Elliott Gluck

23 results

A New Way to Query: Introducing the Atlas Search Playground

Today, MongoDB is thrilled to announce the launch of a brand new sandbox environment for Atlas Search. The Atlas Search Playground offers developers an unparalleled opportunity to quickly experiment, iterate, and collaborate on search indexes and queries, reducing the operational overhead throughout the entire software development lifecycle. What is the Atlas Search Playground? The Atlas Search Playground is a sandbox environment where you can explore the power and versatility of Atlas Search without needing to set up a full Atlas collection or waiting for your search index to build. It provides an instantaneous and frictionless way to experiment with creating indexes and crafting search queries on your own data—all in a single, user-friendly interface that requires no prior experience or account setup. Key Features: Instant access: No need to sign up or log in. Simply visit the Playground Environment page and start exploring immediately. Playground workspace: A dedicated workspace where you can add and modify data to work with, create, edit, and test search indexes, and test search queries in real-time. Pre-configured templates: Access a variety of sample templates to simulate real-world scenarios and test your search skills against diverse use cases. Shareable snapshots: Easily share your experiments and findings with colleagues or collaborators using unique URLs generated for each session. Just press Share to generate your unique Snapshot URL to share your pre-configured environment. A shareable snapshot from the Playground Ready to move into Atlas Search? Once you’re ready to move into Atlas, just click on the Go To Atlas button to sign up or log into your existing Atlas account. Once you are in Atlas, you can: Create a project, cluster, database, and collection to use with Atlas Search Tip! To use the documents from the Playground, select Add Documents and paste in the array of documents that you want to add. Create a search index Under the Data Services tab, click on the cluster name and navigate to the Atlas Search tab. Follow the setup instructions to create a search index. Tip! To use the search index from the Playground, select the JSON editor configuration method and paste in your index definition. Run a query Click on the name of your index, and select Search Tester from the navigation menu. Tip! To use the query from the Playground, click Edit $search query to open the query editor and paste in the query. If the query has multiple stages, click on visit the aggregation pipeline . Already an Atlas user? If you're already using Atlas Search, you can easily set up the Atlas Search Playground to match your existing configurations. All you have to do is copy and paste your documents, search index definitions, and queries into the corresponding editor panels. Ready, Set, Play Ready to embark on your search journey? Visit the Atlas Search Playground now and unleash the full potential of Atlas Search. Whether you're a seasoned pro or a curious novice, there's something for everyone to discover without the need for any setup. To learn more about the Atlas Search Playground, visit our documentation . And be sure to share what you think in our user feedback portal .

May 29, 2024

How the NFSA is Using MongoDB Atlas and AI to Make Aussie Culture Accessible

Where can you find everything from facts about Kylie Minogue, to more than 6,000 Australian home movies, to a 60s pop group playing a song with a drum-playing kangaroo ? The NFSA! Founded in 1935, the National Film and Sound Archive of Australia (NFSA) is one of the oldest archives of its kind in the world. It is tasked with collecting, preserving, and sharing Australia’s audiovisual culture. According to its website, the NFSA “represents not only [Australia’s] technical and artistic achievements, but also our stories, obsessions and myths; our triumphs and sorrows; who we were, are, and want to be.” The NFSA’s collection includes petabytes of audiovisual data—including broadcast-quality news footage, TV shows, and movies, high-resolution photographs, radio shows, and video games—plus millions of physical and contextual items like costumes, scripts, props, photographs, and promotional materials, all tucked away in a warehouse. “Today, we have eight petabytes of data, and our data is growing from one to two petabytes each year,” said Shahab Qamar, software engineering manager at NFSA. Making this wealth of data easily accessible to users across Australia (not to mention all over the world) has led to a number of challenges, which is where MongoDB Atlas—which helps developers simplify and accelerate building with data—comes in. Don’t change (but apply a few updates) Because of its broad appeal, the NFSA's collection website alone receives an average of 100,000 visitors each month. When Qamar joined the NFSA in 2020, he saw an opportunity to improve the organization’s web platform. His aim was to ensure the best possible experience for the site’s high number of daily visitors, which had begun to plateau. This included a website refresh, as well as addressing technical issues related to handling site traffic, due to the site being hosted on on-premises servers. The site also wasn’t “optimized for Google Analytics,” said Qamar. In fact, the NFSA website was invisible to Google and other search engines, so he knew it was time for a significant update, which also presented an opportunity to set up strong data foundations to build deeper capabilities down the line. But first, Qamar and team needed to find a setup that could serve the needs of the NFSA and Australia’s 26 million residents more robustly than their previous solution. Specifically, Qamar said, the NFSA was looking for a fully managed database that could also implement search at scale, as well as a system that his small team of five could easily manage. It also needed to ensure high levels of resiliency and the ability to work with more than one cloud provider. The previous NFSA site also didn’t support content delivery networks , he added. MongoDB Atlas supported all of the use cases the NFSA was looking for, Qamar said, including the ability to support multi-cloud hosting. And because Atlas is fully managed, it would readily meet the NFSA's requirements. In July 2023, after months of development, the new and greatly improved NFSA website was launched. The redesign was immediately impactful: Since the NFSA’s redesigned site was launched, the number of users visiting the collection search website has gone up 200%, and content requests—which the NFSA access team responds to on a case-by-case basis—have gone up 16%. (Getting search) back in black While the previous version of the NFSA site included search, the prior functionality was prone to crashing, and the quality of the results was often poor, Qamar said. For example, search results were delivered alphabetically rather than based on relevance, and the previous search didn’t support fine-tuning of relevance based on matches in specific fields. So, as part of its site redesign, the NFSA was looking to add full text search, relevance-based search results, faceting, and pagination. MongoDB Atlas Search —which integrates the database, search engine, and sync mechanism into a single, unified, fully managed platform—ticked all of those boxes. A search results page on the NFSA website Indeed, the NFSA compared search results from its old site to its new MongoDB Atlas site and “found that MongoDB Atlas-based searches were more relevant and targeted,” Qamar said. Previously, configuring site search required manual coding and meant downtime for the site, he noted. “The whole setup wasn’t very developer friendly and, therefore, a barrier to working efficiently with search configuration and fine-tuning,” Qamar said. In comparison, MongoDB Atlas allowed for simple configuration and fine-tuning of the NFSA's search requirements. The NFSA has also been using MongoDB Atlas Charts . Charts help the NFSA easily visualize its collection by custom grouping (like production year or genre), as well as helping the NFSA see which items are most popular with users. “Charts have helped us understand how our collection is growing and evolving over time,” Qamar said. NFSA’s use of MongoDB Charts Can’t get you (AI) out of my head Now, the NFSA—inspired by Qamar’s own training in machine learning and the broad interest in all things AI—is exploring how it can use Atlas Vector Search and generative AI tools to allow users to explore content buried in the NFSA collection. One example cited is putting transcriptions of audiovisual files in NFSA’s collection into a vector database for retrieval-augmented generation (RAG). The NFSA has approximately 27 years worth—meaning, it would take 27 years to play it all back—of material to transcribe, and is currently developing a model to accurately capture the Australian dialect so the work is transcribed correctly. Ultimately, the NFSA is interested in building a RAG-powered AI bot to provide historically and contextually accurate information about work in the NFSA’s archive. The NFSA is also exploring how it can use RAG to deliver accurate, conversation-like search results without training large language models itself, and whether it can leverage AI to help restore some of the older videos in its collection. Qamar and team are also interested in vectorizing audio-visual material for semantic analysis and genre-based classification of collection material at scale, he said. “Historically, we’ve been very metadata-driven and keyword-driven, and I think that’s a missed opportunity. Because when we talk about what an archive does, we archive stories,” Qamar said of the possibilities offered by vectors. “An example I use is, what if the world ended tomorrow? And what if aliens came to Earth and only saw our metadata, what image of Australia would they see? Is that a true image of what Australia is really like?” Qamar said. “How content is described is important, but content’s imagery, the people in it, and the audio and words being spoken are really important. Full-text search can take you somewhere along the way, but vector search allows you to look things up in a semantic manner. So it’s more about ideas and concepts than very specific keywords,” he said. If you’re interested in learning how MongoDB helps accelerate and simplify time-to-mission for federal, state, and local governments, defense agencies, education, and across the public sector, check out MongoDB for Public Sector . Check out MongoDB Atlas Vector Search to learn more about how Vector Search helps organizations like the NFSA build applications powered by semantic search and gen AI. *Note that this story’s subheads come from Australian song titles!

