--- title: Grounding with Google Search in the Firebase AI Logic... description: Firebase AI Logic client-side SDKs now support Grounding with Google Search, letting the Gemini model perform real-time web searches before generating answers... canonical: https://daily.dev/posts/grounding-with-google-search-in-the-firebase-ai-logic-client-sdks-wphk9hprx twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Grounding with Google Search in the Firebase AI Logic client SDKs | daily.dev og:description: Firebase AI Logic client-side SDKs now support Grounding with Google Search, letting the Gemini model perform real-time web searches before generating answers... og:url: https://daily.dev/posts/grounding-with-google-search-in-the-firebase-ai-logic-client-sdks-wphk9hprx og:image: https://api.daily.dev/og/posts/wpHk9HPrx.png og:image:alt: Grounding with Google Search in the Firebase AI Logic client SDKs og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Grounding with Google Search in the Firebase AI Logic client SDKs **[Firebase](https://daily.dev/sources/firebase-blog)** · 4 min read · 0 upvotes · 0 comments ## Summary Firebase AI Logic client-side SDKs now support Grounding with Google Search, letting the Gemini model perform real-time web searches before generating answers so responses reflect current events rather than being limited to training data. Developers pass googleSearch as a tool to the generative model and receive a groundingMetadata object with search queries, source chunks, and citation segments. The feature requires upgrading to specific new SDK versions: Android BoM 34.0.0, Flutter 2.3.0, iOS 12.0.0, Web 12.0.0, and Unity 12.11.0. Apps using this feature must display the Google Search suggestions in their UI to comply with usage requirements. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I enable Grounding with Google Search in Firebase AI Logic with Gemini? Pass googleSearch as a tool when calling getGenerativeModel, for example tools: [{ googleSearch: {} }] with model gemini-2.5-flash. The response then includes a groundingMetadata object containing webSearchQueries, groundingChunks with source URIs, and groundingSupports mapping response text segments to sources, letting Gemini answer with current, real-time facts instead of relying only on training data. _daily.dev surfaces integration guides like this for teams wiring live search into their AI features._ ### What is the minimum Firebase SDK version needed for Grounding with Google Search? Grounding with Google Search requires Android BoM 34.0.0, Flutter 2.3.0, iOS 12.0.0, Web 12.0.0, or Unity 12.11.0, depending on platform. Upgrading to at least these versions of the Firebase AI Logic client-side SDKs is required before the googleSearch tool option becomes available in the generative model API. _Developers tracking SDK version requirements before upgrading often follow release details on daily.dev._ ### What are the usage requirements when displaying grounded Gemini search results in an app? Apps must display the Google Search suggestions returned in the groundingMetadata.searchEntryPoint.renderedContent field within the UI whenever a response is grounded. This is required to comply with the Grounding with Google Search usage terms, and if renderedSearchSuggestions is unavailable, the app should indicate that the result was not grounded in search rather than omitting attribution. _daily.dev helps developers keep up with compliance details tied to AI search grounding features._ ## Similar posts on daily.dev - [Experimental hybrid inference and new Gemini models for Android](https://daily.dev/posts/experimental-hybrid-inference-and-new-gemini-models-for-android-cc5bn1znk) · Android Developers Blog · 1 upvotes · 0 comments - [Expanding Choice in Gemini Enterprise Agent Platform: Introducing Grounding with Parallel Web Search](https://daily.dev/posts/expanding-choice-in-gemini-enterprise-agent-platform-introducing-grounding-with-parallel-web-search-hypx2i4kb) · Google Developers · 1 upvotes · 0 comments - [Serverless AI for Android with Firebase AI Logic](https://daily.dev/posts/serverless-ai-for-android-with-firebase-ai-logic-33d7pefc4) · ProAndroidDev · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#mobile](https://daily.dev/tags/mobile), [#firebase](https://daily.dev/tags/firebase), [#google-gemini](https://daily.dev/tags/google-gemini) [View this post on daily.dev](https://daily.dev/posts/grounding-with-google-search-in-the-firebase-ai-logic-client-sdks-wphk9hprx) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Grounding with Google Search in the Firebase AI Logic client SDKs","url":"https://daily.dev/posts/grounding-with-google-search-in-the-firebase-ai-logic-client-sdks-wphk9hprx","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/grounding-with-google-search-in-the-firebase-ai-logic-client-sdks-wphk9hprx"},"datePublished":"2026-08-23T12:17:50.511Z","dateModified":"2026-08-23T12:26:30.743Z","description":"Firebase AI Logic client-side SDKs now support Grounding with Google Search, letting the Gemini model perform real-time web searches before generating answers...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/69d5e26a8df3e8825f4ea1276e9bdb40?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/69d5e26a8df3e8825f4ea1276e9bdb40?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Firebase","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Firebase","logo":"https://media.daily.dev/image/upload/s--i395oqZH--/f_auto,q_auto/v1787487448/logos/firebase-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/firebase-blog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/grounding-with-google-search-in-the-firebase-ai-logic-client-sdks-wphk9hprx","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,mobile,firebase,google-gemini","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Firebase","item":"https://daily.dev/sources/firebase-blog"},{"@type":"ListItem","position":3,"name":"Grounding with Google Search in the Firebase AI Logic client SDKs"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/grounding-with-google-search-in-the-firebase-ai-logic-client-sdks-wphk9hprx#faq","mainEntity":[{"@type":"Question","name":"How do I enable Grounding with Google Search in Firebase AI Logic with Gemini?","acceptedAnswer":{"@type":"Answer","text":"Pass googleSearch as a tool when calling getGenerativeModel, for example tools: [{ googleSearch: {} }] with model gemini-2.5-flash. The response then includes a groundingMetadata object containing webSearchQueries, groundingChunks with source URIs, and groundingSupports mapping response text segments to sources, letting Gemini answer with current, real-time facts instead of relying only on training data. daily.dev surfaces integration guides like this for teams wiring live search into their AI features."}},{"@type":"Question","name":"What is the minimum Firebase SDK version needed for Grounding with Google Search?","acceptedAnswer":{"@type":"Answer","text":"Grounding with Google Search requires Android BoM 34.0.0, Flutter 2.3.0, iOS 12.0.0, Web 12.0.0, or Unity 12.11.0, depending on platform. Upgrading to at least these versions of the Firebase AI Logic client-side SDKs is required before the googleSearch tool option becomes available in the generative model API. Developers tracking SDK version requirements before upgrading often follow release details on daily.dev."}},{"@type":"Question","name":"What are the usage requirements when displaying grounded Gemini search results in an app?","acceptedAnswer":{"@type":"Answer","text":"Apps must display the Google Search suggestions returned in the groundingMetadata.searchEntryPoint.renderedContent field within the UI whenever a response is grounded. This is required to comply with the Grounding with Google Search usage terms, and if renderedSearchSuggestions is unavailable, the app should indicate that the result was not grounded in search rather than omitting attribution. daily.dev helps developers keep up with compliance details tied to AI search grounding features."}}]} ```