Skip to content

Engineering & Deep Dives

Scaling Vector Search to 1 Billion on PostgreSQL vector-database
How We Made 100M Vector Indexing in 20 Minutes Possible on PostgreSQL vectorsearch
Bringing Search‑Engine Ranking to PostgreSQL with VectorChord‑BM25 postgresqlvectorchord
VectorChord: Cost-Efficient Upload & Search of 400 Million Vectors on AWS postgresqlvectorchord
Optimize RAG with Contextual Retrieval in PostgreSQL contextual-retrieval
All-in-one VectorChord Suite: Building Production-Ready RAG Solutions Directly in PostgreSQL postgresqlvectorchord
Introducing Vechord: Turn PostgreSQL into your search engine in a Pythonic way. vectorsearch
Beyond Text: Unlock OCR-Free RAG in PostgreSQL with Modal & VectorChord ocrvectorchord
3 Billion Vectors in PostgreSQL to Protect the Earth postgresql
Vector Search Over PostgreSQL: A Comparative Analysis of Memory and Disk Solutions vectorchord
VectorChord-BM25: Introducing pg_tokenizer—A Standalone, Multilingual Tokenizer for Advanced Search vector-databasevectorchord
PostgreSQL Full-Text Search: Fast When Done Right (Debunking the Slow Myth) bm25
Hybrid search with Postgres Native BM25 and VectorChord postgresqlvectorchord
Vector Search at 10,000 QPS in PostgreSQL with VectorChord vectorsearchvectorchord
VectorChord-BM25: Revolutionize PostgreSQL Search with BM25 Ranking — 3x Faster Than ElasticSearch postgresqlvectorchord
Do we really need a specialized vector database? (2023) postgresql
Supercharge vector search with ColBERT rerank in PostgreSQL colbert
ARM + VectorChord: Affordable, Fast Vector Search postgresqlvectorchord

  • Scaling Vector Search to 1 Billion on PostgreSQL

    In Engineering 1000 words 5 min

    vector-database

    For teams trying to run vector search at billion scale themselves, the challenge is often not raw performance, but practicality. Many solutions designed for billion-scale, low-latency vector search come with practical constraints, requiring tradeoffs …

    For teams trying to run vector search at billion scale themselves, the challenge is often not raw performance, but practicality. Many solutions designed for billion-scale, low-latency vector search come with practical constraints, requiring tradeoffs …

  • How We Made 100M Vector Indexing in 20 Minutes Possible on PostgreSQL

    In Engineering 2676 words 13 min

    vectorsearch

    1. Introduction 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 pgvector is well-received, index build time and memory usage remain major …

    1. Introduction 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 pgvector is well-received, index build time and memory usage remain major …

  • Bringing Search‑Engine Ranking to PostgreSQL with VectorChord‑BM25

    In Engineering 880 words 5 min

    postgresqlvectorchord

    Modern applications rely on PostgreSQL for its fully ACID‑compliant, expressive SQL, and rich ecosystem of extensions. The database handles relational workloads exceptionally well, but many projects also need to search for large text …

    Modern applications rely on PostgreSQL for its fully ACID‑compliant, expressive SQL, and rich ecosystem of extensions. The database handles relational workloads exceptionally well, but many projects also need to search for large text …

  • VectorChord: Cost-Efficient Upload & Search of 400 Million Vectors on AWS

    In Engineering 1668 words 8 min

    postgresqlvectorchord

    In this article, we will describe one method for uploading, indexing, and searching a big dataset of vector data in a cost-efficient manner using the real-world LAION-400M dataset and the VectorChord extension in PostgreSQL. We’re attempting to show …

    In this article, we will describe one method for uploading, indexing, and searching a big dataset of vector data in a cost-efficient manner using the real-world LAION-400M dataset and the VectorChord extension in PostgreSQL. We’re attempting to show …