May 14, 2024

Workload Isolation for More Scalability and Availability: Search Nodes Now on Google Cloud

June 25, 2024: Announcing Search Nodes in general availability on Microsoft Azure Today we’re excited to take the next step in bringing scalable, dedicated architecture to your search experiences with the introduction of Atlas Search Nodes, now in general availability for Google Cloud. This post is also available in: Deutsch , Français , Español , Português , Italiano , 한국어 , 简体中文 . Since our initial announcement of Search Nodes in June of 2023, we’ve been rapidly accelerating access to the most scalable dedicated architecture, starting with general availability on AWS and now expanding to general availability on Google Cloud. We'd like to give you a bit more context on what Search Nodes are and why they're important to any search experience running at scale. Search Nodes provide dedicated infrastructure for Atlas Search and Vector Search workloads to enable even greater control over search workloads. They also allow you to isolate and optimize compute resources to scale search and database needs independently, delivering better performance at scale and higher availability. One of the last things developers want to deal with when building and scaling apps is having to worry about infrastructure problems. Any downtime or poor user experiences can result in lost users or revenue, especially when it comes to your database and search experience. This is one of the reasons developers turn to MongoDB, given the ease of use of having one unified system for your database and search solution. With the introduction of Atlas Search Nodes, we’ve taken the next step in providing our builders with ultimate control, giving them the ability to remain flexible by scaling search workloads without the need to over-provision the database. By isolating your search and database workloads while at the same time automatically keeping your search cluster data synchronized with operational data, Atlas Search and Atlas Vector Search eliminate the need to run a separate ETL tool, which takes time and effort to set up and is yet another fail point for your scaling app. This provides superior performance and higher availability while reducing architectural complexity and wasted engineering time recovering from sync failures. In fact, we’ve seen a 40% to 60% decrease in query time for many complex queries, while eliminating the chances of any resource contention or downtime. With just a quick button click, Search Nodes on Google Cloud offer our existing Atlas Search and Vector Search users the following benefits: Higher availability Increased scalability Workload isolation Better performance at scale Improved query performance We offer both compute-heavy search-specific nodes for relevance-based text search, as well as a memory-optimized option that is optimal for semantic and retrieval augmented generation (RAG) production use cases with Atlas Vector Search. This makes resource contention or availability issues a thing of the past. Search Nodes are easy to opt into and set up — to start, jump on into the MongoDB UI and follow the steps do the following: Navigate to your “Database Deployments” section in the MongoDB UI Click the green “+Create” button On the “Create New Cluster” page, change the radio button for Google Cloud for “Multi-cloud, multi-region & workload isolation” to enable Toggle the radio button for “Search Nodes for workload isolation” to enable. Select the number of nodes in the text box Check the agreement box Click “Create cluster” For existing Atlas Search users, click “Edit Configuration” in the MongoDB Atlas Search UI and enable the toggle for workload isolation. Then the steps are the same as noted above. Jump straight into our docs to learn more!

March 28, 2024

利用工作负载隔离提高可扩展性和可用性:Search Nodes 现已在 Google Cloud 上提供

今天,我们很高兴地宣布 Atlas Search Nodes(公开预览版)现已在 Google Cloud 上提供,这离我们针对搜索体验提供可扩展的专用架构这个目标更进了一步。 自 2023 年 6 月首次宣布推出 Search Nodes 以来,我们一直在加快这个最具可扩展性的专用架构的应用速度, 先是在 AWS 上正式发布 ,现在又在 Google Cloud 上发布了它的公开预览版。让我们简单介绍一下什么是 Search Nodes,以及它为何对任何大规模运行的搜索体验非常重要。 Search Nodes 可为 Atlas Search 和 Vector Search 工作负载提供专用基础架构,让您能够对搜索工作负载拥有更大的控制力度。通过隔离并优化计算资源来独立地扩展搜索和数据库需求,从而大规模提升性能并实现更高的可用性。 在构建和扩展应用时,开发者最不愿处理的一件事情就是要担心基础架构问题。任何停机或不佳的用户体验都可导致用户流失或收入受损,在涉及数据库和搜索体验时,这种影响尤为明显。这也是开发者纷纷转向 MongoDB 的原因之一,因为它可以让开发者为数据库和搜索解决方案使用一个统一的系统。 随着 Atlas Search Nodes 的推出,我们在为构建者提供最大控制力度方面又迈出了重要一步。现在,构建者可以扩展搜索工作负载,而无需过度预配数据库,因此能够保持灵活性。利用 Atlas Search 和 Atlas Vector Search,您可以在隔离搜索和数据库工作负载的同时,自动保持搜索集群数据与操作数据的同步。这样,您就无需运行单独的 ETL 工具,也就不用耗费时间和精力进行额外设置,从而避免在扩展应用时出错。这有助于提升性能和可用性,同时降低架构复杂性,以及减少从同步失败事件中恢复所耗费的工程时间。事实上,我们已经看到许多复杂查询的查询时间减少了 40% - 60%,资源争用或停机问题也得到了解决。 只需切换一下按钮,Google Cloud 上的 Search Nodes 就能为使用 Atlas Search 和 Vector Search 的用户提供以下优势: 更高的可用性 更强的可扩展性 工作负载隔离 大规模提升性能 更好的查询性能 我们为基于相关性的文本搜索提供计算密集型且特定于搜索的节点,同时还提供内存优化选项,该选项最适合使用 Atlas Vector Search 的语义和 RAG 生产用例。这解决了一直以来存在的资源争用或可用性问题。 启用和设置 Search Nodes 非常简单,只需前往 MongoDB 用户界面并执行以下操作: 前往 MongoDB 用户界面中的“数据库部署”部分 单击绿色的“+创建”按钮 在“创建新集群”页面上,将 Google Cloud 的“多云、多区域和工作负载隔离”单选按钮切换至“开启” 将“用于工作负载隔离的 Search Nodes”单选按钮切换至“开启”。在文本框中选择节点数 勾选协议框 单击“创建集群” 对于使用 Atlas Search 的用户,请单击 MongoDB Atlas Search 用户界面中的“修改配置”,并开启工作负载隔离的切换开关。后续步骤与之前所述步骤相同。 直接跳转至我们的文档以了解更多信息 !

