# ann

Published articles for ann.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Evolving Pinterest's Embedding Retrieval Platform

DevFeed: [Evolving Pinterest's Embedding Retrieval Platform](<https://devfeed.tech/articles/evolving-pinterest-s-embedding-retrieval-platform-1230.md>)

Original publisher: [Read original article](<https://medium.com/pinterest-engineering/evolving-pinterests-embedding-retrieval-platform-aede4e831e01?source=rss----4c5a5f6279b6---4>)

Author: Pinterest Engineering

Published: 2026-09-11T15:01:03Z

Content type: article

Language: en

Sources: [Pinterest Engineering Blog - Medium](<https://devfeed.tech/sources/pinterest-engineering-blog-medium.md>)

Topics: [Architecture & Design](<https://devfeed.tech/topics/architecture-design.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>), [Scalability](<https://devfeed.tech/topics/scalability.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [IO](<https://devfeed.tech/topics/io.md>)

Tags: [ann](<https://devfeed.tech/tags/ann.md>), [cost](<https://devfeed.tech/tags/cost.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [latency](<https://devfeed.tech/tags/latency.md>), [memory](<https://devfeed.tech/tags/memory.md>), [models](<https://devfeed.tech/tags/models.md>), [pinterest](<https://devfeed.tech/tags/pinterest.md>), [platform](<https://devfeed.tech/tags/platform.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

Pinterest describes evolving its Manas embedding-retrieval platform to address the cost, scale, and flexibility challenges of serving billions of embeddings. The excerpt covers ANN search, vector quantization, and SSD-based serving.

### Source excerpt

Authors: Bowen Zhou | Staff Software Engineer; Shan Gao | Senior Software Engineer; Jingwen Hu | Software Engineer II; Wenjiang Chu | Staff Software Engineer The Billion-Embedding Challenge At Pinterest, the "signal" is our lifeblood. Whether it's a home decor enthusiast finding the perfect rug or a fashion seeker discovering a new aesthetic, our discovery engine relies on understanding deep semantic relationships to help our users find inspirations. Over the last few years, the explosive growth of embedding-based retrieval has fundamentally transformed how we surface these signals -- and at the heart of that transformation is Manas, Pinterest's in-house distributed search platform. Embedding Retrieval is one of the core capabilities of Manas, supporting multiple approximate nearest neighbor search algorithms, hybrid queries with both token and embedding clauses, as well as real-time updates to ensure fresh contents become searchable within seconds. Deployed on over 80 clusters and serving billions of embeddings, Manas embedding retrieval powers all major product surfaces at Pinterest including Home Feed, Search, Related Pins, Ads, and Notifications. However, as our corpus scales toward tens of billions of embeddings and our models capture increasingly complex interactions, we face mounting challenges around cost efficiency, scalability, and flexibility. On the infrastructure side, traditional ANN algorithms like HNSW are notoriously memory-hungry -- they require the entire index to reside in RAM to maintain low query latency, making cost grow linearly with corpus size. On the modeling side, the classic two-tower retrieval paradigm is too restrictive: it reduces each candidate to a single embedding and scores relevance through a simple dot product, leaving little room to express richer, context-dependent notions of similarity. To tackle these challenges, our team has been evolving Manas's embedding retrieval stack across three fronts: Quantization. We reduce the memor

## Benchmarking vector indexes

DevFeed: [Benchmarking vector indexes](<https://devfeed.tech/articles/benchmarking-vector-indexes-14092.md>)

Original publisher: [Read original article](<https://www.percona.com/blog/benchmarking-vector-indexes/>)

Author: Evgeniy Patlan

Published: 2026-08-27T13:35:32Z

Content type: article

Language: en

Sources: [Blog - Percona](<https://devfeed.tech/sources/blog-percona.md>)

Topics: [benchmarking](<https://devfeed.tech/topics/benchmarking.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [Databases](<https://devfeed.tech/topics/databases.md>), [ann](<https://devfeed.tech/topics/ann.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Sorting](<https://devfeed.tech/topics/sorting.md>)

