{"id":473,"date":"2023-11-13T10:00:00","date_gmt":"2023-11-13T10:00:00","guid":{"rendered":"https:\/\/jacar.es\/bases-datos-vectoriales\/"},"modified":"2023-11-13T10:00:00","modified_gmt":"2023-11-13T10:00:00","slug":"bases-datos-vectoriales","status":"publish","type":"post","link":"https:\/\/jacar.es\/en\/bases-datos-vectoriales\/","title":{"rendered":"Vector Databases: Qdrant, Pinecone, and Weaviate"},"content":{"rendered":"<p>After covering <a href=\"https:\/\/jacar.es\/chroma-vector-embedding\/\">Chroma<\/a> as a prototype option and <a href=\"https:\/\/jacar.es\/pgvector-busqueda-semantica\/\">pgvector<\/a> as a PostgreSQL solution, it\u2019s time to talk about the <strong>dedicated<\/strong> vector databases that scale beyond. In 2023 the three most-adopted options are <a href=\"https:\/\/qdrant.tech\/\">Qdrant<\/a>, <a href=\"https:\/\/www.pinecone.io\/\">Pinecone<\/a>, and <a href=\"https:\/\/weaviate.io\/\">Weaviate<\/a>. Each has different strengths and the right choice depends on the case.<\/p>\n<h2 id=\"qdrant\">Qdrant<\/h2>\n<p><a href=\"https:\/\/qdrant.tech\/\">Qdrant<\/a> is probably the most popular open-source option for serious production in 2023.<\/p>\n<p><strong>Architecture<\/strong>:<\/p>\n<ul>\n<li>Written in <strong>Rust<\/strong> \u2014 predictable performance and memory consumption.<\/li>\n<li>HNSW index by default, with optional quantization (scalar, product, binary).<\/li>\n<li>Supports rich payloads (metadata) with filtering integrated efficiently into search.<\/li>\n<li>Client-server mode or distributed cluster with sharding and replication.<\/li>\n<\/ul>\n<p><strong>Strengths<\/strong>:<\/p>\n<ul>\n<li><strong>Filters alongside vector search<\/strong> very well solved \u2014 applies the filter during the HNSW algorithm, not after.<\/li>\n<li><strong>Self-hosted free<\/strong> or paid managed (Qdrant Cloud).<\/li>\n<li><strong>Exceptional performance<\/strong> in public QPS and latency benchmarks.<\/li>\n<li><strong>Clear API<\/strong>, SDKs in Python, JavaScript, Go, Rust.<\/li>\n<\/ul>\n<p><strong>Limitations<\/strong>:<\/p>\n<ul>\n<li>Distributed operation (cluster) requires expertise \u2014 non-trivial.<\/li>\n<li>Smaller community than Pinecone in tutorials and blogs.<\/li>\n<\/ul>\n<p>It\u2019s the option I\u2019d recommend by default for 2024 if you want open source with a future and you\u2019re not afraid of operating your own service.<\/p>\n<h2 id=\"pinecone\">Pinecone<\/h2>\n<p><a href=\"https:\/\/www.pinecone.io\/\">Pinecone<\/a> is the <strong>managed-only<\/strong> option: you can\u2019t run it yourself; you consume its cloud service.<\/p>\n<p><strong>Architecture<\/strong>:<\/p>\n<ul>\n<li>100% SaaS \u2014 no access to the binary or self-host option.<\/li>\n<li>Proprietary indexing algorithm (not pure HNSW). Auto-tuned by the service.<\/li>\n<li>Replication, scaling, and operations managed by Pinecone.<\/li>\n<\/ul>\n<p><strong>Strengths<\/strong>:<\/p>\n<ul>\n<li><strong>Zero operations<\/strong>. Create an index and use it. Ideal for teams without dedicated infra.<\/li>\n<li><strong>Transparent automatic scaling<\/strong>.<\/li>\n<li><strong>Very stable and well-documented API<\/strong>, mature tutorial ecosystem.<\/li>\n<li><strong>Wide adoption<\/strong> \u2014 easy to hire people who know it.<\/li>\n<\/ul>\n<p><strong>Limitations<\/strong>:<\/p>\n<ul>\n<li><strong>Cost<\/strong>: for high volume, price scales fast. A moderately sized pod runs hundreds of dollars per month.<\/li>\n<li><strong>Lock-in<\/strong>: your pipeline depends on the service. Migration implies re-vectorising and re-loading everything elsewhere.<\/li>\n<li><strong>No self-host<\/strong>: for sensitive or regulated data may be a show-stopper.<\/li>\n<li><strong>Filtering functionality<\/strong> less rich than Qdrant or Weaviate (but enough for typical cases).