March 28, 2024

확장성 및 가용성 향상을 위한 워크로드 격리: 이제 Google Cloud에서 노드 검색 가능

MongoDB는 확장 가능한 전용 아키텍처를 검색 환경에 도입하는 다음 단계로 나아가게 되어 매우 기쁘게 생각하며, 이의 일환으로 Google Cloud 용 공개 미리보기에서 Atlas Search Nodes를 선보입니다. 2023년 6월에 Search Nodes를 처음 발표한 이후, MongoDB는 AWS 에서의 일반 공개로 시작하여 오늘날 Google Cloud에서의 공개 미리보기에 이르기까지 확장성이 가장 뛰어난 전용 아키텍처에 대한 액세스를 급속히 앞당겨왔습니다. Search Nodes가 무엇인지, 그리고 대규모로 실행되는 모든 검색 환경에서 Search Nodes가 중요한 이유는 무엇인지에 대해 좀 더 자세히 설명하겠습니다. Search Nodes는 Atlas Search 및 Vector Search 워크로드를 위한 전용 인프라를 제공하므로 검색 워크로드를 더욱 효과적으로 제어할 수 있습니다. 컴퓨팅 리소스를 격리하고 최적화하여 검색 및 데이터베이스 요구 사항을 별개로 확장함으로써 우수한 성능과 더욱 높은 가용성을 대규모로 제공합니다. 개발자가 앱을 구축하고 확장할 때 가장 원치 않는 일 중 하나는 인프라 문제를 걱정하는 것입니다. 다운타임이나 불만족스러운 사용자 경험은 사용자 및 수익 손실을 초래하며, 이는 특히 데이터베이스 및 검색 환경의 경우 더더욱 더 그렇습니다. 이러한 맥락에서, 개발자들이 MongoDB를 선택하는 이유 중 하나는 데이터베이스와 검색 솔루션을 하나의 통합된 시스템으로 간편하게 사용할 수 있기 때문입니다. MongoDB는 Atlas Search Nodes를 도입함으로써 빌더에게 최상의 제어를 제공하고, 데이터베이스를 과도하게 프로비저닝하지 않고도 검색 워크로드 확장이 가능하여 유연성 유지가 가능하기 위한 다음 단계로 나아갔습니다. Atlas Search 및 Atlas Vector Search는 검색 및 데이터베이스 워크로드를 분리하는 동시에 검색 cluster 데이터를 운영 데이터와 자동으로 동기화하므로, 설정에 시간과 노력이 필요하고 확장 앱의 또 다른 실패 요인으로 작용하는 별도의 ETL 도구를 실행할 필요가 없습니다. 이를 통해 뛰어난 성능과 높은 가용성을 제공하는 동시에 아키텍처의 복잡성과 동기화 장애 복구에 낭비되는 엔지니어링 시간을 줄일 수 있습니다. 실제로 많은 복잡한 쿼리의 쿼리 시간이 40~60% 감소하는 동시에 리소스 경합이나 다운타임이 발생할 가능성이 제거되는 것이 확인되었습니다. Google Cloud의 Search Nodes는 빠른 버튼 전환만으로 기존 Atlas Search 및 Vector Search 사용자에게 다음과 같은 이점을 제공합니다. 향상된 가용성 확장성 증가 워크로드 격리 대규모로 성능 향상 쿼리 성능 향상 정확도 기반 텍스트 검색을 위한 컴퓨팅 집약적인 검색 전용 노드와 Atlas Vector Search의 시맨틱 및 RAG 생산 사용 사례에 최적화된 메모리 최적화 옵션을 모두 제공합니다. 따라서 이제 더 이상 리소스 경합이나 가용성 문제는 없습니다. Search Nodes는 선택과 설정이 쉽습니다. 시작하려면 MongoDB UI로 이동하여 다음을 수행하세요. MongoDB UI의 '데이터베이스 배포' 섹션으로 이동합니다. 초록색 '+생성' 버튼을 클릭합니다 '새 클러스터 생성' 페이지에서 Google Cloud의 '멀티 클라우드, 멀티 리전 및 워크로드 격리' 라디오 버튼을 변경하여 활성화합니다. '워크로드 격리를 위한 Search Nodes' 라디오 버튼을 전환하여 활성화합니다. 텍스트 상자에서 노드 수를 선택합니다. 동의란을 선택합니다. '클러스터 생성'을 클릭합니다. 기존 Atlas Search 사용자의 경우, MongoDB Atlas Search UI에서 '구성 편집'을 클릭하고 워크로드 격리 토글을 활성화합니다. 이후 단계는 위 설명과 동일합니다. 자세히 알아보려면 바로 문서로 이동하세요 !

