{"id":530900,"date":"2026-03-17T12:42:21","date_gmt":"2026-03-17T12:42:21","guid":{"rendered":"https:\/\/webkul.com\/blog\/?p=530900"},"modified":"2026-03-17T12:42:33","modified_gmt":"2026-03-17T12:42:33","slug":"gemini-embedding-2","status":"publish","type":"post","link":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/","title":{"rendered":"Gemini Embedding 2: Google\u2019s Multimodal Embedding Model"},"content":{"rendered":"\n<p>On March 10, 2026, Google released Gemini Embedding 2 in preview. It is a big step forward in embedding technology.<\/p>\n\n\n\n<p>It is the first natively multimodal embedding model of Google, and it is made over the Gemini foundation model architecture.<\/p>\n\n\n\n<p>Gemini Embedding 2 can process text, images, video, audio, and documents in one shared space. Older models needed separate systems for each type of data.<\/p>\n\n\n\n<p>This enables true cross-modal retrieval\u2014where a text query can seamlessly surface relevant videos, audio clips, images.<\/p>\n\n\n\n<p>This lets a text search find videos, audio clips, images, or parts of documents.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Why Natively Multimodal Matters<\/h2>\n\n\n\n<p>Most older multimodal models use separate encoders for each type of data. They connect them later during training so they can work together.<\/p>\n\n\n\n<p>This lacks rich deep interactions that take place in middle layers within a common transformer.<\/p>\n\n\n\n<p>Gemini Embedding 2 is the multimodal understanding of Gemini.<\/p>\n\n\n\n<p>Each of the modalities is routed through the same architecture, and each of them captures subtle semantic relationship.<\/p>\n\n\n\n<p>The outcome: better, more consistent embeddings of all forms of media.<\/p>\n\n\n\n<p>It can also take mixed inputs in one API call, like text with an image or audio with video, and create the needed embeddings.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Major technical specifications of Gemini Embedding 2 :<\/h2>\n\n\n\n<figure class=\"wp-block-image size-full\"><img decoding=\"async\" width=\"800\" height=\"500\" src=\"https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp\" alt=\"Multi Modal Input\" class=\"wp-image-531179\" srcset=\"https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp 800w, https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput-300x188.webp 300w, https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput-250x156.webp 250w, https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput-768x480.webp 768w\" sizes=\"(max-width: 800px) 100vw, 800px\" loading=\"lazy\" \/><\/figure>\n\n\n\n<p><strong>Model ID<\/strong>: gemini-embedding-2-preview ( Gemini API and Vertex AI)<\/p>\n\n\n\n<p><strong>Input Modalities and Limits<\/strong> (Vertex AI is a description; Gemini API resembles)<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Text<\/strong>: 8,192 tokens (4 times larger than the previous models, which had a limit of about 2,048 tokens)<\/li>\n\n\n\n<li><strong>Images<\/strong>: 6 images per request (PNG, JPEG)<\/li>\n\n\n\n<li><strong>Video<\/strong>: Up to 120 seconds (without audio) or ~80\u2013128 seconds (with audio); formats like MP4, MOV.<\/li>\n\n\n\n<li><strong>Audio<\/strong>: 80 seconds maximum (MP3, WAV); natively processed, no transcription needed.<\/li>\n\n\n\n<li>Documents (PDF) Up to 6 pages in a file; supports OCR text + layout.<\/li>\n<\/ul>\n\n\n\n<p><strong>Output<\/strong>: 3072-dimensional vectors default.<\/p>\n\n\n\n<p><strong>Flexible Dimensions<\/strong>: 128\u20133072 through output dimensionality parameter (courtesy of <a href=\"https:\/\/huggingface.co\/blog\/matryoshka\">Matryoshka Representation Learning<\/a><strong> <\/strong>).<\/p>\n\n\n\n<p>Recommended sizes: 768, 1536, 3072. Reduced dimensions store\/compute with less loss of quality.<\/p>\n\n\n\n<p><strong>Task Type:<\/strong> You can use it for tasks reterival document, reterival query, <a href=\"https:\/\/store.webkul.com\/magento2-semantic-search.html\">semantic search<\/a> , classification, clustering, semantic similarity, question &amp; answering, etc<\/p>\n\n\n\n<p><strong>Languages<\/strong>: Good results in 100+ languages.