# Vector Published articles for Vector. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Java 27 Delivers Post-Quantum Cryptography, Future Language Innovation, Helidon 27, JavaFX 27 DevFeed: [Java 27 Delivers Post-Quantum Cryptography, Future Language Innovation, Helidon 27, JavaFX 27]() Original publisher: [Read original article]() Author: Michael Redlich Published: 2026-09-16T10:00:00Z Content type: news Language: en Sources: [InfoQ]() Topics: [Java](), [java-27](), [Post-quantum cryptography](), [Cryptography](), [Security](), [Programming](), [releases]() Tags: [application-security](), [architecture-design](), [cryptography](), [development](), [digital-signature](), [helidon](), [java](), [java-27](), [java27-released](), [javafx](), [jdk-27](), [jdk-28](), [lattice](), [module](), [news](), [oracle](), [portfolio](), [post-quantum-cryptography](), [preview](), [project-valhalla](), [quantum-computing](), [release](), [security](), [structured-concurrency](), [vector]() ### AI overview Oracle released Java 27, the second non-LTS release since JDK 25. Its final feature set contains nine JEPs, including post-quantum hybrid key exchange for TLS 1.3, structured concurrency, compact object headers, JFR data redaction, the Vector API, and PEM encodings for cryptographic objects. Five features remain in preview or incubator stages. ### Source excerpt Oracle has released version 27 of the Java programming language and virtual machine. As the second non-LTS release since JDK 25, the final feature set includes nine JEPs, five of which are still progressing through the preview and incubator stages. This release focuses on strengthening security, future language innovation, and projects under the auspices of the Java Verified Portfolio. By Michael Redlich ## Pinterest's Manas Search Platform Uses Quantization and SSD-Based Serving DevFeed: [Pinterest's Manas Search Platform Uses Quantization and SSD-Based Serving]() Original publisher: [Read original article]() Author: Olimpiu Pop Published: 2026-09-16T06:06:00Z Content type: news Language: en Sources: [InfoQ]() Topics: [quantization](), [AI search](), [webgpu]() Tags: [algorithms](), [architecture-design](), [development](), [infrastructure](), [news](), [optimization](), [performance](), [pinterest-search](), [quantization](), [search](), [ssd](), [vector]() ### AI overview Pinterest Engineering enhanced its Manas distributed search platform with scalar and product quantization, SSD-based serving, and late-interaction retrieval. The reported evaluations describe trade-offs among index size, recall, throughput, latency, and serving cost. ### Source excerpt Pinterest Engineering has enhanced its Manas search platform to manage vast data, improving efficiency in search and discovery functions. By applying Scalar and Product Quantization, memory usage decreased significantly while maintaining high recall rates. The platform utilizes SSDs for optimized performance, and it is transitioning to multi-vector models for refined relevance matching. By Olimpiu Pop ## Data Engineering Weekly #287 DevFeed: [Data Engineering Weekly #287]() Original publisher: [Read original article]() Author: Ananth Packkildurai Published: 2026-09-14T02:52:23Z Content type: article Language: en Sources: [Data Engineering Weekly]() Topics: [data-engineering](), [Kafka](), [data observability](), [Embeddings](), [Multi-tenancy](), [Event-Streaming](), [OpenAI](), [Library](), [Code]() Tags: [architecture](), [architectures](), [data-engineering](), [data-quality](), [embedding](), [engineering](), [kafka](), [multi-tenancy](), [object-storage](), [observability](), [openai](), [streaming](), [vector]() ### AI overview Data Engineering Weekly #287 covers building data platforms from scratch, including composable architectures, data quality, and observability. It also previews talks on governed machine-executable ontologies for marketing activation and fair, order-preserving Kafka consumption for many tenants. The issue links to OpenAI's storage platform scaling for ChatGPT and Pinterest's embedding retrieval platform. ### Source excerpt The Weekly Data Engineering Newsletter ## Three principles for building a vector platform at Thumbtack DevFeed: [Three principles for building a vector platform at Thumbtack]() Original publisher: [Read original article]() Author: John Zhu Published: 2026-09-10T15:45:00Z Content type: article Language: en Sources: [Thumbtack Engineering - Medium]() Topics: [Embeddings](), [AI search](), [Database](), [data](), [Machine learning](), [API]() Tags: [api](), [data](), [embeddings](), [engineering](), [etl](), [infrastructure](), [machine-learning](), [ml-platform](), [pgvector](), [retrieval](), [search](), [vector](), [vector-search]() ### AI overview This article explains how Thumbtack built a vector platform that lets ML engineers deploy production vector search without managing database access, custom ETL, or query services. It describes three guiding principles: reuse existing infrastructure, treat embeddings as data, and reduce adoption costs for future teams. ### Source excerpt Reusing what we already had, treating embeddings as data, and lowering the next team's cost Today, an ML engineer at Thumbtack can stand up production vector search without negotiating database access, building a custom ETL, or writing a query service. The team brings their choice of embedding model, the data, and the query; the platform handles what connects them. It took several iterations to get to this point. In this post we'll walk through how we got there and the three principles that shaped what we built. A vector database stores high-dimensional numeric arrays (embeddings) and serves nearest-neighbor queries against them. It's how an ML system asks "what's most similar to this?" instead of "what matches this exact key?" The shift from exact lookup to semantic retrieval is what makes vectors useful: a search can return results that mean the same thing, not just results that spell the same. At Thumbtack, embeddings sit between the models that produce them and the services that consume them: language models for text, multimodal models for images, retrieval models for ranking. The platform we describe here is where those embeddings live and how teams reach for them when they need to. Three principles shaped what we built. Reuse what we have: extend the infrastructure we already run rather than stand up a new system. Treat embeddings as data: flow them through the same pipelines that move every other dataset at the company. Lower the next team's cost: make the platform easier to adopt than to work around. Each principle shaped one layer of the system, and together they took vector search from a one-off project to a platform that any team can build on. Architecture at a glance The platform has four moving parts: where embeddings come from, how they reach the database, where they live, and how consumers query them. Each is a layer, and together they form a pipeline that produces vectors and serves similarity searches as a typed API call. The diagram below traces a ## How MCP Toolbox turns agent text into ClickHouse vectors DevFeed: [How MCP Toolbox turns agent text into ClickHouse vectors]() Original publisher: [Read original article]() Author: Pete Hampton Published: 2026-09-07T09:00:00Z Content type: tutorial Language: en Sources: [ClickHouse Blog]() Topics: [MSP MCP]() Tags: [ai-agent](), [clickhouse](), [databases](), [embedding](), [gemini](), [go](), [google](), [how-to](), [mcp](), [search](), [sql](), [vector]() ### AI overview A tutorial for configuring Google's MCP Toolbox with ClickHouse to embed text during inserts and searches, then return cosine-ranked results without a separate embedding service. ### Source excerpt Google's MCP Toolbox for Databases embeds agent text into vectors on insert and search, then lets ClickHouse rank the results - no embedding service to build or maintain. Here's how to set it up, and what it looks like end to end. ## 5 Embedding Compression Techniques DevFeed: [5 Embedding Compression Techniques]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-04T20:51:57Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Compression](), [Embeddings](), [quantization](), [Inference]() Tags: [compression](), [embedding](), [inference](), [quantization](), [vector]() ### AI overview A tutorial explaining five embedding compression techniques: PCA, Matryoshka Representation Learning, scalar quantization, binary quantization, and Product Quantization. It describes how they reduce dimensions or per-value precision and how rescoring can improve ranking after compressed retrieval. ### Source excerpt ...explained visually. ## Laravel August product updates DevFeed: [Laravel August product updates]() Original publisher: [Read original article]() Author: Laravel Team Published: 2026-09-03T20:30:00Z Content type: release Language: en Sources: [Laravel Blog]() Topics: [cloud-infrastructure](), [Filesystems](), [AI search](), [Database](), [Authorization](), [changelog]() Tags: [api](), [changelog](), [cloud](), [compute](), [database](), [filesystems](), [laravel](), [product](), [search](), [ubuntu](), [updates](), [vector]() ### AI