Tags: [ai-vector](<https://devfeed.tech/tags/ai-vector.md>), [ann](<https://devfeed.tech/tags/ann.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [blog](<https://devfeed.tech/tags/blog.md>), [blog-post](<https://devfeed.tech/tags/blog-post.md>), [data](<https://devfeed.tech/tags/data.md>), [database-performance](<https://devfeed.tech/tags/database-performance.md>), [database-trends](<https://devfeed.tech/tags/database-trends.md>), [databases](<https://devfeed.tech/tags/databases.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [index](<https://devfeed.tech/tags/index.md>), [measurements](<https://devfeed.tech/tags/measurements.md>), [model](<https://devfeed.tech/tags/model.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [percona](<https://devfeed.tech/tags/percona.md>), [points](<https://devfeed.tech/tags/points.md>), [report](<https://devfeed.tech/tags/report.md>), [run](<https://devfeed.tech/tags/run.md>), [search](<https://devfeed.tech/tags/search.md>), [sorting](<https://devfeed.tech/tags/sorting.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vectorsearch](<https://devfeed.tech/tags/vectorsearch.md>)

### AI overview

This article explains how Percona's vector-bench measures vector indexes by building database engines from pinned versions, running them in identical containers with the same data and hardware, and comparing consistent measurements. It describes embeddings, exact search, approximate nearest neighbour search, and ground truth as the brute-force reference needed to evaluate index accuracy.

### Source excerpt

Nearly every database has vector search now, and every one of them has a blog post with a big number in it. Almost none of those numbers can be checked, because the thing that makes them meaningful is usually missing. We built a vector-bench to stop guessing. You name the engines you want, build them ... Continued The post Benchmarking vector indexes appeared first on Percona.

## Build a unified AI agent architecture with DynamoDB and Bedrock

DevFeed: [Build a unified AI agent architecture with DynamoDB and Bedrock](<https://devfeed.tech/articles/build-a-unified-ai-agent-architecture-with-dynamodb-and-bedrock-4636.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/architecture/build-a-unified-ai-agent-architecture-with-dynamodb-and-bedrock/>)

Author: Dhananjay Karanjkar

Published: 2026-08-21T18:19:23Z

Content type: tutorial

Language: en

Sources: [AWS Architecture Blog](<https://devfeed.tech/sources/aws-architecture-blog.md>)

Topics: [AI Bots](<https://devfeed.tech/topics/ai-bots.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-dynamodb](<https://devfeed.tech/tags/amazon-dynamodb.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [ann](<https://devfeed.tech/tags/ann.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [data-architecture](<https://devfeed.tech/tags/data-architecture.md>), [database](<https://devfeed.tech/tags/database.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [streams](<https://devfeed.tech/tags/streams.md>), [sync](<https://devfeed.tech/tags/sync.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

A tutorial for building an Amazon Bedrock agent that uses one DynamoDB table for structured data and semantic vector search. DynamoDB Streams generates embeddings when content changes, keeping the vector index synchronized.

### Source excerpt

With native vector search in Amazon DynamoDB, you can store vector embeddings alongside your operational data in a single table. This post shows how to build a unified AI agent architecture where an Amazon Bedrock agent uses one DynamoDB table for both structured lookups and semantic search, with a DynamoDB Streams pipeline that keeps embeddings in sync.