<\/p>\n\n\n\n<p><strong>Knowledge Cutoff<\/strong>: Around November 2025 (for the underlying model).<\/p>\n\n\n\n<p><strong>Important<\/strong> : Embeddings of various models do not inhabit compatible vector spaces. The re-indexing of your data is required when migrating.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Major Improvements Over Prior Models <\/h2>\n\n\n\n<p><strong>Unified Space:<\/strong> It uses one model instead of many separate encoders for text or other data types.<\/p>\n\n\n\n<p><strong>Increased Context Lengths and Richer Inputs<\/strong>: 8,192 tokens and support of native video\/audio\/PDF.<\/p>\n\n\n\n<p><strong>Efficiency:<\/strong> It can reduce vector size, optimize for tasks, and process many items at once to lower cost.<\/p>\n\n\n\n<p><strong>Less complex Pipelines<\/strong> &#8211; No longer embedded calls individually + post process alignment. Mixed media in one request.<\/p>\n\n\n\n<p>For text-only tasks, gemini-embedding-001 can still be used. But Gemini Embedding 2 works better when images, audio, video, or other data are included.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Practical Use Cases of Gemini Embedding 2<\/h2>\n\n\n\n<p>Gemini Embedding 2 excels in:<\/p>\n\n\n\n<p><strong>Cross-Modal Search &amp; RAG:<\/strong> You can use text to find videos, audio, images, or document pages, or search the other way around.<\/p>\n\n\n\n<p><strong>Multimodal Recommendations: <\/strong>It can suggest videos, images, and product details together.<\/p>\n\n\n\n<p><strong>Document Intelligence:<\/strong> It can use full PDFs with text and images to search, sort, and answer questions<\/p>\n\n\n\n<p><strong>Content Moderation &amp; Classification:<\/strong> It can check posts, videos, or audio to find topics, feelings, or unusual content.<\/p>\n\n\n\n<p><strong>Multimedia Archives and Knowledge Bases:<\/strong> It helps store and search videos, podcasts, reports, and images in one place.<\/p>\n\n\n\n<p><strong>Two-stage Retrieval<\/strong>: First, it quickly finds possible matches with small vectors. Then it checks them again with larger vectors for better results.<\/p>\n\n\n\n<p>In real use, it makes systems simpler, faster, and cheaper to store. It can also add new data types without changing the system design.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">How to Get Started with Gemini Embedding 2<\/h2>\n\n\n\n<p>Via Gemini API (Python example \u2013 single image):<\/p>\n\n\n\n<pre class=\"EnlighterJSRAW\">from google import genai\n\ntypes. from google.genai import types.\n\nclient = genai.Client()\n\nwith open(&#039;example.png&#039;, &#039;rb&#039;) as f:\n\n    image_bytes = f.read()\n\nresult = client.models.embed_content(\n\n    model=&#039;gemini-embedding-2-preview&#039;,\n\n    contents=&#091;types.Part.from_bytes(data=image_bytes, mime_type=&#039;image\/png&#039;)]\n\n)\n\nprint(result.embeddings&#091;0].values)  # 3072-dim vector (or dimensionality)<\/pre>\n\n\n\n<p>You can send text, images, and audio together in one request to create one embedding.<\/p>\n\n\n\n<p>The same is true with video, audio, and PDF.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Migration Tips &amp; Best Practices <\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Re-index strategically<\/strong>&#8211; Indexing by the use of the Batch API is cost-effective.<\/li>\n\n\n\n<li><strong>Shadow testing and A\/B<\/strong> &#8211; Run old and new indexes in parallel and step by step redistribute traffic and re-trained similarity thresholds.<\/li>\n\n\n\n<li><strong>Dimension Strategy<\/strong> &#8211; start with full 3072 quality, MRL prefixes + normalization production storage\/speed.<\/li>\n\n\n\n<li><strong>Task types<\/strong> &#8211; always provide tasktype (e.g. RETRIEVAL_DOCUMENT to index), so it will be more relevant.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">The Future of Embeddings<\/h2>\n\n\n\n<p>Gemini Embedding 2 compresses multimodal stacks into a powerful single model.<\/p>\n\n\n\n<p>It makes development much easier, retrieval on any media is better, and more intensive.<\/p>\n\n\n\n<p><a href=\"https:\/\/webkul.com\/artificial-intelligence\/\">Artifical Intellignece <\/a>applications become available- intelligent multimedia searching and well-integrated knowledge management in enterprises.