overview Laravel's August update announces framework, Cloud, and Forge changes, including read-through filesystems, semantic search, vector support, managed queue options, scoped API tokens, and Ubuntu 26.04 rollout. ### Source excerpt Here's everything that shipped in August. ## NeoMME: an efficient Multimodal-native and Multilingual Encoder DevFeed: [NeoMME: an efficient Multimodal-native and Multilingual Encoder]() Original publisher: [Read original article]() Author: Tony Wu; Aurélien Lac Published: 2026-09-03T13:13:48Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [vlm](), [Fine-tuning](), [Large Language Model](), [GPU]() Tags: [apache](), [architecture](), [diffusion](), [embeddings](), [fine-tuning](), [gpu](), [hugging-face](), [multimodal](), [quantization](), [retrieval](), [training](), [transformers](), [vector](), [vision](), [vlm]() ### AI overview NeoMME is a family of multilingual multimodal encoders trained from scratch with a masked discrete-diffusion objective. It uses one bidirectional Transformer for text tokens and image patches, and is fine-tuned for visual document retrieval with dense and late-interaction embeddings. ### Source excerpt We introduce NeoMME, a family of 260M and 800M multilingual multimodal encoders. Unlike many generative visual language models, NeoMME does not use a separate pretrained vision tower or a causal language model. A single bidirectional Transformer processes both text tokens and raw image patches, and we train the entire model from scratch with a masked discrete-diffusion objective. We fine-tuned NeoMME for visual document retrieval using ColPali's page-image approach. ## Introducing strands-dynamodb-storage: Durable agent storage for the Strands Agents SDK DevFeed: [Introducing strands-dynamodb-storage: Durable agent storage for the Strands Agents SDK]() Original publisher: [Read original article]() Author: Lee Hannigan Published: 2026-09-02T15:48:06Z Content type: release Language: en Sources: [AWS Database Blog]() Topics: [AI Development](), [Database](), [SDKs](), [Amazon Bedrock](), [AWS Lambda]() Tags: [advanced-300](), [ai-agents](), [amazon-dynamodb](), [announcements](), [memory](), [open-source](), [python](), [storage](), [strands-agents](), [typescript](), [vector]() ### AI overview Amazon Web Services announces strands-dynamodb-storage, an open-source DynamoDB backend for the Strands Agents SDK. It stores agent session state, long-term memories, and transcripts in one DynamoDB table and supports semantic memory recall through a vector index. ### Source excerpt Announcing strands-dynamodb-storage, an open source Amazon DynamoDB storage backend for the Strands Agents SDK. Back a Strands agent's session state, long-term memories, and transcripts with one DynamoDB table in your own account, and give the agent semantic recall with a vector index on that same table. ## Announcing VectorsDB: Similarity search as a first-class Appwrite database DevFeed: [Announcing VectorsDB: Similarity search as a first-class Appwrite database]() Original publisher: [Read original article]() Author: Arnab Chatterjee Published: 2026-09-02T00:00:00Z Content type: release Language: en Sources: [Appwrite Blog]() Topics: [Appwrite](), [AI search](), [Databases](), [Embeddings]() Tags: [ai](), [announcements](), [databases](), [embeddings](), [product](), [search](), [vector]() ### AI overview Appwrite announces VectorsDB, a first-class database for storing and searching vectors. It supports built-in text embedding generation, externally generated embeddings, similarity ranking, metadata, permissions, queries, pagination, ordering, transactions, bulk operations, and CSV import and export. ### Source excerpt Store embeddings, generate them from text with built-in models, and rank documents by similarity without adding a separate vector service to your stack. ## KV vs Prefix vs Prompt vs Semantic Caching DevFeed: [KV vs Prefix vs Prompt vs Semantic Caching]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-27T20:01:47Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [Caching](), [Large Language Model](), [Neo4j]() Tags: [caching](), [embedding](), [knowledge-graph](), [latency](), [llm](), [memory](), [nvme](), [object-storage](), [retrieval](), [server](), [token](), [vector]() ### AI overview The article distinguishes KV caching, prefix caching, prompt caching, and semantic caching in LLM systems. It explains what each cache stores, how exact-match and fuzzy-match behavior differ, and how cache misses affect cost, latency, and correctness. It