<\/li>\n<\/ul>\n<p>Pinecone is the right choice when \u201cI don\u2019t want to think about operating a vector DB\u201d weighs more than cost.<\/p>\n<h2 id=\"weaviate\">Weaviate<\/h2>\n<p><a href=\"https:\/\/weaviate.io\/\">Weaviate<\/a> is the most <strong>feature-rich<\/strong> of the three.<\/p>\n<p><strong>Architecture<\/strong>:<\/p>\n<ul>\n<li>Open source, written in Go.<\/li>\n<li>Self-hosted or managed (Weaviate Cloud).<\/li>\n<li>Schema-based: define classes with typed properties, similar to a document DB.<\/li>\n<li>Optional embedded embedding generation (vectorise text on insert using pluggable modules: OpenAI, HuggingFace, Cohere).<\/li>\n<li>Native hybrid search (vector + BM25 keyword).<\/li>\n<\/ul>\n<p><strong>Strengths<\/strong>:<\/p>\n<ul>\n<li><strong>Native hybrid search<\/strong> very well implemented \u2014 combines vector and keyword in a single query.<\/li>\n<li><strong>Solid multi-tenancy<\/strong> for multi-client SaaS.<\/li>\n<li><strong>Generative search<\/strong>: integrates LLMs directly to return generated answers, not just documents.<\/li>\n<li><strong>GraphQL as API<\/strong> \u2014 interesting if your team already consumes GraphQL.<\/li>\n<\/ul>\n<p><strong>Limitations<\/strong>:<\/p>\n<ul>\n<li>More concepts to learn (schema, modules, references). Steeper curve.<\/li>\n<li>Pure HNSW performance sometimes slightly below Qdrant (depends on benchmark).<\/li>\n<li>Operating at scale requires attention (cluster, backups, recovery).<\/li>\n<\/ul>\n<p>Weaviate is the right choice when you need real hybrid search or serious multi-tenancy.<\/p>\n<h2 id=\"practical-comparison\">Practical Comparison<\/h2>\n<table>\n<thead>\n<tr class=\"header\">\n<th>Aspect<\/th>\n<th>Qdrant<\/th>\n<th>Pinecone<\/th>\n<th>Weaviate<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr class=\"odd\">\n<td>Self-host<\/td>\n<td>Yes<\/td>\n<td>No<\/td>\n<td>Yes<\/td>\n<\/tr>\n<tr class=\"even\">\n<td>Managed<\/td>\n<td>Yes<\/td>\n<td>Yes (only option)<\/td>\n<td>Yes<\/td>\n<\/tr>\n<tr class=\"odd\">\n<td>Language<\/td>\n<td>Rust<\/td>\n<td>Proprietary<\/td>\n<td>Go<\/td>\n<\/tr>\n<tr class=\"even\">\n<td>Vector filters<\/td>\n<td>Excellent<\/td>\n<td>Good<\/td>\n<td>Excellent<\/td>\n<\/tr>\n<tr class=\"odd\">\n<td>Hybrid search<\/td>\n<td>Limited<\/td>\n<td>Limited<\/td>\n<td>Native<\/td>\n<\/tr>\n<tr class=\"even\">\n<td>Multi-tenant<\/td>\n<td>Yes<\/td>\n<td>Yes<\/td>\n<td>Excellent<\/td>\n<\/tr>\n<tr class=\"odd\">\n<td>Cost at scale<\/td>\n<td>Low (self)<\/td>\n<td>High<\/td>\n<td>Low (self)<\/td>\n<\/tr>\n<tr class=\"even\">\n<td>Learning curve<\/td>\n<td>Smooth<\/td>\n<td>Minimal<\/td>\n<td>Medium<\/td>\n<\/tr>\n<tr class=\"odd\">\n<td>Community<\/td>\n<td>Growing<\/td>\n<td>Large<\/td>\n<td>Solid<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2 id=\"how-to-choose\">How to Choose<\/h2>\n<p>A reasonable decision tree for 2024:<\/p>\n<ul>\n<li><strong>Don\u2019t want to operate anything, budget OK<\/strong>: Pinecone.<\/li>\n<li><strong>Want open source with good performance, reasonable ops<\/strong>: Qdrant.<\/li>\n<li><strong>Need hybrid search or complex multi-tenant<\/strong>: Weaviate.<\/li>\n<li><strong>Just exploring and don\u2019t know final size<\/strong>: Chroma \u2192 migrate later.<\/li>\n<li><strong>Already have Postgres and corpus is &lt;10M<\/strong>: pgvector \u2192 maybe never migrate.<\/li>\n<\/ul>\n<p>Good news: APIs are similar enough that migrating between them is feasible if your RAG logic is well encapsulated. Structure code with an abstract retriever from day one and reduce switching cost.