<\/p>\n\n\n\n<p>Models such as these are now the new standard as multimodal data becomes a flood: a single embedding space to govern them all.<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p><em>Want to Build AI-powered solutions visit&nbsp;<a href=\"https:\/\/webkul.com\/generative-ai-services-and-solutions\/\">Webkul<\/a>!<\/em><\/p>\n<\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>On March 10, 2026, Google released Gemini Embedding 2 in preview. It is a big step forward in embedding technology. It is the first natively multimodal embedding model of Google, and it is made over the Gemini foundation model architecture. Gemini Embedding 2 can process text, images, video, audio, and documents in one shared space. <a href=\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/\">[&#8230;]<\/a><\/p>\n","protected":false},"author":724,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[13702],"tags":[13571,7240],"class_list":["post-530900","post","type-post","status-publish","format-standard","hentry","category-machine-learning","tag-artificial-intelligence","tag-machine-learning"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v24.5 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Gemini Embedding 2: Google\u2019s Multimodal Embedding Model - Webkul Blog<\/title>\n<meta name=\"description\" content=\"Explore Gemini Embedding 2, Google\u2019s multimodal model for text, image, video, audio, and document embeddings in one shared space.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Gemini Embedding 2: Google\u2019s Multimodal Embedding Model - Webkul Blog\" \/>\n<meta property=\"og:description\" content=\"Explore Gemini Embedding 2, Google\u2019s multimodal model for text, image, video, audio, and document embeddings in one shared space.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/\" \/>\n<meta property=\"og:site_name\" content=\"Webkul Blog\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/webkul\/\" \/>\n<meta property=\"article:published_time\" content=\"2026-03-17T12:42:21+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-03-17T12:42:33+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp\" \/>\n<meta name=\"author\" content=\"Prashant Saini\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@webkul\" \/>\n<meta name=\"twitter:site\" content=\"@webkul\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Prashant Saini\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/\"},\"author\":{\"name\":\"Prashant Saini\",\"@id\":\"https:\/\/webkul.com\/blog\/#\/schema\/person\/53a57eff87fe1f3e9e69c165efdabdc4\"},\"headline\":\"Gemini Embedding 2: Google\u2019s Multimodal Embedding Model\",\"datePublished\":\"2026-03-17T12:42:21+00:00\",\"dateModified\":\"2026-03-17T12:42:33+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/\"},\"wordCount\":784,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/webkul.com\/blog\/#organization\"},\"image\":{\"@id\":\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp\",\"keywords\":[\"Artificial Intelligence\",\"machine learning\"],\"articleSection\":[\"machine learning\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/\",\"url\":\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/\",\"name\":\"Gemini Embedding 2: Google\u2019s Multimodal Embedding Model - Webkul Blog\",\"isPartOf\":{\"@id\":\"https:\/\/webkul.com\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp\",\"datePublished\":\"2026-03-17T12:42:21+00:00\",\"dateModified\":\"2026-03-17T12:42:33+00:00\",\"description\":\"Explore Gemini Embedding 2, Google\u2019s multimodal model for text, image, video, audio, and document embeddings in one shared space.\",\"breadcrumb\":{\"@id\":\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#primaryimage\",\"url\":\"https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp\",\"contentUrl\":\"https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp\",\"width\":800,\"height\":500},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/webkul.