  • Optimize RAG with Contextual Retrieval in PostgreSQL

    In Engineering 1223 words 6 min

    contextual-retrieval

    In the standard approach to Retrieval Augmented Generation (RAG), a common practice is to break down large documents into smaller, more manageable chunks. This is primarily done to improve the efficiency of the retrieval process, leveraging the …

    In the standard approach to Retrieval Augmented Generation (RAG), a common practice is to break down large documents into smaller, more manageable chunks. This is primarily done to improve the efficiency of the retrieval process, leveraging the …

  • All-in-one VectorChord Suite: Building Production-Ready RAG Solutions Directly in PostgreSQL

    In Engineering 998 words 5 min

    postgresqlvectorchord

    Retrieval-Augmented Generation (RAG) is revolutionizing our interaction with vast datasets and language models. RAG systems offer more precise, contextually aware, and current answers by retrieving pertinent information before generating responses. …

    Retrieval-Augmented Generation (RAG) is revolutionizing our interaction with vast datasets and language models. RAG systems offer more precise, contextually aware, and current answers by retrieving pertinent information before generating responses. …

  • Introducing Vechord: Turn PostgreSQL into your search engine in a Pythonic way.

    In Engineering 849 words 5 min

    vectorsearch

    Today, we’re thrilled to announce the release of Vechord, a new Python library designed to dramatically simplify building robust search infrastructure directly on top of the PostgreSQL database. In the rapidly evolving world of AI and large language …

    Today, we’re thrilled to announce the release of Vechord, a new Python library designed to dramatically simplify building robust search infrastructure directly on top of the PostgreSQL database. In the rapidly evolving world of AI and large language …

  • Beyond Text: Unlock OCR-Free RAG in PostgreSQL with Modal & VectorChord

    In Engineering 2265 words 11 min

    ocrvectorchord

    Building effective Retrieval-Augmented Generation (RAG) systems for documents often feels like wrestling with messy, complex pipelines. Especially when dealing with PDFs or scanned images, traditional methods rely heavily on Optical Character …

    Building effective Retrieval-Augmented Generation (RAG) systems for documents often feels like wrestling with messy, complex pipelines. Especially when dealing with PDFs or scanned images, traditional methods rely heavily on Optical Character …

  • 3 Billion Vectors in PostgreSQL to Protect the Earth

    In Engineering 1829 words 9 min

    postgresql

    Monitoring the health of our planet is one of the most critical challenges of our time. Our planet faces immense environmental pressures, and understanding these changes requires sifting through an unimaginable amount of satellite data – petabytes of …

    Monitoring the health of our planet is one of the most critical challenges of our time. Our planet faces immense environmental pressures, and understanding these changes requires sifting through an unimaginable amount of satellite data – petabytes of …

  • Vector Search Over PostgreSQL: A Comparative Analysis of Memory and Disk Solutions

    In Engineering 2192 words 11 min

    vectorchord

    Introduction: real-world challenges Specialized vector databases aren’t always needed. With PostgreSQL extensions like pgvector, pgvectorscale, VectorChord (which evolved from pgvecto.rs)****, you get vector search plus relational power—no extra …

    Introduction: real-world challenges Specialized vector databases aren’t always needed. With PostgreSQL extensions like pgvector, pgvectorscale, VectorChord (which evolved from pgvecto.rs)****, you get vector search plus relational power—no extra …

  • VectorChord-BM25: Introducing pg_tokenizer—A Standalone, Multilingual Tokenizer for Advanced Search

    In Engineering 1135 words 3 min

    vector-databasevectorchord

    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 ranking capabilities directly into your database! VectorChord-BM25 allows you to leverage the power …

    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 ranking capabilities directly into your database! VectorChord-BM25 allows you to leverage the power …

  • PostgreSQL Full-Text Search: Fast When Done Right (Debunking the Slow Myth)