also describes Konig's tiered storage approach for many small knowledge graphs, though the supplied text is truncated. ### Source excerpt ...explained with best practices in production. ## What's in a tag name? JavaScript, apparently DevFeed: [What's in a tag name? JavaScript, apparently]() Original publisher: [Read original article]() Author: Gareth Heyes Published: 2026-08-25T14:24:32Z Content type: article Language: en Sources: [PortSwigger Research]() Topics: [JavaScript](), [browser](), [HTML](), [Developer Tools](), [Web Development]() Tags: [browser](), [eval](), [event](), [html](), [javascript](), [payload](), [vector]() ### AI overview The article explores unusual HTML tag-name and attribute behaviors that can be combined with JavaScript features to create XSS vectors and potentially bypass web application firewalls. It discusses case transformations, event handlers, the Function constructor, eval, focusability, and alternative HTML attributes across browsers. ### Source excerpt I was on my laptop, as I often am when there's rubbish on telly, and found myself wondering what characters are allowed in a tag. I knew they had to begin with "a-zA-Z", but what about after that? I t ## Build a unified AI agent architecture with DynamoDB and Bedrock DevFeed: [Build a unified AI agent architecture with DynamoDB and Bedrock]() Original publisher: [Read original article]() Author: Dhananjay Karanjkar Published: 2026-08-21T18:19:23Z Content type: tutorial Language: en Sources: [AWS Architecture Blog]() Topics: [AI Bots]() Tags: [advanced-300](), [agent](), [agents](), [ai](), [ai-agent](), [amazon-bedrock](), [amazon-dynamodb](), [amazon-opensearch-service](), [ann](), [api](), [architecture](), [aws-lambda](), [data-architecture](), [database](), [embeddings](), [how-to](), [retrieval](), [search](), [streams](), [sync](), [vector]() ### 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. ## How mobility gives language models a deeper understanding of place DevFeed: [How mobility gives language models a deeper understanding of place]() Original publisher: [Read original article]() Published: 2026-08-21T10:54:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Language models](), [AI Models](), [data](), [datasets](), [Google]() Tags: [ai](), [ai-models](), [algorithms-theory](), [artificial-intelligence](), [benchmark](), [benchmarks](), [data](), [datasets](), [earth-ai](), [embedding](), [google](), [language-models](), [machine-intelligence](), [mobility](), [model](), [models](), [points](), [research](), [vector]() ### AI overview Google Research introduces Mobility-Embedded POIs (ME-POIs), a framework that combines language-model-based text representations of places with aggregated, anonymized mobility patterns. The resulting embeddings capture both a place's identity and its changing functional activity, improving predictions such as visit intent, price level, opening hours, and busyness. ### Source excerpt Algorithms & Theory ## Run Massive-Scale UMAP in Minutes Using Multiple GPUs--Without Losing Accuracy DevFeed: [Run Massive-Scale UMAP in Minutes Using Multiple GPUs--Without Losing Accuracy]() Original publisher: [Read original article]() Author: Tanya Lenz Published: 2026-08-18T16:48:08Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Data analysis](), [GPU](), [Graphs](), [datasets](), [RAPIDS](), [Nvidia]() Tags: [accelerate](), [analysis](), [cuda-x](), [data-analytics-processing](), [data-center-cloud](), [data-science](), [datasets](), [feature](), [featured](), [gpu](), [graphs](), [multi-gpu](), [nvidia](), [post](), [scale](), [simulation-modeling-design](), [training](), [vector](), [visualization]() ### AI overview This article explains how multi-GPU UMAP scales dimensionality reduction to datasets containing tens to hundreds of millions of vectors. A feature in NVIDIA cuML and cuVS 25.06 distributes all-neighbors kNN graph construction across multiple GPUs, enabling workloads of several hundred gigabytes to run in minutes while preserving nearest-neighbor relationships and accuracy. ### Source excerpt Uniform Manifold Approximation and Projection (UMAP) is a dimensionality reduction technique widely used for visualization and feature extraction. Applications... ## Scale pgvector with binary quantization on Amazon Aurora PostgreSQL DevFeed: [Scale pgvector with binary quantization on Amazon Aurora PostgreSQL]() Original publisher: [Read original article]() Author: Steve Dille Published: 2026-08-18T16:37:22Z Content type: tutorial Language: en Sources: [AWS Database Blog]() Topics: [Amazon