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Gemini Embedding 2: Google\u2019s Multimodal Embedding Model\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/webkul.com\/blog\/#website\",\"url\":\"https:\/\/webkul.com\/blog\/\",\"name\":\"Webkul Blog\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/webkul.com\/blog\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/webkul.com\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/webkul.com\/blog\/#organization\",\"name\":\"WebKul Software Private Limited\",\"url\":\"https:\/\/webkul.com\/blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/webkul.com\/blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2021\/08\/webkul-logo-accent-sq.png\",\"contentUrl\":\"https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2021\/08\/webkul-logo-accent-sq.png\",\"width\":380,\"height\":380,\"caption\":\"WebKul Software Private Limited\"},\"image\":{\"@id\":\"https:\/\/webkul.com\/blog\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/webkul\/\",\"https:\/\/x.com\/webkul\",\"https:\/\/www.instagram.com\/webkul\/\",\"https:\/\/www.linkedin.com\/company\/webkul\",\"https:\/\/www.youtube.com\/user\/webkul\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/webkul.com\/blog\/#\/schema\/person\/53a57eff87fe1f3e9e69c165efdabdc4\",\"name\":\"Prashant Saini\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/webkul.com\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/90bd6382a7aa9ee0d5835bfaab3a739f91c37833f8e0d7cad51cd6a52b4914f0?s=96&d=https%3A%2F%2Fcdnblog.webkul.com%2Fblog%2Fwp-content%2Fuploads%2F2019%2F10%2Fmike.png&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/90bd6382a7aa9ee0d5835bfaab3a739f91c37833f8e0d7cad51cd6a52b4914f0?s=96&d=https%3A%2F%2Fcdnblog.webkul.com%2Fblog%2Fwp-content%2Fuploads%2F2019%2F10%2Fmike.png&r=g\",\"caption\":\"Prashant Saini\"},\"description\":\"Prashant, a passionate Machine Learning and AI enthusiast, specialized in building intelligent solutions using Python and Generative AI technologies.\",\"url\":\"https:\/\/webkul.com\/blog\/author\/prashant-ml322\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Gemini Embedding 2: Google\u2019s Multimodal Embedding Model - Webkul Blog","description":"Explore Gemini Embedding 2, Google\u2019s multimodal model for text, image, video, audio, and document embeddings in one shared space.","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:\/\/webkul.com\/blog\/gemini-embedding-2\/","og_locale":"en_US","og_type":"article","og_title":"Gemini Embedding 2: Google\u2019s Multimodal Embedding Model - Webkul Blog","og_description":"Explore Gemini Embedding 2, Google\u2019s multimodal model for text, image, video, audio, and document embeddings in one shared space.","og_url":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/","og_site_name":"Webkul Blog","article_publisher":"https:\/\/www.facebook.com\/webkul\/","article_published_time":"2026-03-17T12:42:21+00:00","article_modified_time":"2026-03-17T12:42:33+00:00","og_image":[{"url":"https:\/\/webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp","type":"","width":"","height":""}],"author":"Prashant Saini","twitter_card":"summary_large_image","twitter_creator":"@webkul","twitter_site":"@webkul","twitter_misc":{"Written by":"Prashant Saini","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#article","isPartOf":{"@id":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/"},"author":{"name":"Prashant Saini","@id":"https:\/\/webkul.com\/blog\/#\/schema\/person\/53a57eff87fe1f3e9e69c165efdabdc4"},"headline":"Gemini Embedding 2: Google\u2019s Multimodal Embedding Model","datePublished":"2026-03-17T12:42:21+00:00","dateModified":"2026-03-17T12:42:33+00:00","mainEntityOfPage":{"@id":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/"},"wordCount":784,"commentCount":0,"publisher":{"@id":"https:\/\/webkul.com\/blog\/#organization"},"image":{"@id":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#primaryimage"},"thumbnailUrl":"https:\/\/webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp","keywords":["Artificial Intelligence","machine learning"],"articleSection":["machine learning"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/webkul.com\/blog\/gemini-embedding-2\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/","url":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/","name":"Gemini Embedding 2: Google\u2019s Multimodal Embedding Model - Webkul Blog","isPartOf":{"@id":"https:\/\/webkul.