March 28, 2024

Isolamento do volume de trabalho para maior escalabilidade e disponibilidade: Nós de Pesquisa agora no Google Cloud

Estamos empolgados em dar o próximo passo para trazer uma arquitetura com escalabilidade e dedicada às suas experiências de pesquisa, com a apresentação dos Nós de Pesquisa do Atlas na pré-visualização pública para o Google Cloud. Depois do nosso anúncio inicial dos Nós de Pesquisa em junho de 2023, estamos acelerando rapidamente o acesso à arquitetura dedicada com mais escalabilidade, começando com a disponibilidade geral no AWS e agora expandindo para a pré-visualização pública no Google Cloud. Vamos fornecer um pouco mais de contexto sobre o que são os Nós de Pesquisa e porque eles são importantes para qualquer experiência de pesquisa executada em escala. Os Nós de Pesquisa fornecem infraestrutura dedicada para volume de trabalho no Atlas Search e Vector Search para fornecer controle ainda maior sobre os volumes de trabalho de pesquisa. Ele isola e otimiza os recursos de computação para dimensionar as necessidades de pesquisa e de banco de dados de forma independente, proporcionando um desempenho melhor em escala e maior disponibilidade. Uma das últimas coisas com que os desenvolvedores querem lidar ao criar e dimensionar aplicativos é ter que se preocupar com problemas de infraestrutura. Qualquer tempo de inatividade ou experiência ruim para o usuário representa perda de usuários ou de receita, principalmente quando se trata do seu banco de dados e da experiência de pesquisa. Esse é um dos motivos pelos quais os desenvolvedores recorrem ao MongoDB, dada a facilidade de uso de um sistema unificado para seu banco de dados e solução de pesquisa. Com a introdução dos Nós de Pesquisa do Atlas demos o próximo passo para fornecer aos nossos desenvolvedores o máximo de controle, podendo permanecer flexíveis e dimensionar os volumes de pesquisa sem sermos forçados a provisionar o banco de dados em excesso. Ao isolar os volume de pesquisa e de banco de dados e manter os dados do cluster de pesquisa sincronizados com os dados operacionais automaticamente, o Atlas Search e o Atlas Vector Search eliminam a necessidade de executar uma ferramenta de ETL separada, o que leva tempo e esforço para configurar e é mais um ponto de falha para seu aplicativo de dimensionamento. Isso proporciona desempenho superior e maior disponibilidade, além de reduzir a complexidade da arquitetura e o desperdício de tempo de engenharia na recuperação das falhas de sincronização. De fato, observamos uma redução de 40% a 60% no tempo de query para muitas consultas complexas ao mesmo tempo em que eliminamos as chances de qualquer contenção de recursos ou tempo de inatividade. Com apenas uma troca rápida de botões, os Nós de Pesquisa no Google Cloud oferecem aos usuários existentes do Atlas Search e do Vector Search os seguintes benefícios: Maior disponibilidade Escalabilidade aumentada Isolamento da carga de trabalho Melhor desempenho em escala Melhor desempenho de consulta Oferecemos tanto Search Nodes específicos com alto consumo de computação para pesquisa de texto baseada em relevância quanto uma opção otimizada para memória, que é ideal para casos de uso de produção semântica e RAG com o Atlas Vector Search. Isso faz com que os problemas de contenção ou disponibilidade de recursos sejam coisa do passado. Os Nós de Pesquisa são fáceis de configurar, para começar acesse a interface do usuário do MongoDB e faça o seguinte: Navegue até a seção "Sistemas de Banco de dados" na interface do usuário do MongoDB Clique no botão verde “+Criar” Para ativá-lo, na página "Criar novo cluster" altere o botão de opção do Google Cloud para "Multinuvem, multiregião e isolamento do volume de trabalho" Para habilitá-los, alterne o botão de opção para "Nós de Pesquisa para isolamento do volume de trabalho". Selecione o número de nós na caixa de texto Marque a caixa de seleção do contrato Clique em "Criar cluster" Para usuários existentes do Atlas Search, clique em "Editar configuração" na interface do usuário do MongoDB Atlas Search e habilite o botão que alterna para o isolamento do volume de trabalho. Em seguida, as etapas são as mesmas mencionadas acima. Confira nossos documentos para saber mais!

March 28, 2024

Isolamento del carico di lavoro per ottenere maggiore scalabilità e disponibilità: Nodi di ricerca ora su Google Cloud

Oggi siamo entusiasti di fare il passo successivo nel portare un'architettura scalabile e dedicata alle tue esperienze di ricerca, con l'introduzione dei Nodi di ricerca Atlas in public preview per Google Cloud. Dopo l'annuncio iniziale dei Nodi di ricerca nel giugno del 2023, abbiamo rapidamente accelerato l'accesso all'architettura dedicata più scalabile, iniziando con la disponibilità generale su AWS e ora con la public preview su Google Cloud. Vediamo di capire meglio che cosa sono i Nodi di ricerca e perché sono importanti per qualsiasi esperienza di ricerca in scala. I Nodi di ricerca forniscono un'infrastruttura dedicata per i carichi di lavoro di Atlas Search e Vector Search , per consentire un controllo ancora maggiore sui carichi di lavoro di ricerca. Isola e ottimizza le risorse di calcolo per scalare le esigenze di ricerca e database in modo indipendente, offrendo prestazioni migliori su larga scala e maggiore disponibilità. Una delle ultime problematiche che gli sviluppatori intendono affrontare quando creano e scalano le app è doversi preoccupare dei problemi di infrastruttura. Qualsiasi tempo di inattività o esperienza negativa determina una perdita di utenti o di fatturato, soprattutto per quanto riguarda il database e l'esperienza di ricerca. Questo è uno dei motivi per cui gli sviluppatori si rivolgono a MongoDB, data la facilità d'uso di poter disporre di un sistema unificato per il database e la soluzione di ricerca. Con l'introduzione dei Nodi di ricerca Atlas abbiamo compiuto il passo successivo offrendo ai nostri sviluppatori il massimo controllo, poiché possono rimanere flessibili e scalare i carichi di lavoro di ricerca senza essere costretti a eseguire un provisioning eccessivo del database. Isolando i carichi di lavoro di ricerca e database e al contempo mantenendo automaticamente i dati del cluster di ricerca sincronizzati con i dati operativi, Atlas Search e Atlas Vector Search consentono di non dover eseguire uno strumento ETL separato, la cui configurazione richiede tempo e impegno e che rappresenta pur sempre un altro punto di errore per la propria app di scalabilità. Ciò consente prestazioni superiori e offre maggiore disponibilità, riducendo al contempo la complessità dell'architettura e gli sprechi di tempo di progettazione per il ripristino da errori di sincronizzazione. In effetti, abbiamo riscontrato una riduzione del 40% - 60% del tempo di esecuzione delle query per molte query complesse, eliminando al contempo la possibilità di conflitti di risorse o tempi di inattività. Con un semplice cambio di pulsante, i Nodi di ricerca su Google Cloud offrono ai nostri utenti di Atlas Search e Vector Search i seguenti vantaggi: Disponibilità più elevata Aumento della scalabilità Isolamento dei carichi di lavoro Prestazioni migliori su larga scala Miglioramento delle prestazioni delle query Offriamo sia Search Nodes specifici per la ricerca ad alto carico di calcolo per la ricerca di testo basata sulla pertinenza, sia un'opzione ottimizzata per la memoria che è ideale per casi d'uso di produzione semantica e RAG con Atlas Vector Search. Ciò rende i problemi di contesa o disponibilità delle risorse un vecchio ricordo. È facile attivare e impostare i Nodi di ricerca: per iniziare, accedi all'IU di MongoDB ed esegui le seguenti operazioni: Vai alla sezione "Distribuzioni di database" nell'IU di MongoDB Fai clic sul pulsante verde "+Crea" Nella pagina "Crea nuovo cluster", modifica il pulsante di opzione per Google Cloud in "Isolamento multi-cloud, multi-regione e carico di lavoro" per abilitare Attiva il pulsante di opzione "Nodi di ricerca per l'isolamento del carico di lavoro" per abilitare. Seleziona il numero di nodi nella casella di testo Seleziona la casella di accordo Fai clic su "Crea cluster" Per gli utenti esistenti di Atlas Search, fai clic su "Modifica configurazione" nell'IU di MongoDB Atlas Search e abilita l'interruttore per l'isolamento del carico di lavoro. Successivamente, i passaggi sono gli stessi indicati sopra. Per maggiori informazioni, consulta i nostri documenti .