<\/p>\n<h2 id=\"what-matters-more-than-the-choice\">What Matters More Than the Choice<\/h2>\n<p>After several projects, I observe the vector DB choice <strong>matters less<\/strong> than it seems for final RAG quality. What impacts most:<\/p>\n<ul>\n<li><strong>Corpus quality<\/strong>. Dirty documents produce bad retrieval regardless of DB.<\/li>\n<li><strong>Chunking strategy<\/strong>. Bad chunking sinks any DB.<\/li>\n<li><strong>Embedding model<\/strong>. Notable differences among OpenAI ada-002, BGE, and similar.<\/li>\n<li><strong>Post-retrieval re-ranking<\/strong> with a cross-encoder model. Often improves more than changing DB.<\/li>\n<li><strong>Prompt design<\/strong> that receives the retrieved context.<\/li>\n<\/ul>\n<p>Optimise those five points before obsessing over Qdrant vs Pinecone.<\/p>\n<h2 id=\"conclusion\">Conclusion<\/h2>\n<p>Dedicated vector DBs are an important piece of the modern LLM stack. Each of the three main ones has cases where it shines. The right choice depends more on operational priorities (self-host vs managed, cost vs simplicity) than deep technical differences. Start with the option that best fits your team and migrate only if you find a concrete bottleneck.<\/p>\n<p>Follow us on jacar.es for more on RAG architecture, vector databases, and LLM product building.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Vector databases have gone from experimental to backbone of LLM products. A pragmatic comparison of the three most-used options in 2023.<\/p>\n","protected":false},"author":1,"featured_media":474,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[27,22],"tags":[227,258,257,96,228,259],"class_list":["post-473","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-arquitectura","category-inteligencia-artificial","tag-embeddings","tag-pinecone","tag-qdrant","tag-rag","tag-vector-database","tag-weaviate"],"translation":{"provider":"WPGlobus","version":"3.0.2","language":"en","enabled_languages":["es","en"],"languages":{"es":{"title":true,"content":true,"excerpt":true},"en":{"title":true,"content":true,"excerpt":true}}},"gutentor_comment":0,"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Vector Databases: Qdrant, Pinecone, and Weaviate - Jacar<\/title>\n<meta name=\"description\" content=\"Comparison among Qdrant, Pinecone, and Weaviate: architecture, use cases, cost, performance, and criteria to choose between them.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/jacar.es\/bases-datos-vectoriales\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Vector Databases: Qdrant, Pinecone, and Weaviate - Jacar\" \/>\n<meta property=\"og:description\" content=\"Comparison among Qdrant, Pinecone, and Weaviate: architecture, use cases, cost, performance, and criteria to choose between them.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/jacar.es\/bases-datos-vectoriales\/\" \/>\n<meta property=\"og:site_name\" content=\"Jacar\" \/>\n<meta property=\"article:published_time\" content=\"2023-11-13T10:00:00+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2020\/09\/favicon.png\" \/>\n\t<meta property=\"og:image:width\" content=\"252\" \/>\n\t<meta property=\"og:image:height\" content=\"229\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"javi\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"javi\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"8 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/\"},\"author\":{\"name\":\"javi\",\"@id\":\"https:\\\/\\\/jacar.es\\\/#\\\/schema\\\/person\\\/54a7f7b4224b38fafc9866eb3e614208\"},\"headline\":\"Vector Databases: Qdrant, Pinecone, and Weaviate\",\"datePublished\":\"2023-11-13T10:00:00+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/\"},\"wordCount\":1674,\"publisher\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\\\/wp-content\\\/uploads\\\/2023\\\/11\\\/19233155\\\/jwp-1280618-2506.jpg\",\"keywords\":[\"embeddings\",\"pinecone\",\"qdrant\",\"rag\",\"vector