# Engineering & Deep Dives > Technical articles on RaBitQ quantization, DiskANN vs HNSW, hybrid BM25 search, ColBERT reranking, and large-scale PostgreSQL vector benchmarks. --- LLMS index: [llms.txt](/llms.txt) --- Section pages: - [Scaling Vector Search to 1 Billion on PostgreSQL](/blog/post/scaling-vector-search-to-1-billion-on-postgresql/): Fast Indexing in 2 Hours Using One Machine - [How We Made 100M Vector Indexing in 20 Minutes Possible on PostgreSQL](/blog/post/how-we-made-100m-vector-indexing-in-20-minutes-possible-on-postgresql/): In the past few months, we’ve heard consistent feedback from users and partners: while our goal of providing a scalable, high-performance alternative to… - [Bringing Search‑Engine Ranking to PostgreSQL with VectorChord‑BM25](/blog/post/bringing-searchengine-ranking-to-postgresql-with-vectorchordbm25/): Modern applications rely on PostgreSQL for its fully ACID‑compliant, expressive SQL, and rich ecosystem of extensions. The database handles relational… - [Optimize RAG with Contextual Retrieval in PostgreSQL](/blog/post/optimize-rag-with-contextual-retrieval-in-postgresql/): Enhance generation in language models using PostgreSQL for contextual retrieval with vector search and keyword bm25 scoring. - [VectorChord: Cost-Efficient Upload & Search of 400 Million Vectors on AWS](/blog/post/vectorchord-cost-efficient-upload-and-search-of-400-million-vectors-on-aws/): Upload, index, and search 400M vectors with VectorChord and PostgreSQL. Includes hardware tips and search performance advice - [All-in-one VectorChord Suite: Building Production-Ready RAG Solutions Directly in PostgreSQL](/blog/post/all-in-one-vectorchord-suite-building-production-ready-rag-solutions-directly-in-postgresql/): Build production-ready RAG solutions in PostgreSQL with VectorChord Suite's vector search, BM25 ranking, and flexible tokenization extensions - [Introducing Vechord: Turn PostgreSQL into your search engine in a Pythonic way.](/blog/post/introducing-vechord-turn-postgresql-into-your-search-engine-in-a-pythonic-way/): Turn PostgreSQL into a powerful search engine with Vechord, a Python library for seamless vector and keyword search - [Beyond Text: Unlock OCR-Free RAG in PostgreSQL with Modal & VectorChord](/blog/post/beyond-text-unlock-ocr-free-rag-in-postgresql-with-modal-and-vectorchord/): Building effective Retrieval-Augmented Generation (RAG) systems for documents often feels like wrestling with messy, complex pipelines. Especially when… - [3 Billion Vectors in PostgreSQL to Protect the Earth](/blog/post/3-billion-vectors-in-postgresql-to-protect-the-earth/): Perform ​large-scale vector search in PostgreSQL with ​3 billion+ vectors—powered by ​VectorChord. Get ​fast, scalable similarity search. - [Vector Search Over PostgreSQL: A Comparative Analysis of Memory and Disk Solutions](/blog/post/vector-search-over-postgresql-a-comparative-analysis-of-memory-and-disk-solutions/): Vector Search in PostgreSQL: Comparing VectorChord, pgvector, and pgvectorscale for Memory and Disk Performance - [PostgreSQL Full-Text Search: Fast When Done Right (Debunking the Slow Myth)](/blog/post/postgresql-full-text-search-fast-when-done-right-debunking-the-slow-myth/): Boost PostgreSQL full-text search speed by 50x with simple optimizations. Use VectorChord-BM25 to accelerate and better BM25 ranking in postgres. - [VectorChord-BM25: Introducing pg_tokenizer—A Standalone, Multilingual Tokenizer for Advanced Search](/blog/post/vectorchord-bm25-introducing-pgtokenizera-standalone-multilingual-tokenizer-for-advanced-search/): We're excited to announce the release of VectorChord-BM25 version 0.2, our PostgreSQL extension designed to bring advanced BM25-based full-text search… - [Hybrid search with Postgres Native BM25 and VectorChord](/blog/post/hybrid-search-with-postgres-native-bm25-and-vectorchord/): Hybrid search combining BM25 and pgvector compatible extension VectorChord, seamlessly integrated within PostgreSQL. - [Vector Search at 10,000 QPS in PostgreSQL with VectorChord](/blog/post/vector-search-at-10000-qps-in-postgresql-with-vectorchord/): VectorChord, the successor to pgvecto.rs, is a PostgreSQL