## Vector search database: news & 2026 guide

DevFeed: [Vector search database: news & 2026 guide](<https://devfeed.tech/articles/vector-search-database-news-2026-guide-4860.md>)

Original publisher: [Read original article](<https://redis.io/blog/vector-search-database-news-2026-guide/>)

Author: Simran Regmi

Published: 2026-08-13T00:00:00Z

Content type: tutorial

Language: en

Sources: [Redis Blog](<https://devfeed.tech/sources/redis-blog.md>)

Topics: [Database](<https://devfeed.tech/topics/database.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [ann](<https://devfeed.tech/topics/ann.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>)

Tags: [ann](<https://devfeed.tech/tags/ann.md>), [database](<https://devfeed.tech/tags/database.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [guide](<https://devfeed.tech/tags/guide.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [search](<https://devfeed.tech/tags/search.md>), [tech-de](<https://devfeed.tech/tags/tech-de.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

This guide explains how vector search databases store embeddings and retrieve semantically similar items for LLM-powered applications. It covers vector spaces, dimensionality, similarity measures, traditional indexes, the curse of dimensionality, and approximate nearest neighbor search, including HNSW.

### Source excerpt

If you've built anything on top of an LLM in the past couple of years, you may have hit the wall many builders hit: the model writes fluently but has no view into your data. A vector search database helps close that gap. It stores vector embeddings an...

## Hybrid Search Patterns with Postgres and pgvector

DevFeed: [Hybrid Search Patterns with Postgres and pgvector](<https://devfeed.tech/articles/hybrid-search-patterns-with-postgres-and-pgvector-14480.md>)

Original publisher: [Read original article](<https://www.crunchydata.com/blog/hybrid-vector-search>)

Author: Christopher Winslett

Published: 2026-07-30T15:00:00Z

Content type: article

Language: en

Sources: [CrunchyData Blog](<https://devfeed.tech/sources/crunchydata-blog.md>)

Topics: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Query (disambiguation)](<https://devfeed.tech/topics/query.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [ann](<https://devfeed.tech/tags/ann.md>), [caching](<https://devfeed.tech/tags/caching.md>), [hybrid-search](<https://devfeed.tech/tags/hybrid-search.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [search](<https://devfeed.tech/tags/search.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vectors-llms](<https://devfeed.tech/tags/vectors-llms.md>)

### AI overview

This article explains why filtered vector search in Postgres creates a tradeoff between recall and performance. It discusses how ANN indexes such as HNSW and IVFFlat differ from B-tree indexes, and introduces approaches including pgvector iterative scans, partial indexes, oversampling, and caching.

### Source excerpt

Filtered vector search in Postgres forces a tradeoff between recall and speed because ANN indexes and WHERE clauses do not intersect like B-trees. Read about pgvector iterative scans, partial HNSW indexes, oversampling with pg_stats, caching, and more.

## Build Durable Chat Memory for RAG Using ScyllaDB and LangChain

DevFeed: [Build Durable Chat Memory for RAG Using ScyllaDB and LangChain](<https://devfeed.tech/articles/build-durable-chat-memory-for-rag-using-scylladb-and-langchain-4873.md>)

Original publisher: [Read original article](<https://www.scylladb.com/2026/07/14/durable-chat-memory-for-rag-scylladb-and-langchain/>)

Author: Cynthia Dunlop

Published: 2026-07-14T12:54:49Z

Content type: tutorial

Language: en

Sources: [ScyllaDB](<https://devfeed.tech/sources/scylladb.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Language models](<https://devfeed.tech/topics/language-models.md>)

Tags: [2026-2](<https://devfeed.tech/tags/2026-2.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [ann](<https://devfeed.tech/tags/ann.md>), [cassandra](<https://devfeed.tech/tags/cassandra.md>), [database](<https://devfeed.tech/tags/database.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [history](<https://devfeed.tech/tags/history.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [latency](<https://devfeed.tech/tags/latency.md>), [memory](<https://devfeed.tech/tags/memory.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [sentence-transformers](<https://devfeed.tech/tags/sentence-transformers.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

A tutorial on replacing LangChain's in-memory chat history with ScyllaDB for durable RAG chatbot memory across restarts and replicas.