    In Engineering 1215 words 6 min

    bm25

    You might have come across discussions or blog posts suggesting that PostgreSQL’s built-in full-text search (FTS) struggles with performance compared to dedicated search engines or specialized extensions. A notable recent example comes from Neon’s …

    You might have come across discussions or blog posts suggesting that PostgreSQL’s built-in full-text search (FTS) struggles with performance compared to dedicated search engines or specialized extensions. A notable recent example comes from Neon’s …

  • Hybrid search with Postgres Native BM25 and VectorChord

    In Engineering 1905 words 9 min

    postgresqlvectorchord

    In the era of RAG (Retrieval-Augmented Generation), efficiently retrieving relevant data from vast datasets is crucial for businesses and developers. Traditional keyword-based retrieval methods, such as those utilizing BM25 as a scoring mechanism, …

    In the era of RAG (Retrieval-Augmented Generation), efficiently retrieving relevant data from vast datasets is crucial for businesses and developers. Traditional keyword-based retrieval methods, such as those utilizing BM25 as a scoring mechanism, …

  • Vector Search at 10,000 QPS in PostgreSQL with VectorChord

    In Engineering 1162 words 6 min

    vectorsearchvectorchord

    VectorChord is a PostgreSQL extension designed for scalable, high-performance, and disk-efficient vector similarity search, and serves as the successor to pgvecto.rs. In our previous blog post, we showed that with just $250 per month, VectorChord …

    VectorChord is a PostgreSQL extension designed for scalable, high-performance, and disk-efficient vector similarity search, and serves as the successor to pgvecto.rs. In our previous blog post, we showed that with just $250 per month, VectorChord …

  • VectorChord-BM25: Revolutionize PostgreSQL Search with BM25 Ranking — 3x Faster Than ElasticSearch

    In Engineering 2588 words 13 min

    postgresqlvectorchord

    We’re excited to share something special with you: VectorChord-BM25, a new extension designed to make PostgreSQL’s full-text search even better. Whether you’re building a small app or managing a large-scale system, this tool brings advanced BM25 …

    We’re excited to share something special with you: VectorChord-BM25, a new extension designed to make PostgreSQL’s full-text search even better. Whether you’re building a small app or managing a large-scale system, this tool brings advanced BM25 …

  • Do we really need a specialized vector database? (2023)

    In Engineering 2667 words 13 min

    postgresql

    Notice: This article, originally published in 2023, discusses the relevance and necessity of specialized vector databases, particularly in relation to Postgres and its capabilities. For further insights and discussions on this topic, please refer to …

    Notice: This article, originally published in 2023, discusses the relevance and necessity of specialized vector databases, particularly in relation to Postgres and its capabilities. For further insights and discussions on this topic, please refer to …

  • Supercharge vector search with ColBERT rerank in PostgreSQL

    In Engineering 797 words 4 min

    colbert

    Traditional vector search methods typically employ sentence embeddings to locate similar content. However, generating sentence embeddings through pooling token embeddings can potentially sacrifice fine-grained details present at the token level. …

    Traditional vector search methods typically employ sentence embeddings to locate similar content. However, generating sentence embeddings through pooling token embeddings can potentially sacrifice fine-grained details present at the token level. …

  • ARM + VectorChord: Affordable, Fast Vector Search

    In Engineering 538 words 3 min

    postgresqlvectorchord

    ARM64 is quietly becoming a go-to for cost-effective cloud servers, especially on AWS. With ARM-based processors like the Graviton series (Graviton3 and Graviton4), you can save a good chunk of money without sacrificing performance. These ARM64 …

    ARM64 is quietly becoming a go-to for cost-effective cloud servers, especially on AWS. With ARM-based processors like the Graviton series (Graviton3 and Graviton4), you can save a good chunk of money without sacrificing performance. These ARM64 …

Last modified 2026-11-02 · docs: add Chinese translation, BM25 & tokenizer docs, and unify Vchord suite branding (14fbc31)