database\",\"weaviate\"],\"articleSection\":[\"Arquitectura\",\"Inteligencia Artificial\"],\"inLanguage\":\"en-US\"},{\"@type\":[\"WebPage\",\"ItemPage\"],\"@id\":\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/\",\"url\":\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/\",\"name\":\"Vector Databases: Qdrant, Pinecone, and Weaviate - Jacar\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\\\/wp-content\\\/uploads\\\/2023\\\/11\\\/19233155\\\/jwp-1280618-2506.jpg\",\"datePublished\":\"2023-11-13T10:00:00+00:00\",\"description\":\"Comparison among Qdrant, Pinecone, and Weaviate: architecture, use cases, cost, performance, and criteria to choose between them.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/#primaryimage\",\"url\":\"https:\\\/\\\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\\\/wp-content\\\/uploads\\\/2023\\\/11\\\/19233155\\\/jwp-1280618-2506.jpg\",\"contentUrl\":\"https:\\\/\\\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\\\/wp-content\\\/uploads\\\/2023\\\/11\\\/19233155\\\/jwp-1280618-2506.jpg\",\"width\":1200,\"height\":800,\"caption\":\"Pantalla con visualizaci\u00f3n abstracta de datos en clusters\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/jacar.es\\\/bases-datos-vectoriales\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Portada\",\"item\":\"https:\\\/\\\/jacar.es\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Bases de datos vectoriales: Qdrant, Pinecone y Weaviate\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/jacar.es\\\/#website\",\"url\":\"https:\\\/\\\/jacar.es\\\/\",\"name\":\"Jacar\",\"description\":\"Passion for Technology\",\"publisher\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/jacar.es\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/jacar.es\\\/#organization\",\"name\":\"Jacar\",\"url\":\"https:\\\/\\\/jacar.es\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/jacar.es\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/jacar.es\\\/wp-content\\\/uploads\\\/2020\\\/09\\\/favicon.png\",\"contentUrl\":\"https:\\\/\\\/jacar.es\\\/wp-content\\\/uploads\\\/2020\\\/09\\\/favicon.png\",\"width\":252,\"height\":229,\"caption\":\"Jacar\"},\"image\":{\"@id\":\"https:\\\/\\\/jacar.es\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/javiercanetearroyo\\\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/jacar.es\\\/#\\\/schema\\\/person\\\/54a7f7b4224b38fafc9866eb3e614208\",\"name\":\"javi\",\"sameAs\":[\"https:\\\/\\\/jacar.es\"],\"url\":\"https:\\\/\\\/jacar.es\\\/en\\\/author\\\/javi\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Vector Databases: Qdrant, Pinecone, and Weaviate - Jacar","description":"Comparison among Qdrant, Pinecone, and Weaviate: architecture, use cases, cost, performance, and criteria to choose between them.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/jacar.es\/bases-datos-vectoriales\/","og_locale":"en_US","og_type":"article","og_title":"Vector Databases: Qdrant, Pinecone, and Weaviate - Jacar","og_description":"Comparison among Qdrant, Pinecone, and Weaviate: architecture, use cases, cost, performance, and criteria to choose between them.","og_url":"https:\/\/jacar.es\/bases-datos-vectoriales\/","og_site_name":"Jacar","article_published_time":"2023-11-13T10:00:00+00:00","og_image":[{"width":252,"height":229,"url":"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2020\/09\/favicon.png","type":"image\/png"}],"author":"javi","twitter_card":"summary_large_image","twitter_misc":{"Written by":"javi","Est. reading time":"8 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/jacar.es\/bases-datos-vectoriales\/#article","isPartOf":{"@id":"https:\/\/jacar.es\/bases-datos-vectoriales\/"},"author":{"name":"javi","@id":"https:\/\/jacar.es\/#\/schema\/person\/54a7f7b4224b38fafc9866eb3e614208"},"headline":"Vector