### Source excerpt

How to replace LangChain's in-memory chat history with ScyllaDB -- so your RAG chatbot retains context across restarts and scales across replicas

## We built a vector search engine that lets you choose precision at query time

DevFeed: [We built a vector search engine that lets you choose precision at query time](<https://devfeed.tech/articles/we-built-a-vector-search-engine-that-lets-you-choose-precision-at-query-time-5534.md>)

Original publisher: [Read original article](<https://clickhouse.com/blog/qbit-vector-search>)

Author: Raufs Dunamalijevs

Published: 2025-10-28T00:00:00Z

Content type: article

Language: en

Sources: [ClickHouse Blog](<https://devfeed.tech/sources/clickhouse-blog.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Language models](<https://devfeed.tech/topics/language-models.md>)

Tags: [ann](<https://devfeed.tech/tags/ann.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [databases](<https://devfeed.tech/tags/databases.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [performance](<https://devfeed.tech/tags/performance.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [speed](<https://devfeed.tech/tags/speed.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

ClickHouse introduces QBit, a bit-plane float column type for vector search. It allows query-time adjustment of read precision to balance recall and performance without changing stored data.

### Source excerpt

We added QBit to ClickHouse, a column type that stores floats as bit planes. It lets you choose how many bits to read during vector search, tuning recall and performance without changing the data.

## Inside Glassdoor's Multi-Stage Recommendation System

DevFeed: [Inside Glassdoor's Multi-Stage Recommendation System](<https://devfeed.tech/articles/inside-glassdoor-s-multi-stage-recommendation-system-22611.md>)

Original publisher: [Read original article](<https://medium.com/glassdoor-engineering/inside-glassdoors-multi-stage-recommendation-system-cee58b52a75a?source=rss----288d984af747---4>)

Author: Prateek Shekhar

Published: 2025-08-12T19:37:39Z

Content type: article

Language: en

Sources: [Glassdoor Engineering](<https://devfeed.tech/sources/glassdoor-engineering.md>)

Topics: [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [recommendations](<https://devfeed.tech/topics/recommendations.md>), [personalization](<https://devfeed.tech/topics/personalization.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>), [ordering](<https://devfeed.tech/topics/ordering.md>), [ann](<https://devfeed.tech/topics/ann.md>)

Tags: [algorithms](<https://devfeed.tech/tags/algorithms.md>), [ann](<https://devfeed.tech/tags/ann.md>), [glassdoor](<https://devfeed.tech/tags/glassdoor.md>), [ordering](<https://devfeed.tech/tags/ordering.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [recommendation-system](<https://devfeed.tech/tags/recommendation-system.md>), [recommendation-systems](<https://devfeed.tech/tags/recommendation-systems.md>), [recommender-systems](<https://devfeed.tech/tags/recommender-systems.md>)

### AI overview

This article gives a high-level overview of Glassdoor's hybrid, multi-stage recommendation system. It describes how the system uses user behavior, similar-user behavior, and item features to produce personalized recommendations for the Community Feed, Email, and Push notifications, with stages including candidate generation, filtering, scoring, and ordering.

### Source excerpt

Introduction: Recommendation systems are central to modern digital platforms, delivering personalized content by intelligently analyzing user behavior and preferences through advanced algorithms. Widely used in e-commerce, streaming services, social media, and online learning, they drive user satisfaction, engagement, and retention while supporting business growth. Typically, these systems operate using one or more of the following approaches: Collaborative Filtering: This approach examines user behavior by comparing how users interact with items. It identifies patterns by analyzing similar user actions. For example, if two users have watched or purchased similar items, the system will recommend those same items to other users with similar behavior. Content-Based Filtering: In this approach, the system analyzes the characteristics of the items themselves, such as text, images, or other features. It recommends items that have features similar to those a user has previously liked. For example, if a user enjoyed books with specific keywords, the system will suggest books with those exact keywords. Hybrid Approach: This approach combines collaborative and content-based filtering to enhance personalization and accuracy. It utilizes user behavior patterns in conjunction with item features, offering more personalized and accurate recommendations. At Glassdoor, our Community Feed, Email, and Push notifications are powered by a recommendation system that follows a hybrid approach. It analyzes individual users' behavior, such as posts, comments, and reactions, as well as the behavior of similar users, to deliver tailored, personalized recommendations. This post presents a high-level overview of the multi-stage architecture behind our system, highlighting candidate generation, filtering, scoring, ordering, and supporting infrastructure. Glassdoor's Recommendation System ArchitectureFigure 1: Glassdoor's Recommendation System Architecture Glassdoor's Recommendation System follo