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#primaryimage"},"image":{"@id":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#primaryimage"},"thumbnailUrl":"https:\/\/webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp","datePublished":"2026-03-17T12:42:21+00:00","dateModified":"2026-03-17T12:42:33+00:00","description":"Explore Gemini Embedding 2, Google\u2019s multimodal model for text, image, video, audio, and document embeddings in one shared space.","breadcrumb":{"@id":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/webkul.com\/blog\/gemini-embedding-2\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#primaryimage","url":"https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp","contentUrl":"https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2026\/03\/multimodalinput.webp","width":800,"height":500},{"@type":"BreadcrumbList","@id":"https:\/\/webkul.com\/blog\/gemini-embedding-2\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/webkul.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Gemini Embedding 2: Google\u2019s Multimodal Embedding Model"}]},{"@type":"WebSite","@id":"https:\/\/webkul.com\/blog\/#website","url":"https:\/\/webkul.com\/blog\/","name":"Webkul Blog","description":"","publisher":{"@id":"https:\/\/webkul.com\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/webkul.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/webkul.com\/blog\/#organization","name":"WebKul Software Private Limited","url":"https:\/\/webkul.com\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/webkul.com\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2021\/08\/webkul-logo-accent-sq.png","contentUrl":"https:\/\/cdnblog.webkul.com\/blog\/wp-content\/uploads\/2021\/08\/webkul-logo-accent-sq.png","width":380,"height":380,"caption":"WebKul Software Private Limited"},"image":{"@id":"https:\/\/webkul.com\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/webkul\/","https:\/\/x.com\/webkul","https:\/\/www.instagram.com\/webkul\/","https:\/\/www.linkedin.com\/company\/webkul","https:\/\/www.youtube.com\/user\/webkul\/"]},{"@type":"Person","@id":"https:\/\/webkul.com\/blog\/#\/schema\/person\/53a57eff87fe1f3e9e69c165efdabdc4","name":"Prashant Saini","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/webkul.com\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/90bd6382a7aa9ee0d5835bfaab3a739f91c37833f8e0d7cad51cd6a52b4914f0?s=96&d=https%3A%2F%2Fcdnblog.webkul.com%2Fblog%2Fwp-content%2Fuploads%2F2019%2F10%2Fmike.png&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/90bd6382a7aa9ee0d5835bfaab3a739f91c37833f8e0d7cad51cd6a52b4914f0?s=96&d=https%3A%2F%2Fcdnblog.webkul.com%2Fblog%2Fwp-content%2Fuploads%2F2019%2F10%2Fmike.png&r=g","caption":"Prashant Saini"},"description":"Prashant, a passionate Machine Learning and AI enthusiast, specialized in building intelligent solutions using Python and Generative AI technologies.","url":"https:\/\/webkul.com\/blog\/author\/prashant-ml322\/"}]}},"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/webkul.com\/blog\/wp-json\/wp\/v2\/posts\/530900","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/webkul.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/webkul.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/webkul.com\/blog\/wp-json\/wp\/v2\/users\/724"}],"replies":[{"embeddable":true,"href":"https:\/\/webkul.com\/blog\/wp-json\/wp\/v2\/comments?post=530900"}],"version-history":[{"count":2,"href":"https:\/\/webkul.com\/blog\/wp-json\/wp\/v2\/posts\/530900\/revisions"}],"predecessor-version":[{"id":531180,"href":"https:\/\/webkul.com\/blog\/wp-json\/wp\/v2\/posts\/530900\/revisions\/531180"}],"wp:attachment":[{"href":"https:\/\/webkul.com\/blog\/wp-json\/wp\/v2\/media?parent=530900"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/webkul.com\/blog\/wp-json\/wp\/v2\/categories?post=530900"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/webkul.com\/blog\/wp-json\/wp\/v2\/tags?post=530900"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}