{"id":17907,"date":"2026-10-02T10:59:08","date_gmt":"2026-10-02T17:59:08","guid":{"rendered":"https:\/\/www.pingcap.com\/?post_type=article&#038;p=17907"},"modified":"2026-10-02T12:33:11","modified_gmt":"2026-10-02T19:33:11","slug":"ai-powered-search-with-tidb-vector-search","status":"publish","type":"article","link":"https:\/\/www.pingcap.com\/ko\/article\/ai-powered-search-with-tidb-vector-search\/","title":{"rendered":"AI-Powered Search with TiDB Vector Search"},"content":{"rendered":"<p class=\"wp-block-paragraph\">Keyword search only matches exact words, so it misses the query that means the same thing but says it differently. Most teams fix this by bolting on a dedicated vector database next to the one they already run, which means two systems to keep in sync, two consistency models, and a pipeline that can silently drift out of date. <a href=\"https:\/\/www.pingcap.com\/ko\/what-is-tidb\/\">\ud2f0DB<\/a> Vector Search removes that second system. It stores embeddings as a native SQL data type inside the same distributed, HTAP database that already holds your transactional and analytical data.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"What_Is_TiDB_Vector_Search\"><\/span><strong>What Is TiDB Vector Search?<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">TiDB Vector Search lets you query by the meaning of your data instead of by exact keyword match. It stores vector embeddings, numeric representations of text, images, audio, or video, in a native VECTOR column, then finds the nearest matches by measuring the distance between vectors. Because it lives inside TiDB, the same distributed SQL database used for transactional and analytical workloads, there is no separate vector store to provision or keep synchronized.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">TiDB Vector Search supports two related patterns:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Semantic search:<\/strong> find records whose meaning is close to a query, even when the wording differs.<\/li>\n\n\n\n<li><strong>Similarity search:<\/strong> find items that resemble a given item, useful for recommendations and content discovery.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">A TiDB vector column stores up to 16,383 dimensions, which covers the embedding sizes produced by most current models.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"How_TiDB_Vector_Search_Works\"><\/span><strong>How TiDB Vector Search Works<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Building a semantic search feature on TiDB follows three steps:<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>Embedding generation.<\/strong> Convert your source data (text, images, or other content) into vectors using an embedding model.<\/li>\n\n\n\n<li><strong>Vector storage.<\/strong> Store the resulting vectors in a TiDB table alongside your existing structured data.<\/li>\n\n\n\n<li><strong>Similarity search.<\/strong> Query with a distance function such as vec_cosine_distance to find the nearest vectors to a given query embedding, using an HNSW (Hierarchical Navigable Small World) index for fast approximate nearest-neighbor lookups at scale.<\/li>\n<\/ol>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"How_TiDB_Solves_the_Data-Silo_Problem\"><\/span><strong>How TiDB Solves the Data-Silo Problem<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">A dedicated vector database can answer &#8220;which items are similar,&#8221; but it cannot join that answer against your live transactional data without crossing a system boundary, which means an extra network hop, an extra consistency question, and an extra service to operate. TiDB closes that gap with its HTAP architecture: TiKV handles row-based transactional storage, TiFlash handles columnar analytical storage, and vector columns live in the same tables as everything else. A single SQL query can filter on a WHERE clause, join across tables, and rank by vector distance, all inside one ACID transaction boundary. See the <a href=\"https:\/\/www.pingcap.com\/ko\/blog\/htap-demystified-defining-modern-data-architecture-tidb\/\">HTAP architecture diagram<\/a> for how TiKV and TiFlash divide the work.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">AI-native companies already run this pattern in production. <a href=\"https:\/\/www.pingcap.com\/ko\/case-study\/kimi-2-6-agent-hosting-platform-tidb-cloud\/\">Kimi<\/a>, the agent platform built by Moonshot AI, runs its persistent agent infrastructure on TiDB Cloud specifically because a single unified data stack means agents never have to reason across separate database boundaries. The same principle applies to vector search: storing embeddings next to the transactional records they describe means an application can filter, join, and rank in one query instead of stitching results together from two systems after the fact.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Setting_Up_TiDB_Vector_Search\"><\/span><strong>Setting Up TiDB Vector Search<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Vector search is available on TiDB Cloud Starter, TiDB Cloud Essential, TiDB Cloud Dedicated, and TiDB Self-Managed (self-managed deployments need TiDB v8.4.0 or later; v8.5.0 or later is recommended). To get started:<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>Sign up:<\/strong> <a href=\"https:\/\/tidbcloud.com\/free-trial\/\">Create a TiDB Cloud<\/a> account.