March 28, 2024

Isolation des charges de travail pour plus d'évolutivité et de disponibilité : nœuds de recherche désormais disponibles sur Google Cloud

Aujourd'hui, nous sommes ravis de passer à l'étape suivante en apportant une architecture évolutive et dédiée à vos expériences de recherche, avec l'introduction des nœuds de recherche d'Atlas dans la version préliminaire publique de Google Cloud. Après l'annonce initiale des nœuds de recherche en juin 2023, nous avons rapidement accéléré l'accès à l'architecture dédiée la plus évolutive, en commençant par la disponibilité générale sur AWS , puis en l'étendant à la version préliminaire publique sur Google Cloud. Découvrons un peu plus de contexte sur ce que sont les nœuds de recherche et pourquoi ils sont importants pour toute expérience de recherche fonctionnant à l'échelle. Les nœuds de recherche fournissent une infrastructure dédiée aux charges de travail Atlas Search et Vector Search afin d'offrir un contrôle encore plus renforcé sur les charges de travail de recherche. Isolez et optimisez les ressources de calcul pour répartir indépendamment les besoins de recherche et de base de données, offrant ainsi de meilleures performances à grande échelle et une plus grande disponibilité. Les problèmes d'infrastructure représentent l'une des dernières choses que les développeurs souhaitent gérer lorsqu'ils créent et mettent à l'échelle des applications. Tout temps d'arrêt ou mauvaise expérience utilisateur se traduit par une perte d'utilisateurs ou de chiffre d'affaires, en particulier lorsque cela concerne votre base de données et de l'expérience de recherche. C'est l'une des raisons pour lesquelles les développeurs se tournent vers MongoDB, étant donné la facilité d'utilisation d'un système unifié pour votre base de données et votre solution de recherche. Avec l'introduction des nœuds de recherche d'Atlas, nous avons franchi une nouvelle étape en offrant à nos constructeurs un contrôle ultime, leur permettant ainsi de rester flexibles en étant capables de répartir les charges de travail de recherche sans être obligés de surapprovisionner la base de données. En isolant vos charges de travail de recherche et de base de données tout en synchronisant automatiquement les données de votre cluster de recherche avec les données opérationnelles, Atlas Search et Atlas Vector Search éliminent le besoin d'exécuter un outil ETL distinct, dont la configuration demande du temps et des efforts et constitue un autre point d'échec pour votre application de mise à l'échelle. Cela permet d'obtenir des performances supérieures et une plus grande disponibilité, tout en réduisant la complexité architecturale et le temps d'ingénierie perdu lors de la récupération après des échecs de synchronisation. En effet, nous avons constaté une diminution de 40 à 60 % du temps de requête pour de nombreuses requêtes complexes, parallèlement à une élimination des risques de conflit de ressources ou de temps d'arrêt. D'un simple clic, les nœuds de recherche sur Google Cloud offrent à nos utilisateurs existants d'Atlas Search et de Vector Search les avantages suivants : Disponibilité plus élevée Évolutivité accrue Isolation des charges de travail Meilleures performances à l'échelle Performances des requêtes renforcées Nous proposons à la fois des nœuds destinés à la recherche gourmande en calcul pour la recherche de texte basée sur la pertinence, ainsi qu'une option optimisée pour la mémoire, idéale pour les cas d'utilisation sémantiques et de production RAG avec Atlas Vector Search. Les problèmes de conflits ou de disponibilité des ressources appartiennent désormais au passé. Les nœuds de recherche sont faciles à utiliser et à configurer. Pour commencer, accédez à l'UI de MongoDB et procédez comme suit : Accédez à la section « Déploiements de bases de données » de l'UI MongoDB. Cliquez sur le bouton vert « + Créer ». Sur la page « Créer un cluster », remplacez le bouton d'option de Google Cloud par « Isolation multi-cloud, multi-région et des charges de travail » pour l'activer. Activez le bouton d'option « Nœuds de recherche pour l'isolation des charges de travail ». Sélectionnez le nombre de nœuds dans la zone de texte. Cochez la case d'accord. Cliquez sur « Créer un cluster ». Pour les utilisateurs existants d'Atlas Search, cliquez sur « Modifier la configuration » dans l'UI de MongoDB Atlas Search et activez l'option d'isolation des charges de travail. Les étapes sont alors les mêmes que celles indiquées ci-dessus. Accédez directement à nos documents pour en savoir plus !