Aurora](), [PostgreSQL](), [quantization](), [AI search](), [Compression](), [Embeddings](), [Cache](), [Latency](), [datasets](), [configuration](), [postgresql clusters](), [Database]() Tags: [advanced-300](), [ai](), [amazon-aurora](), [cache](), [compression](), [datasets](), [embeddings](), [latency](), [postgresql](), [postgresql-compatible](), [quantization](), [rds-for-postgresql](), [search](), [technical-how-to](), [validation](), [vector]() ### AI overview This practical guide explains how to use binary quantization with reranking in pgvector to scale HNSW vector search on Amazon Aurora PostgreSQL. It covers index-size reduction, performance and recall tradeoffs, sizing, validation, and suitable operating conditions for datasets ranging from 5 million to 100 million vectors. ### Source excerpt Learn how to use binary quantization with reranking (HNSW+BQ) in pgvector to scale vector search to hundreds of millions or billions of vectors on Amazon Aurora PostgreSQL, with practical guidance on index sizing, recall validation, and the scenarios where the approach works best. ## Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers DevFeed: [Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers]() Original publisher: [Read original article]() Author: Tom Aarsen; Antoine Chaffin; Raphael Sourty Published: 2026-08-18T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [sentence-transformers](), [Embeddings](), [Open Source]() Tags: [community](), [embedding](), [embeddings](), [guide](), [multimodal](), [nlp](), [open-source](), [retrieval](), [search](), [sentence-transformers](), [transformers](), [vector]() ### AI overview This article explains multi-vector, or late-interaction, embedding models with Sentence Transformers. It covers token-level representations, MaxSim scoring, retrieval over text and page images, integration with search systems, and index-size tradeoffs. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Metadata filtering: boost search precision as data grows DevFeed: [Metadata filtering: boost search precision as data grows]() Original publisher: [Read original article]() Author: Simran Regmi Published: 2026-08-17T00:00:00Z Content type: tutorial Language: en Sources: [Redis Blog]() Topics: [AI search](), [data](), [datasets](), [Retrieval Augmented Generation (RAG)](), [Software as a service](), [Authorization](), [Benchmark]() Tags: [benchmark](), [data](), [datasets](), [rag](), [retrieval](), [saas](), [search](), [tech-de](), [vector]() ### AI overview Metadata filtering improves vector search precision by applying structured constraints such as price, status, tenant, and date to semantically similar results. The article explains pre-filtering and post-filtering, filtering at scale, hybrid queries, and the role of unified engines in production search, RAG, e-commerce, academic search, and multi-tenant SaaS. It cites a benchmark where filtering increased accuracy from 0.12 to 0.61. ### Source excerpt Vector search is great at finding things that are semantically similar, but similarity isn't the same as correctness. A pure vector query doesn't know that a product is out of stock, that a document belongs to a different customer, or that a policy wa... ## Vector search in production: index trade-offs, failure modes & what to watch DevFeed: [Vector search in production: index trade-offs, failure modes & what to watch]() Original publisher: [Read original article]() Author: Cedric Turner Published: 2026-08-14T00:00:00Z Content type: tutorial Language: en Sources: [Redis Blog]() Topics: [AI search]() Tags: [algorithms](), [data](), [database](), [embeddings](), [production](), [search](), [tech-de](), [vector]() ### AI overview A practical guide to vector search in production, explaining embeddings, nearest-neighbor retrieval, index accuracy-speed trade-offs, and when keyword search is preferable. ### Source excerpt Vector search runs on a simple idea: turn data into coordinates, and treat similarity as distance. An embedding model maps each sentence, image, or document to a point in a few hundred dimensions of space, where items with related meaning land near ea... ## How Fly.io logging works and how to collect application logs DevFeed: [How Fly.io logging works and how to collect application logs]() Original publisher: [Read original article]() Author: Muhammed Ali Published: 2026-08-13T07:00:00Z Content type: tutorial Language: en Sources: [Honeybadger]() Topics: [fly.io](), [Logging](), [App](), [FastAPI](), [Streams](), [Deployment]() Tags: [app](), [deployment](), [devops-articles](), [fastapi](), [fly-io](), [guide](), [how-to](), [logging](), [streams](), [vector]() ### AI overview This tutorial explains how Fly.io collects and routes application logs, including output from standard output and standard error. It also demonstrates a FastAPI application that generates different log messages and describes handling logs with Honeybadger. ### Source excerpt Logging is an import part of debugging an app. Without a good method of catching errors or logs in general, you would end up with uncaught issues and could also lose valuable customers in the process. Read this article to learn how to effectively handle logs on Fly.io. ## Vector search database: news & 2026 guide DevFeed: [Vector search database: news & 2026 guide]() Original publisher: [Read original article]() Author: Simran Regmi Published: 2026-08-13T00:00:00Z Content type: tutorial Language: en Sources: [Redis Blog]() Topics: [Database](), [AI search](), [Embeddings](), [ann](), [Large Language Model](), [Algorithms]() Tags: [ann](), [database](), [embeddings](), [guide](), [latency](), [llm](), [search](), [tech-de](), [vector]() ### 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... ## Building Tactile UX: Honoring Intentional Design With Lottie DevFeed: [Building Tactile UX: Honoring Intentional Design With Lottie]() Original publisher: [Read original article]() Author: hello@smashingmagazine.com (Alexey Kopytin) Published: 2026-08-11T10:00:00Z Content type: article Language: en Sources: [Articles on Smashing Magazine -- For Web Designers And Developers]() Topics: [User experience (UX)](), [Front end](), [Web](), [Document Object Model (DOM)](), [real-time](), [math](), [JSON](), [Matter]() Tags: [animation](), [article](), [design](), [developers](), [json](), [real-time](), [ui](), [ux](), [vector](), [web](), [web-interface]() ### AI overview This article explains how Isadora Agency built Stress Release, a tactile digital stress-relief squeeze toy, using intentional Lottie animations, DOM events, and distance-based math instead of a physics engine. It focuses on deterministic, frame-accurate animation control and describes mapping DOM interactions to Lottie states rendered as JSON-based SVG animations. ### Source excerpt When tasked with building a highly interactive, tactile web experience, the architecture must serve the art direction. In this article, Alexey Kopytin explains their architectural rationale for building a digital stress-relief squeeze toy game using Lottie animations, DOM events, and distance-based math to maintain absolute control over their designers' intentional motion. ## Vector embeddings & language: how models turn words into geometry DevFeed: [Vector embeddings & language: how models turn words into geometry]() Original publisher: [Read original article]() Author: Simran Regmi Published: 2026-08-10T00:00:00Z Content type: article Language: en Sources: [Redis Blog]() Topics: [Embeddings](), [Artificial Intelligence](), [Redis]() Tags: [ai](), [embeddings](), [models](), [retrieval](), [search](), [tech-de](), [vector]() ### AI overview A guide to vector embeddings and how language models represent text as points in high-dimensional space. It explains semantic similarity, distributional context, ambiguity, and why language is harder to encode than pixels. ### Source excerpt A user types "refund policy" into your search box, but the doc they need is titled "returns and reimbursements." Keyword matching scores it near zero even though it's exactly what the user asked for. Vector embeddings help address this mismatch by rep... ## Reciprocal rank fusion: why combining search results is harder than it looks DevFeed: [Reciprocal rank fusion: why combining search results is harder than it looks]() Original publisher: [Read original article]() Author: Jeff Mills Published: 2026-08-09T00:00:00Z Content type: tutorial Language: en Sources: [Redis Blog]() Topics: [AI search](), [Redis](), [real-time]() Tags: [guide](), [redis](), [retrieval](), [search](), [tech-de](), [vector]() ### AI overview A guide to reciprocal rank fusion (RRF), a method for combining keyword and vector search rankings without directly adding their raw scores. It explains the formula, the role of the constant k, why agreement between retrievers matters, and RRF's unsupervised nature. ### Source excerpt You run a keyword search and get back a ranked list with Best Matching 25 (BM25) scores. You run a vector search over the same documents and get a second list with cosine similarities. You want to merge them into a single ranking that surfaces the mos... [Next page]()