<\/li>\n\n\n\n<li><strong>Create a cluster:<\/strong> Follow the <a href=\"https:\/\/docs.pingcap.com\/tidbcloud\/tidb-cloud-quickstart\">quickstart guide<\/a> to set up a TiDB Cloud Starter cluster. Vector search is available by default, with no separate enablement step or region restriction.<\/li>\n\n\n\n<li><strong>Connect:<\/strong> From the Clusters page, select your cluster, click Connect, and choose General to get your connection parameters.<\/li>\n<\/ol>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Example_Semantic_Search_with_TiDB\"><\/span><strong>Example: Semantic Search with TiDB<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Here is a working example using OpenAI embeddings and the peewee ORM.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Prerequisites<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Python 3.8 or later<\/li>\n\n\n\n<li>A TiDB Cloud Starter cluster with vector search enabled<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Setting up the environment<\/strong><\/h3>\n\n\n\n<pre class=\"wp-block-code\"><code># Create virtual environment<br>python3 -m venv .venv<br>source .venv\/bin\/activate<br><br># Install dependencies<br>pip install openai peewee pymysql tidb_vector<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Example code<\/strong><\/h3>\n\n\n\n<pre class=\"wp-block-code\"><code>import os<br>from openai import OpenAI<br>from peewee import Model, MySQLDatabase, TextField<br>from tidb_vector.peewee import VectorField<br><br># Initialize OpenAI client<br>client = OpenAI(api_key=os.environ.get('OPENAI_API_KEY'))<br>embedding_model = \"text-embedding-3-small\"<br>embedding_dimensions = 1536<br><br># Connect to TiDB<br>db = MySQLDatabase(<br>&nbsp; &nbsp; 'test',<br>&nbsp; &nbsp; user=os.environ.get('TIDB_USERNAME'),<br>&nbsp; &nbsp; password=os.environ.get('TIDB_PASSWORD'),<br>&nbsp; &nbsp; host=os.environ.get('TIDB_HOST'),<br>&nbsp; &nbsp; port=4000,<br>&nbsp; &nbsp; ssl_verify_cert=True,<br>&nbsp; &nbsp; ssl_verify_identity=True<br>)<br><br># Sample documents<br>documents = &#91;<br>&nbsp; &nbsp; \"TiDB is an open-source distributed SQL database that supports Hybrid Transactional and Analytical Processing (HTAP) workloads.\",<br>&nbsp; &nbsp; \"TiFlash is the columnar storage engine that makes TiDB an HTAP database.\",<br>&nbsp; &nbsp; \"TiKV is a distributed, transactional key-value store with ACID compliance.\"<br>]<br><br># Define model<br>class DocModel(Model):<br>&nbsp; &nbsp; text = TextField()<br>&nbsp; &nbsp; embedding = VectorField(dimensions=embedding_dimensions)<br><br>&nbsp; &nbsp; class Meta:<br>&nbsp; &nbsp; &nbsp; &nbsp; database = db<br>&nbsp; &nbsp; &nbsp; &nbsp; table_name = \"doc_test\"<br><br># Set up the table<br>db.connect()<br>db.create_tables(&#91;DocModel])<br><br># Generate embeddings and insert<br>embeddings = &#91;r.embedding for r in client.embeddings.create(input=documents, model=embedding_model).data]<br>data_source = &#91;{\"text\": doc, \"embedding\": emb} for doc, emb in zip(documents, embeddings)]<br>DocModel.insert_many(data_source).execute()<br><br># Query example<br>question = \"What is TiKV?\"<br>question_embedding = client.embeddings.create(input=question, model=embedding_model).data&#91;0].embedding<br>related_docs = (<br>&nbsp; &nbsp; DocModel<br>&nbsp; &nbsp; .select(DocModel.text, DocModel.embedding.cosine_distance(question_embedding).alias(\"distance\"))<br>&nbsp; &nbsp; .order_by(SQL(\"distance\"))<br>&nbsp; &nbsp; .limit(3)<br>)<br><br>for doc in related_docs:<br>&nbsp; &nbsp; print(doc.distance, doc.text)<br><br>db.close()<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">If you would rather not call an embedding API by hand, TiDB also supports native auto-embedding and direct integrations with <a href=\"https:\/\/docs.pingcap.com\/tidb\/dev\/vector-search-integration-overview\">LangChain and LlamaIndex<\/a>, so you can insert plain text and let TiDB generate the embeddings for you.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"FAQ\"><\/span><strong>\uc790\uc8fc \ubb3b\ub294 \uc9c8\ubb38<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>What data types can TiDB Vector Search handle?<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Text, images, audio, video, and any other data type that can be converted into an embedding<\/li>\n\n\n\n<li>Vectors up to 16,383 dimensions per column<\/li>\n\n\n\n<li>Standard SQL data types alongside vector columns in the same table<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Does TiDB Vector Search replace a dedicated vector database?<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>For most applications, yes: TiDB stores vectors, transactional data, and analytical data in one system<\/li>\n\n\n\n<li>No separate service, sync pipeline, or second consistency model to maintain<\/li>\n\n\n\n<li>Vector similarity, filtering, and joins run in a single SQL query<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>What embedding models does TiDB support?