Databases: Qdrant, Pinecone, and Weaviate","datePublished":"2023-11-13T10:00:00+00:00","mainEntityOfPage":{"@id":"https:\/\/jacar.es\/bases-datos-vectoriales\/"},"wordCount":1674,"publisher":{"@id":"https:\/\/jacar.es\/#organization"},"image":{"@id":"https:\/\/jacar.es\/bases-datos-vectoriales\/#primaryimage"},"thumbnailUrl":"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2023\/11\/19233155\/jwp-1280618-2506.jpg","keywords":["embeddings","pinecone","qdrant","rag","vector database","weaviate"],"articleSection":["Arquitectura","Inteligencia Artificial"],"inLanguage":"en-US"},{"@type":["WebPage","ItemPage"],"@id":"https:\/\/jacar.es\/bases-datos-vectoriales\/","url":"https:\/\/jacar.es\/bases-datos-vectoriales\/","name":"Vector Databases: Qdrant, Pinecone, and Weaviate - Jacar","isPartOf":{"@id":"https:\/\/jacar.es\/#website"},"primaryImageOfPage":{"@id":"https:\/\/jacar.es\/bases-datos-vectoriales\/#primaryimage"},"image":{"@id":"https:\/\/jacar.es\/bases-datos-vectoriales\/#primaryimage"},"thumbnailUrl":"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2023\/11\/19233155\/jwp-1280618-2506.jpg","datePublished":"2023-11-13T10:00:00+00:00","description":"Comparison among Qdrant, Pinecone, and Weaviate: architecture, use cases, cost, performance, and criteria to choose between them.","breadcrumb":{"@id":"https:\/\/jacar.es\/bases-datos-vectoriales\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/jacar.es\/bases-datos-vectoriales\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/jacar.es\/bases-datos-vectoriales\/#primaryimage","url":"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2023\/11\/19233155\/jwp-1280618-2506.jpg","contentUrl":"https:\/\/jcs-wp-jacar-es.fsn1.your-objectstorage.com\/wp-content\/uploads\/2023\/11\/19233155\/jwp-1280618-2506.jpg","width":1200,"height":800,"caption":"Pantalla con visualizaci\u00f3n abstracta de datos en clusters"},{"@type":"BreadcrumbList","@id":"https:\/\/jacar.es\/bases-datos-vectoriales\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Portada","item":"https:\/\/jacar.es\/"},{"@type":"ListItem","position":2,"name":"Bases de datos vectoriales: Qdrant, Pinecone y Weaviate"}]},{"@type":"WebSite","@id":"https:\/\/jacar.es\/#website","url":"https:\/\/jacar.es\/","name":"Jacar","description":"Passion for Technology","publisher":{"@id":"https:\/\/jacar.es\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/jacar.es\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/jacar.es\/#organization","name":"Jacar","url":"https:\/\/jacar.es\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/jacar.es\/#\/schema\/logo\/image\/","url":"https:\/\/jacar.es\/wp-content\/uploads\/2020\/09\/favicon.png","contentUrl":"https:\/\/jacar.es\/wp-content\/uploads\/2020\/09\/favicon.png","width":252,"height":229,"caption":"Jacar"},"image":{"@id":"https:\/\/jacar.es\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.linkedin.com\/in\/javiercanetearroyo\/"]},{"@type":"Person","@id":"https:\/\/jacar.es\/#\/schema\/person\/54a7f7b4224b38fafc9866eb3e614208","name":"javi","sameAs":["https:\/\/jacar.es"],"url":"https:\/\/jacar.es\/en\/author\/javi\/"}]}},"_links":{"self":[{"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/posts\/473","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/comments?post=473"}],"version-history":[{"count":0,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/posts\/473\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/media\/474"}],"wp:attachment":[{"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/media?parent=473"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/categories?post=473"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jacar.es\/en\/wp-json\/wp\/v2\/tags?post=473"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}