent-memory-capstone","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/agent-memory-capstone","updatedAt":"2026-07-31"},{"position":62,"slug":"production-launch-checklist","title":"Production Launch Checklist and Architecture Review","section":"Capstones and Reference","description":"Review a pgvector system across purpose, data, retrieval, security, reliability, performance, operations, governance, cost, and launch evidence.","url":"https://muhammadusmanakbar.com/pgvector-book/production-launch-checklist","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/production-launch-checklist","updatedAt":"2026-07-31"},{"position":63,"slug":"troubleshooting-sql-cookbook","title":"Troubleshooting Playbook and SQL Cookbook","section":"Capstones and Reference","description":"Diagnose pgvector installation, dimensions, missing indexes, low recall, filtered results, slow builds, bloat, queues, RLS, and recovery with evidence.","url":"https://muhammadusmanakbar.com/pgvector-book/troubleshooting-sql-cookbook","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/troubleshooting-sql-cookbook","updatedAt":"2026-07-31"},{"position":64,"slug":"glossary-learning-map-next-steps","title":"Glossary, Learning Map, and Next Steps","section":"Capstones and Reference","description":"Review essential pgvector, PostgreSQL, retrieval, RAG, agent, security, and operations terms, then choose a concrete path to continued mastery.","url":"https://muhammadusmanakbar.com/pgvector-book/glossary-learning-map-next-steps","contentApi":"https://muhammadusmanakbar.com/api/pgvector-book-content/glossary-learning-map-next-steps","updatedAt":"2026-07-31"}]}