<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Any model that outputs a fixed-length vector, including OpenAI, Cohere, and Jina AI<\/li>\n\n\n\n<li>Native auto-embedding for common providers, so you can skip manual API calls<\/li>\n\n\n\n<li>Framework integrations with LangChain and LlamaIndex<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>How many dimensions can a TiDB vector store?<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Up to 16,383 dimensions per vector column<\/li>\n\n\n\n<li>Covers the output size of most current embedding models<\/li>\n\n\n\n<li>HNSW indexing keeps nearest-neighbor queries fast at that dimensionality<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Build_Semantic_Search_Without_a_Second_Database\"><\/span><strong>Build Semantic Search Without a Second Database<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">TiDB Vector Search gives you semantic and similarity search inside the same distributed SQL database that already runs your transactional and analytical workloads, so you query embeddings and structured data together instead of stitching results across systems. <a href=\"https:\/\/tidbcloud.com\/free-trial\/\">Sign up for TiDB Cloud Starter<\/a> and try vector search with your own data today.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>","protected":false},"excerpt":{"rendered":"<p>Keyword search only matches exact words, so it misses the query that means the same thing but says it differently. Most teams fix this by bolting on a dedicated vector database next to the one they already run, which means two systems to keep in sync, two consistency models, and a pipeline that can silently [&hellip;]<\/p>\n","protected":false},"author":305,"featured_media":0,"template":"","class_list":["post-17907","article","type-article","status-publish","hentry"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.2 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>AI-Powered Search with TiDB Vector Search TiDB Vector Search: AI-Powered Semantic Search Guide<\/title>\n<meta name=\"description\" content=\"TiDB adds AI-powered semantic search with native vector search. Store embeddings, query by similarity in plain SQL, no separate database.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.pingcap.com\/ko\/article\/ai-powered-search-with-tidb-vector-search\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI-Powered Search with TiDB Vector Search TiDB Vector Search: AI-Powered Semantic Search Guide\" \/>\n<meta property=\"og:description\" content=\"TiDB adds AI-powered semantic search with native vector search. Store embeddings, query by similarity in plain SQL, no separate database.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.pingcap.com\/ko\/article\/ai-powered-search-with-tidb-vector-search\/\" \/>\n<meta property=\"og:site_name\" content=\"TiDB\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/facebook.com\/pingcap2015\" \/>\n<meta property=\"article:modified_time\" content=\"2026-10-02T19:33:11+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/static.pingcap.com\/files\/2024\/09\/11005522\/Homepage-Ad.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1440\" \/>\n\t<meta property=\"og:image:height\" content=\"714\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@PingCAP\" \/>\n<meta name=\"twitter:label1\" content=\"\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04\" \/>\n\t<meta name=\"twitter:data1\" content=\"6\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.pingcap.com\\\/article\\\/ai-powered-search-with-tidb-vector-search\\\/\",\"url\":\"https:\\\/\\\/www.pingcap.com\\\/article\\\/ai-powered-search-with-tidb-vector-search\\\/\",\"name\":\"AI-Powered Search with TiDB Vector Search TiDB Vector Search: AI-Powered Semantic Search Guide\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.pingcap.com\\\/#website\"},\"datePublished\":\"2026-10-02T17:59:08+00:00\",\"dateModified\":\"2026-10-02T19:33:11+00:00\",\"description\":\"TiDB adds AI-powered semantic search with native vector search. Store embeddings, query by similarity in plain SQL, no separate database.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.pingcap.com\\\/article\\\/ai-powered-search-with-tidb-vector-search\\\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.pingcap.com\\\/article\\\/ai-powered-search-with-tidb-vector-search\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.pingcap.com\\\/article\\\/ai-powered-search-with-tidb-vector-search\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.pingcap.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Articles\",\"item\":\"https:\\\/\\\/www.pingcap.com\\\/article\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"AI-Powered Search with TiDB Vector Search\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.pingcap.com\\\/#website\",\"url\":\"https:\\\/\\\/www.pingcap.com\\\/\",\"name\":\"TiDB\",\"description\":\"TiDB | SQL at Scale\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.pingcap.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.pingcap.