March 28, 2024

Aislamiento de carga de trabajo para mayor escalabilidad y disponibilidad: buscar nodos ahora en Google Cloud

Hoy estamos entusiasmados de dar el siguiente paso para llevar una arquitectura escalable y dedicada a sus experiencias de búsqueda, con la introducción de Atlas Search Nodes en vista previa pública para Google Cloud. Después de nuestro anuncio inicial de Search Nodes en junio de 2023, estuvimos acelerando rápidamente el acceso a la arquitectura dedicada más escalable, comenzando con la disponibilidad general en AWS y ahora expandiéndonos a la vista previa pública en Google Cloud. Proporcionemos un poco más de contexto sobre qué son los nodos de búsqueda y por qué son importantes para cualquier experiencia de búsqueda que se ejecute a escala. Los nodos de búsqueda proporcionan una infraestructura dedicada para las cargas de trabajo de Atlas Search y Vector Search para proporcionar un control aún mayor sobre las cargas de trabajo de búsqueda. Aísle y optimice los recursos informáticos para escalar las necesidades de búsqueda y base de datos de forma independiente, ofreciendo un mejor rendimiento a escala y una mayor disponibilidad. Una de las últimas cosas con las que los desarrolladores quieren lidiar al crear y escalar aplicaciones es tener que preocuparse por problemas de infraestructura. Cualquier tiempo de inactividad o mala experiencia de usuario significa pérdida de usuarios o ingresos, especialmente cuando se trata de su base de datos y experiencia de búsqueda. Esta es una de las razones por las que los desarrolladores recurren a MongoDB, dada la facilidad de uso de tener un sistema unificado para su base de datos y solución de búsqueda. Con la introducción de Atlas Search Nodes dimos el siguiente paso para proporcionar a nuestros constructores el máximo control, pudiendo seguir siendo flexibles al ser capaces de escalar las cargas de trabajo de búsqueda sin tener que aprovisionar en exceso la base de datos. Al aislar sus cargas de trabajo de búsqueda y base de datos y al mismo tiempo mantener automáticamente los datos de su cluster de búsqueda sincronizados con los datos operativos, Atlas Search y Atlas Vector Search eliminan la necesidad de ejecutar una herramienta ETL separada, que requiere tiempo y esfuerzo de configuración y es otro punto de falla para su aplicación de escalado. Esto proporciona un rendimiento superior y una mayor disponibilidad, al tiempo que reduce la complejidad de la arquitectura y la pérdida de tiempo de ingeniería en la recuperación de fallos de sincronización. De hecho, hemos observado una reducción del 40% al 60% en el tiempo de consulta para muchas consultas complejas, al tiempo que se eliminan las posibilidades de contención de recursos o tiempos de inactividad. Con solo un botón rápido, los nodos de búsqueda en Google Cloud ofrecen a nuestros usuarios existentes de Atlas Search y Vector Search los siguientes beneficios: Mayor disponibilidad Mayor escalabilidad Aislamiento de la carga de trabajo Mejor rendimiento a escala Rendimiento de consultas mejorado Ofrecemos tanto Nodos específicos de búsqueda con gran carga computacional para la búsqueda de texto basada en relevancia, como una opción optimizada para memoria que es óptima para casos de uso semántico y de producción RAG con Atlas Vector Search. Esto hace que los problemas de contención o disponibilidad de recursos sean cosa del pasado. Los nodos de búsqueda son fáciles de aceptar y establecer: para empezar, vaya a la IU de MongoDB y haga lo siguiente: Vaya a la sección “Implementaciones de bases de datos” en la IU de MongoDB. Haga clic en el botón verde “+Crear” En la página “Crear nuevo cluster”, cambie el botón de opción de Google Cloud por “Multi-cloud, multiregión & aislamiento de carga de trabajo” para activarlo. Active el botón de opción “Buscar nodos para el aislamiento de carga de trabajo”. Seleccione el número de nodos en el cuadro de texto Marque la casilla de acuerdo. Haga clic en “Crear cluster”. Para los usuarios existentes de Atlas Search, haga clic en “Editar configuración” en la IU de MongoDB Atlas Search y habilite el interruptor para el aislamiento de cargas de trabajo. Entonces los pasos son los mismos que se indicaron anteriormente. ¡Vaya directamente a nuestros docs para obtener más información!

March 28, 2024

Workload-Isolierung für mehr Skalierbarkeit und Verfügbarkeit: Search Nodes jetzt auf Google Cloud

Heute haben wir den nächsten Schritt bei der Einführung einer skalierbaren, dedizierten Architektur für Ihre Sucherlebnisse gemacht und Atlas Search Nodes als öffentliche Vorschau für Google Cloud vorgestellt. Nach unserer ersten Ankündigung von Search Nodes im Juni 2023 haben wir den Zugang zu der am besten skalierbaren dedizierten Architektur schnell beschleunigt, angefangen mit der allgemeinen Verfügbarkeit auf AWS und jetzt auch mit der öffentlichen Vorschau auf Google Cloud. Im Folgenden erläutern wir etwas genauer, was Search Nodes sind und warum sie für jedes Sucherlebnis im großen Maßstab wichtig sind. Search Nodes bieten eine dedizierte Infrastruktur für Atlas Search - und Vector Search -Workloads, um eine noch bessere Kontrolle über Search-Workloads zu ermöglichen. Isolieren und optimieren Sie Rechenressourcen, um Such- und Datenbankanforderungen unabhängig voneinander zu skalieren, und sorgen Sie so für eine bessere Leistung im großen Maßstab und eine höhere Verfügbarkeit. Eines der letzten Dinge, mit denen sich Entwickler bei der Entwicklung und Skalierung von Apps beschäftigen möchten, sind Probleme mit der Infrastruktur. Jede Ausfallzeit oder schlechte Benutzererfahrung bedeutet verlorene Benutzer oder Einnahmen, insbesondere wenn es um Ihre Datenbank und die Suchfunktion geht. Dies ist einer der Gründe, warum sich Entwickler für MongoDB entscheiden, denn es ist einfach, ein einheitliches System für Ihre Datenbank- und Suchlösung zu haben. Mit der Einführung von Atlas Search Nodes haben wir den nächsten Schritt unternommen, um unseren Entwicklern die ultimative Kontrolle zu geben. Sie bleiben flexibel, indem sie Sucharbeitslasten skalieren können, ohne gezwungen zu sein, die Datenbank zu überlasten. Durch die Isolierung Ihrer Such- und Datenbank-Workloads und die gleichzeitige automatische Synchronisierung Ihrer Suchclusterdaten mit den Betriebsdaten machen Atlas Search und Atlas Vector Search ein separates ETL-Tool überflüssig, dessen Einrichtung Zeit und Mühe kostet und einen weiteren Fehlerpunkt für Ihre skalierende App darstellt. Dies sorgt für eine überragende Leistung und höhere Verfügbarkeit und reduziert gleichzeitig die architektonische Komplexität und die Zeitverschwendung bei der Wiederherstellung nach Synchronisationsfehlern. In der Tat konnten wir bei vielen komplexen Abfragen eine Verringerung der Abfragezeit um 40 bis 60 % feststellen, während gleichzeitig die Gefahr von Ressourcenkonflikten oder Ausfallzeiten beseitigt wurde. Mit einem einfachen Knopfdruck bieten Search Nodes auf Google Cloud unseren bestehenden Atlas Search- und Vector Search-Benutzern die folgenden Vorteile: Höhere Verfügbarkeit Erhöhte Skalierbarkeit Workload-Isolation Bessere Skalierungsleistung Verbesserte Abfrageleistung Wir bieten sowohl rechenintensive suchspezifische Knoten für die relevanzbasierte Textsuche als auch eine speicheroptimierte Option, die für semantische und RAG -Produktionsanwendungen mit Atlas Vector Search optimal ist. Damit gehören Ressourcenkonflikte oder Verfügbarkeitsprobleme der Vergangenheit an. Search Nodes sind einfach zu aktivieren und einzurichten. Gehen Sie dazu in die MongoDB-Benutzeroberfläche und führen Sie die folgenden Schritte aus: Navigieren Sie in der MongoDB-Benutzeroberfläche zu Ihrem Abschnitt „Datenbankbereitstellungen“ Klicken Sie auf die grüne Schaltfläche „+Erstellen“ Ändern Sie auf der Seite „Neuen Cluster erstellen“ die Optionsschaltfläche für Google Cloud für „Multi-Cloud, mehrere Regionen & Workload-Isolierung“, um es zu aktivieren. Schalten Sie das Optionsfeld für „Search Nodes für Workload-Isolierung“ um, um es zu aktivieren. Wählen Sie die Anzahl der Knoten im Textfeld aus Aktivieren Sie das Kontrollkästchen „Vereinbarung“ Klicken Sie auf „Cluster erstellen“ Für bestehende Atlas Search-Benutzer klicken Sie in der MongoDB Atlas Search-Benutzeroberfläche auf „Konfiguration bearbeiten“ und aktivieren Sie den Schalter für die Workload-Isolierung. Dann sind die Schritte die gleichen wie oben beschrieben. Sehen Sie sich unsere Dokumente direkt an, um mehr zu erfahren!