## The space complexity of vector indexes in LibSQL

DevFeed: [The space complexity of vector indexes in LibSQL](<https://devfeed.tech/articles/the-space-complexity-of-vector-indexes-in-libsql-6047.md>)

Original publisher: [Read original article](<https://turso.tech/blog/the-space-complexity-of-vector-indexes-in-libsql>)

Author: Volodymyr Pavlyshyn

Published: 2024-10-03T00:00:00Z

Content type: article

Language: en

Sources: [Turso Blog](<https://devfeed.tech/sources/turso-blog.md>)

Topics: [libSQL](<https://devfeed.tech/topics/libsql.md>), [ann](<https://devfeed.tech/topics/ann.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [Compression](<https://devfeed.tech/topics/compression.md>), [Optimization](<https://devfeed.tech/topics/optimization.md>), [Database](<https://devfeed.tech/topics/database.md>), [Latency](<https://devfeed.tech/topics/latency.md>)

Tags: [ann](<https://devfeed.tech/tags/ann.md>), [compression](<https://devfeed.tech/tags/compression.md>), [env-file-security](<https://devfeed.tech/tags/env-file-security.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [latency](<https://devfeed.tech/tags/latency.md>), [libsql](<https://devfeed.tech/tags/libsql.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [storage](<https://devfeed.tech/tags/storage.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

This article examines the storage complexity of libSQL vector indexes based on the graph-based FreshDiskANN algorithm. It explains how graph storage and neighbor vectors increased a database from 3.5 MB to 50 MB, then discusses compression and max-neighbor settings for reducing space while balancing search speed and accuracy.

### Source excerpt

How Kin shrunk libSQL's LM-DiskANN vector index storage on mobile by tuning compress_neighbors and max_neighbors, trading a little recall for big space wins.

## Approximate nearest neighbor search with DiskANN in libSQL

DevFeed: [Approximate nearest neighbor search with DiskANN in libSQL](<https://devfeed.tech/articles/approximate-nearest-neighbor-search-with-diskann-in-libsql-5892.md>)

Original publisher: [Read original article](<https://turso.tech/blog/approximate-nearest-neighbor-search-with-diskann-in-libsql>)

Author: Pekka Enberg

Published: 2024-07-26T00:00:00Z

Content type: article

Language: en

Sources: [Turso Blog](<https://devfeed.tech/sources/turso-blog.md>)

Topics: [libSQL](<https://devfeed.tech/topics/libsql.md>), [ann](<https://devfeed.tech/topics/ann.md>), [SQLite](<https://devfeed.tech/topics/sqlite.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [ann](<https://devfeed.tech/tags/ann.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [libsql](<https://devfeed.tech/tags/libsql.md>), [performance](<https://devfeed.tech/tags/performance.md>), [rag](<https://devfeed.tech/tags/rag.md>), [sql](<https://devfeed.tech/tags/sql.md>), [sqlite](<https://devfeed.tech/tags/sqlite.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

This article explains how libSQL implements approximate nearest neighbor search for large embedding datasets using the low-memory LM-DiskANN algorithm. It describes the trade-off between exactness and speed, graph-based search, vector indexing in SQLite, cosine distance, and the integration between SQLite's code generator and the DiskANN index.

### Source excerpt

Learn how to use retrieval augmented generation to improve vector search results with SQLite.