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/www.pingcap.com\\\/#organization\",\"name\":\"PingCAP\",\"url\":\"https:\\\/\\\/www.pingcap.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\\\/\\\/www.pingcap.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/static.pingcap.com\\\/files\\\/2021\\\/11\\\/pingcap-logo.png\",\"contentUrl\":\"https:\\\/\\\/static.pingcap.com\\\/files\\\/2021\\\/11\\\/pingcap-logo.png\",\"width\":811,\"height\":232,\"caption\":\"PingCAP\"},\"image\":{\"@id\":\"https:\\\/\\\/www.pingcap.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/facebook.com\\\/pingcap2015\",\"https:\\\/\\\/x.com\\\/PingCAP\",\"https:\\\/\\\/linkedin.com\\\/company\\\/pingcap\",\"https:\\\/\\\/youtube.com\\\/channel\\\/UCuq4puT32DzHKT5rU1IZpIA\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AI-Powered Search with TiDB Vector Search TiDB Vector Search: AI-Powered Semantic Search Guide","description":"TiDB adds AI-powered semantic search with native vector search. Store embeddings, query by similarity in plain SQL, no separate database.","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:\/\/www.pingcap.com\/ko\/article\/ai-powered-search-with-tidb-vector-search\/","og_locale":"ko_KR","og_type":"article","og_title":"AI-Powered Search with TiDB Vector Search TiDB Vector Search: AI-Powered Semantic Search Guide","og_description":"TiDB adds AI-powered semantic search with native vector search. Store embeddings, query by similarity in plain SQL, no separate database.","og_url":"https:\/\/www.pingcap.com\/ko\/article\/ai-powered-search-with-tidb-vector-search\/","og_site_name":"TiDB","article_publisher":"https:\/\/facebook.com\/pingcap2015","article_modified_time":"2026-10-02T19:33:11+00:00","og_image":[{"width":1440,"height":714,"url":"https:\/\/static.pingcap.com\/files\/2024\/09\/11005522\/Homepage-Ad.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_site":"@PingCAP","twitter_misc":{"\uc608\uc0c1 \ub418\ub294 \ud310\ub3c5 \uc2dc\uac04":"6\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.pingcap.com\/article\/ai-powered-search-with-tidb-vector-search\/","url":"https:\/\/www.pingcap.com\/article\/ai-powered-search-with-tidb-vector-search\/","name":"AI-Powered Search with TiDB Vector Search TiDB Vector Search: AI-Powered Semantic Search Guide","isPartOf":{"@id":"https:\/\/www.pingcap.com\/#website"},"datePublished":"2026-10-02T17:59:08+00:00","dateModified":"2026-10-02T19:33:11+00:00","description":"TiDB adds AI-powered semantic search with native vector search. Store embeddings, query by similarity in plain SQL, no separate database.","breadcrumb":{"@id":"https:\/\/www.pingcap.com\/article\/ai-powered-search-with-tidb-vector-search\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.pingcap.com\/article\/ai-powered-search-with-tidb-vector-search\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.pingcap.com\/article\/ai-powered-search-with-tidb-vector-search\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.pingcap.com\/"},{"@type":"ListItem","position":2,"name":"Articles","item":"https:\/\/www.pingcap.com\/article\/"},{"@type":"ListItem","position":3,"name":"AI-Powered Search with TiDB Vector Search"}]},{"@type":"WebSite","@id":"https:\/\/www.pingcap.com\/#website","url":"https:\/\/www.pingcap.com\/","name":"\ud2f0DB","description":"TiDB | SQL at Scale","publisher":{"@id":"https:\/\/www.pingcap.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.pingcap.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/www.pingcap.com\/#organization","name":"PingCAP","url":"https:\/\/www.pingcap.com\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/www.pingcap.com\/#\/schema\/logo\/image\/","url":"https:\/\/static.pingcap.com\/files\/2021\/11\/pingcap-logo.png","contentUrl":"https:\/\/static.pingcap.com\/files\/2021\/11\/pingcap-logo.png","width":811,"height":232,"caption":"PingCAP"},"image":{"@id":"https:\/\/www.pingcap.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/facebook.com\/pingcap2015","https:\/\/x.com\/PingCAP","https:\/\/linkedin.com\/company\/pingcap","https:\/\/youtube.com\/channel\/UCuq4puT32DzHKT5rU1IZpIA"]}]}},"card_markup":"        <a class=\"card-article\" href=\"https:\/\/www.pingcap.com\/ko\/article\/ai-powered-search-with-tidb-vector-search\/\">            <h3>AI-Powered Search with TiDB Vector Search<\/h3>            <p>Keyword search only matches exact words, so it misses the query that means the same thing but says it differently. Most teams fix this by bolting on a dedicated vector database next to the one they already run, which means two systems to keep in sync, two consistency models, and a pipeline that can silently [&hellip;]<\/p>        <\/a>","_links":{"self":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/article\/17907","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/article"}],"about":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/types\/article"}],"author":[{"embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/users\/305"}],"wp:attachment":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/media?parent=17907"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}