March 28, 2024

A Discussion with VISO TRUST: Expanding Atlas Vector Search to Provide Better-Informed Risk Decisions

We recently caught up with the team at VISO TRUST to check in and learn more about their use of MongoDB and their evolving search needs (if you missed our first story, read more about VISO TRUST’s AI use cases with MongoDB on our first blog ). VISO TRUST is an AI-powered third-party cyber risk and trust platform that enables any company to access actionable vendor security information in minutes. VISO TRUST delivers the fast and accurate intelligence needed to make informed cybersecurity risk decisions at scale for companies at any maturity level. Since our last discussion back in September 2023, VISO TRUST has adopted our new dedicated Search Nodes architecture, as well as scaled up both dense and sparse embeddings and retrieval to improve the user experience for their customers. We sat down for a deeper dive with Pierce Lamb, Senior Software Engineer on the Data and Machine Learning team at VISO TRUST to hear more about the latest exciting updates. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. How have things been evolving at VISO TRUST? What are some of the new things you're excited about since we spoke last? There have definitely been some exciting developments since we last spoke. Since then, we’ve implemented a new technique for extracting information out of PDF and image files that is much more accurate and breaks extractions into clear semantic units: sentences, paragraphs, and table rows. This might sound simple, but correctly extracting semantic units out of these PDF files is not an easy task by any means. We tested the entire Python ecosystem of PDF extraction libraries, cloud-based OCR services, and more, and settled on what we believe is currently state-of-the-art. For a retrieval augmented generation (RAG) system , which includes vector search, the accuracy of data extraction is the foundation on which everything else rests. Improving this process is a big win and will continue to be a mainstay of our focus. Last time we spoke, I mentioned that we were using MongoDB Atlas Vector Search to power a dense retrieval system and that we had plans to build a re-ranking architecture. Since then I’m happy to confirm we have achieved this goal. In our intelligent question-answering service, every time a question is asked, our re-ranking architecture provides four levels of ranking and scoring to a set of possible contexts in a matter of seconds to be used by large language models (LLMs) to answer the question. One additional exciting announcement is we’re now using MongoDB Atlas Search Nodes , which allow workload isolation when scaling search independently from our database. Previously, we were upgrading our entire database instance solely because our search needs were changing so rapidly (but our database needs were not). Now we are able to closely tune our search workloads to specific nodes and allow our database needs to change at a much different pace. As an example, retraining is much easier to track and tune with search nodes that can fit the entire Atlas Search Index in memory (which has significant latency implications). As many have echoed recently, our usage of LLMs has not reduced or eliminated our use of discriminative model inference but rather increased it. As the database that powers our ML tools, MongoDB has become the place we store and retrieve training data, which is a big performance improvement over AWS S3. We continue to use more and more model inference to perform tasks like classification that the in-context learning of LLMs cannot beat. We let LLMs stick to the use cases they are really good at like dealing with imperfect human language and providing labeled training data for discriminative models. VISO TRUST's AI Q&A feature being asked a security question You mentioned the recent adoption of Search Nodes. What impacts have you seen so far, especially given your existing usage of Atlas Vector Search? We were excited when we heard the announcement of Search Nodes in General Availability , as the offering solves an acute pain point we’d been experiencing. MongoDB started as the place where our machine learning and data team backed up and stored training data generated by our Document Intelligence Pipeline. When the requirements to build a generative AI product became clear, we were thrilled to see that MongoDB had a vector search offering because all of our document metadata already existed in Atlas. We were able to experiment with, deploy, and grow our generative AI product right on top of MongoDB. Our deployment, however, was now serving multiple use cases: backing up and storing data created by our pipeline and also servicing our vector search needs. The latter forced us to scale the entire deployment multiple times when our original MongoDB use case didn’t require it. Atlas Search Nodes enable us to decouple these two use cases and scale them independently. It was incredibly easy to deploy our search data to Atlas Search Nodes, requiring only a few button clicks. Furthermore, the memory requirements of vector search can now match our Atlas Search Node deployment exactly; we do not need to consider any extra memory for our storage and backup use case. This is a crucial consideration for keeping vector search fast and streamlined. Can you go into a bit more detail on how your use cases have evolved with Vector Search, especially as it relates to dense and sparse embeddings and retrieval? We provide a Q&A system that allows clients to ask questions of the security documents they or their vendors upload. For example, if a client wanted to know what one of their vendor’s password policies is, they could ask the system that question and get an answer with cited evidence without needing to look through the documents themselves. The same system can be used to automatically answer third-party security questionnaires our clients receive by parsing the questions out of them and answering those questions using data from our client’s documents. This saves a lot of time because answering security questions can often take weeks and involve multiple departments. The above system relies on three main collections separated via the semantic units mentioned above: paragraphs, sentences, and table rows . These are extracted from various security compliance documents uploaded to the VISO TRUST platform (things like SOC2s, ISOs, and security policies, among others). Each sentence has a field with an ObjectId that links to the corresponding paragraph or table row for easy look-up. To give a sense of size, the sentences collection is in the order of tens of millions of documents and growing every day. When a question request enters the re-ranking system, sparse retrieval (keyword search for similarity) is performed and then dense retrieval using a list of IDs passed by the request to filter to a set of possible documents the context can come from. The document filtering generally takes the scope from tens of millions to tens or hundreds of thousands. Sparse/dense retrieval independently scores and ranks those thousands or millions of sentences, and return the top one hundred in a matter of milliseconds to seconds. The output of these two sets of results are merged into a final set of one hundred favoring dense results unless a sparse result meets certain thresholds. At this point, we have a set of one hundred sentences, scored and ranked by similarity to the question, using two different methods powered by Atlas Search, in milliseconds to seconds. In parallel, we pass those hundred to a multi-representational model and a cross-encoder model to provide their scoring and ranking of each sentence. Once complete, we now have four independent levels of scoring and ranking for each sentence (sparse, dense, multi-representational, and cross-encoder). This data is passed to the Weighted Reciprocal Rank Fusion algorithm which uses the four independent rankings to create a final ranking and sorting, returning the number of results requested by the caller. How are you measuring the impact or relative success of your retrieval efforts? The monolithic collections I spoke about above grow substantially daily, as we’ve almost tripled our sentence volume since first bringing data into MongoDB, while still maintaining the same low latency our users depend on. We needed a vector database partner that allowed us to easily scale as our datasets grow and continue to deliver millisecond-to-second performance on similarity searches. Our system can often have many in-flight question requests occurring in parallel and Atlas has allowed us to scale with the click of a button when we start to hit performance limits. One piece of advice I would give to readers creating a RAG system using MongoDB’s Vector Search is to use ReadPreferences to ensure that retrieval queries and other reads occur primarily on secondary nodes. We use ReadPreferece.secondariesPreferred almost everywhere and this has helped substantially with the load on the system. Lastly, can you describe how MongoDB helps you execute on your goal of helping to better make informed risk assessments? As most people involved in compliance, auditing, and risk assessment efforts will report, these essential tasks tend to significantly slow down business transactions. This is in part because the need for perfect accuracy is extremely high and also because they tend to be human-reliant and slow to adopt new technology. At VISO TRUST , we are committed to delivering that same level of accuracy, but much faster. Since 2017, we have been executing on that vision and our generative AI products represent a leap forward in enabling our clients to assess and mitigate risk at a faster pace with increased levels of accuracy. MongoDB has been a key partner in the success of our generative AI products by becoming the reliable place we can store and query the data for our AI-based results. Getting started Thanks so much to Pierce Lamb for sharing details on VISO TRUST’s AI-powered applications and experiences with MongoDB. To learn more about MongoDB Atlas Search check out our learning byte , or if you’re ready to get started, head over to the product page to explore tutorials, documentation, and whitepapers. You’ll just be a few clicks away from spinning up your own vector search engine where you can experiment with the power of vector embeddings, RAG, and more!