extension for vector search, scaling up to 10,000 QPS with ease. - [VectorChord-BM25: Revolutionize PostgreSQL Search with BM25 Ranking — 3x Faster Than ElasticSearch](/blog/post/vectorchord-bm25-revolutionize-postgresql-search-with-bm25-ranking-3x-faster-than-elasticsearch/): VectorChord-BM25 enhances PostgreSQL search with BM25 ranking, 3x faster than ElasticSearch. Supports BERT, Tocken, and Unicode tokenizers - [Do we really need a specialized vector database? (2023)](/blog/post/do-we-really-need-a-specialized-vector-database-2023/): Notice: This article, originally published in 2023, discusses the relevance and necessity of specialized vector databases, particularly in relation to… - [Supercharge vector search with ColBERT rerank in PostgreSQL](/blog/post/supercharge-vector-search-with-colbert-rerank-in-postgresql/): Learn to enhance vector search accuracy with ColBERT rerank using PostgreSQL and VectorChord in this comprehensive tutorial - [ARM + VectorChord: Affordable, Fast Vector Search](/blog/post/arm-vectorchord-affordable-fast-vector-search/): ARM64 servers like AWS Graviton save costs. VectorChord - 26x cheaper than pgvector. Optimized for ARM64/x86, it delivers fast, efficient vector search - [Why HNSW is Not the Answer](/blog/post/why-hnsw-is-not-the-answer/): HNSW (Hierarchical Navigable Small World) has become the go-to algorithm for many vector databases. Its multi-layered graph structure and ability to… - [Benefits and Steps of External Centroids Building in VectorChord](/blog/post/benefits-and-steps-of-external-centroids-building-in-vectorchord/): Enhance vector search efficiency with external centroids building in VectorChord using external resources and hierarchical K-means - [VectorChord: Store 400k Vectors for $1 in PostgreSQL](/blog/post/vectorchord-store-400k-vectors-for-1-in-postgresql/): Introducing VectorChord: The successor to pgvecto.rs. Using VectorChord, you can achieve a QPS of 131 with 0.95 precision on 100 million 768D dataset - [Introducing PGVecto.rs Cloud - Scalable Vector Search in PostgreSQL, Now in the Cloud](/blog/post/introducing-pgvectors-cloud-scalable-vector-search-in-postgresql-now-in-the-cloud/): In an exciting development, we are thrilled to announce the launch of PGVecto.rs Cloud - bringing the power of scalable vector search to your PostgreSQL… - [Introducing Terraform Support for PGVecto.rs Cloud](/blog/post/introducing-terraform-support-for-pgvectors-cloud/): Use Terraform to manage PGVecto.rs Cloud like your other infrastructure components - [Unleash the power of sparse vector](/blog/post/unleash-the-power-of-sparse-vector/): Unlock the potential of data pipelines with pure vector search using sparse vectors, BGE-M3, and pgvecto.rs - [pg_bestmatch.rs: Elevate Your PostgreSQL Text Queries with BM25](/blog/post/pgbestmatchrs-elevate-your-postgresql-text-queries-with-bm25/): Postgres BM25 full-text search, better RAG, hybrid search - [My binary vector search is better than your FP32 vectors](/blog/post/my-binary-vector-search-is-better-than-your-fp32-vectors/): Binary Vector Search: The 30x Memory Reduction Revolution with Preserved Accuracy - [pgvector vs. pgvecto.rs in 2024: A Comprehensive Comparison for Vector Search in PostgreSQL](/blog/post/pgvector-vs-pgvectors-in-2024-a-comprehensive-comparison-for-vector-search-in-postgresql/): In this blog post, we will illustrate the differences between pgvector and pgvecto.rs. - [Building LLM Applications in LangChain using pgvecto.rs](/blog/post/building-llm-applications-in-langchain-using-pgvectors/): Supercharge your LLM (Large Language Model) applications in LangChain by leveraging the powerful capabilities of pgvecto.rs - [Building the RAG pipeline with LlamaIndex and pgvecto.rs](/blog/post/building-the-rag-pipeline-with-llamaindex-and-pgvectors/): In this blog post, we will show you how to build a RAG pipeline with pgvecto.rs and LlamaIndex. - [Do we really need a specialized vector database?](/blog/post/do-we-really-need-a-specialized-vector-database/): With the popularity of LLM (Large Language Model), vector databases have also become a hot topic. With just a few lines of simple Python code, a vector…