## pgvector: 30x Faster Index Build for your Vector Embeddings

DevFeed: [pgvector: 30x Faster Index Build for your Vector Embeddings](<https://devfeed.tech/articles/pgvector-30x-faster-index-build-for-your-vector-embeddings-5720.md>)

Original publisher: [Read original article](<https://neon.com/blog/pgvector-30x-faster-index-build-for-your-vector-embeddings>)

Author: Raouf Chebri

Published: 2024-02-07T15:43:47Z

Content type: article

Language: en

Sources: [Blog -- Neon Docs](<https://devfeed.tech/sources/blog-neon-docs.md>)

Topics: [Databases](<https://devfeed.tech/topics/databases.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [ann](<https://devfeed.tech/topics/ann.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [API](<https://devfeed.tech/topics/api.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ann](<https://devfeed.tech/tags/ann.md>), [api](<https://devfeed.tech/tags/api.md>), [database](<https://devfeed.tech/tags/database.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [llm](<https://devfeed.tech/tags/llm.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [product](<https://devfeed.tech/tags/product.md>), [rag](<https://devfeed.tech/tags/rag.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

Neon describes how parallel HNSW index builds in pgvector can reduce vector index build time by 30x. The article explains how Neon's elastic, separate-storage-and-compute architecture can allocate extra resources during indexing and scale them down afterward for AI applications using vector search, semantic search, and Retrieval Augmented Generation.

### Source excerpt

We are Neon, the serverless Postgres. We power thousands of AI apps with the pgvector extension and separate storage and compute enabling your database resources to scale independently. In this article, Raouf explains how you can use Neon's elasticity, and parallel HNSW index bui...

## pgvector vs Pinecone: cost and performance

DevFeed: [pgvector vs Pinecone: cost and performance](<https://devfeed.tech/articles/pgvector-vs-pinecone-cost-and-performance-491.md>)

Original publisher: [Read original article](<https://supabase.com/blog/pgvector-vs-pinecone>)

Author: Egor Romanov

Published: 2023-10-10T07:00:00Z

Content type: comparison

Language: en

Sources: [Supabase Blog](<https://devfeed.tech/sources/supabase-blog.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>)

Tags: [ann](<https://devfeed.tech/tags/ann.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cost](<https://devfeed.tech/tags/cost.md>), [database](<https://devfeed.tech/tags/database.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [latency](<https://devfeed.tech/tags/latency.md>), [openai](<https://devfeed.tech/tags/openai.md>), [performance](<https://devfeed.tech/tags/performance.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [search](<https://devfeed.tech/tags/search.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

A direct cost and performance comparison of pgvector on Postgres and Pinecone for vector search workloads.

### Source excerpt

Direct performance comparison between pgvector and Pinecone.

## Optimizing vector search performance with pgvector

DevFeed: [Optimizing vector search performance with pgvector](<https://devfeed.tech/articles/optimizing-vector-search-performance-with-pgvector-5704.md>)

Original publisher: [Read original article](<https://neon.com/blog/optimizing-vector-search-performance-with-pgvector>)

Author: Raouf Chebri

Published: 2023-06-28T16:01:07Z

Content type: article

Language: en

Sources: [Blog -- Neon Docs](<https://devfeed.tech/sources/blog-neon-docs.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>), [ann](<https://devfeed.tech/topics/ann.md>), [Database](<https://devfeed.tech/topics/database.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ann](<https://devfeed.tech/tags/ann.md>), [community](<https://devfeed.tech/tags/community.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgres](<https://devfeed.tech/tags/postgres.md>), [product](<https://devfeed.tech/tags/product.md>), [search](<https://devfeed.tech/tags/search.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

This article explains how to optimize vector similarity search with pgvector in Postgres. It compares exact sequential scans with approximate nearest neighbor search using the ivfflat index, discusses performance as datasets grow, and introduces the Lists and Probes parameters that affect search speed and recall.

### Source excerpt

According to the StackOverflow Survey 2023, nearly half of professional developers use Postgres. It's natural then that the Postgres extension for vector similarity search, pgvector, is one of the most popular options for prototyping AI-powered applications. But how to properly u...