January 17, 2024

Vector Search 和专用 Search Nodes:现已正式发布

今天,我们非常高兴地推出了 Atlas Vector Search 和 Search Nodes 的正式发布版本 (GA),为 Atlas 平台增添了更多价值。 自从在公开预览版中发布 Atlas Vector Search 和带有 Search Nodes 的专用基础架构以来,我们注意到,对于使用向量优化搜索节点,执行更多工作负载,客户热情高涨,需求旺盛。这一新的可扩展性和性能水平确保了工作负载隔离性,并能更好地优化矢量搜索用例的资源。 利用 Atlas Vector Search ,开发者对任何数据类型均可以构建由语义搜索和生成式 AI 驱动的智能应用程序。即便用户不知道自己要查找内容的确切名称,Atlas Vector Search 也能提供相关结果,它可以使用机器学习模型为几乎任何类型的数据找到相似的结果,成功地解决了上述难题。根据 Retool 的《人工智能现状》 报告,Atlas Vector Search 在推出公开预览版后的短短五个月内,已经获得了最高的开发者净推荐分数 (NPS)(用于衡量一个人向其他人推荐一个解决方案的可能性),并成为使用第二广泛的矢量数据库。 查看我们的 AI 资源页面 ,了解有关使用 MongoDB 构建 AI 支持的应用的更多信息。 Atlas Vector Search 有两个关键用例来构建下一代应用程序: 语义搜索:基于语义相似度从非结构化数据中搜索并找到相关结果 检索增强生成 (RAG):利用您自己的实时数据源,将大型语言模型的推理能力提升到令人赞叹的程度,从而创建专为您的业务需求量身定制的 GenAI 应用程序。 Atlas Vector Search 可以充分发挥数据的潜力,无论是结构化数据还是非结构化数据,随着人工智能和大型语言模型的普及和使用率不断攀升的势头,解决关键的业务挑战。之所以能够做到这一点,是因为 Vector Search 是 MongoDB Atlas 开发者数据平台的一部分,该平台从我们灵活的文档数据模型和统一的应用程序接口开始,提供一致的体验。为了确保您从 Atlas Vector Search 中获得最大价值,我们建立了一个强大的人工智能集成生态系统,允许开发者使用他们最喜欢的大型语言模型或框架进行构建。 要了解有关 Atlas Vector Search 的更多信息,请观看我们的 视频 短片或直接进入 教程 。 Atlas Vector Search 还利用了我们新的 Search Nodes 专用架构,能够更好地优化资源配置水平,以满足特定的工作负载需求。Search Nodes 为 Atlas Search 和 Vector Search 工作负载提供专用基础架构,使您能够优化计算资源,并独立于数据库全面扩展搜索需求。Search Nodes 可提供更高的性能,实现工作负载隔离、更高的可用性,并能更好地优化资源使用。在某些情况下,利用 Search Nodes 的并发查询功能,我们发现一些用户的工作负载的查询时间缩短了 60%。 除了我们在公开预览版中提供的计算量大的搜索节点外,这个 GA 版本还包括一个内存优化的低 CPU 选项,是生产中 Vector Search 的最佳选择。这使得资源争用或导致服务中断的可能性(由于您的数据库和搜索之前共享相同的基础架构)成为过去。 "我们将其视为 Atlas Search 和 Vector Search 架构的下一次演变,进一步提升 MongoDB 开发者数据平台提供的价值。目前,Search Nodes 在 AWS 单区域集群上提供(在 Google Cloud 和 Azure 上即将提供),客户可继续使用 Google Cloud 和 Microsoft Azure 的共享基础架构。" 请阅读我们 最初的公告博文 ,查看打开 Search Nodes 的步骤,或直接跳到 教程 。 这两个功能现已可供生产使用。我们期待着看到您构建的应用, 如有任何问题请与我们联系 。

December 4, 2023