Platform Summary used ♊ Gemini AI DISCOVER: Generative AI Overviews Explore how teams at Google are using Generative AI to create new experiences. Historically, AI was used to understand and recommend information. Now, generative AI can also help us create new content. Generative AI builds on existing technologies, like large language models (LLMs) which are trained on large amounts of text and learn to predict the next word in a sentence. For example, "peanut butter and ___" is more likely to be followed by "jelly" than "shoelace". Generative AI can not only create new text, but also images, videos, or audio. Explore how teams at Google are implementing generative AI to create new experiences.
Google AI Studio Empowering developers to build with Gemini Google AI Studio enables developers to seamlessly integrate Gemini models with an easy and safe API, quickly develop prompts, and transform ideas into code to build generative AI applications.
Aries Google AI Edge Introducing LiteRT: Google's high-performance runtime for on-device AI, formerly known as TensorFlow Lite. Learn more Home Google AI Edge Solutions Was this helpful? Send feedback Setup guide for web
Cache-Control: no-cache Content-Security-Policy: default-src 'none'; style-src 'unsafe-inline' Content-Type: text/html; charset=utf-8 Strict-Transport-Security: max-age=31536000 X-Content-Type-Options: nosniff X-Frame-Options: deny X-Xss-Protection: 0
Settings Recent Deliveries a6a0daf0-92aa-11ef-8522-2877fba53515 repository.unarchived 2024-10-25 15:25:11 … Request Response 403 Completed in 0.01 seconds.
Request URL: https://api.github.com/repos/AriesTriputranto/chromium-dashboard/hook Request method: POST Accept: / Content-Type: application/json User-Agent: GitHub-Hookshot/c0ace7e X-GitHub-Delivery: a6a0daf0-92aa-11ef-8522-2877fba53515 X-GitHub-Event: repository X-GitHub-Hook-ID: 506445521 X-GitHub-Hook-Installation-Target-ID: 865714049 X-GitHub-Hook-Installation-Target-Type: repository X-Hub-Signature: sha1=e361065c059ff3dfaa278eac68af1587ebad1117 X-Hub-Signature-256: sha256=32c2cb49324ac63d66a68b8b18f2d054f8529e428396aaae59a039c3ad4c99fd
{ "action": "unarchived", "repository": { "id": 865714049, "node_id": "R_kgDOM5m_gQ", "name": "Gemini-AI", "full_name": "AriesTriputranto99/Gemini-AI", "private": false, "owner": { "login": "AriesTriputranto99", "id": 104224708, "node_id": "U_kgDOBjZXxA", "avatar_url": "https://avatars.githubusercontent.com/u/104224708?v=4", "gravatar_id": "", "url": "https://api.github.com/users/AriesTriputranto99", "html_url": "https://github.com/AriesTriputranto99", "followers_url": "https://api.github.com/users/AriesTriputranto99/followers", "following_url": "https://api.github.com/users/AriesTriputranto99/following{/other_user}", "gists_url": "https://api.github.com/users/AriesTriputranto99/gists{/gist_id}", "starred_url": "https://api.github.com/users/AriesTriputranto99/starred{/owner}{/repo}", "subscriptions_url": "https://api.github.com/users/AriesTriputranto99/subscriptions", "organizations_url": "https://api.github.com/users/AriesTriputranto99/orgs", "repos_url": "https://api.github.com/users/AriesTriputranto99/repos", "events_url": "https://api.github.com/users/AriesTriputranto99/events{/privacy}", "received_events_url": "https://api.github.com/users/AriesTriputranto99/received_events", "type": "User", "user_view_type": "public", "site_admin": false }, "html_url": "https://github.com/AriesTriputranto99/Gemini-AI", "description": "Platform Summary used ♊ Gemini AI ", "fork": false, "url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI", "forks_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/forks", "keys_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/keys{/key_id}", "collaborators_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/collaborators{/collaborator}", "teams_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/teams", "hooks_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/hooks", "issue_events_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/issues/events{/number}", "events_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/events", "assignees_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/assignees{/user}", "branches_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/branches{/branch}", "tags_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/tags", "blobs_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/git/blobs{/sha}", "git_tags_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/git/tags{/sha}", "git_refs_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/git/refs{/sha}", "trees_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/git/trees{/sha}", "statuses_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/statuses/{sha}", "languages_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/languages", "stargazers_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/stargazers", "contributors_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/contributors", "subscribers_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/subscribers", "subscription_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/subscription", "commits_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/commits{/sha}", "git_commits_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/git/commits{/sha}", "comments_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/comments{/number}", "issue_comment_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/issues/comments{/number}", "contents_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/contents/{+path}", "compare_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/compare/{base}...{head}", "merges_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/merges", "archive_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/{archive_format}{/ref}", "downloads_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/downloads", "issues_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/issues{/number}", "pulls_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/pulls{/number}", "milestones_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/milestones{/number}", "notifications_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/notifications{?since,all,participating}", "labels_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/labels{/name}", "releases_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/releases{/id}", "deployments_url": "https://api.github.com/repos/AriesTriputranto99/Gemini-AI/deployments", "created_at": "2024-10-01T02:11:13Z", "updated_at": "2024-10-25T08:25:09Z", "pushed_at": "2024-10-18T06:06:09Z", "git_url": "git://github.com/AriesTriputranto99/Gemini-AI.git", "ssh_url": "git@github.com:AriesTriputranto99/Gemini-AI.git", "clone_url": "https://github.com/AriesTriputranto99/Gemini-AI.git", "svn_url": "https://github.com/AriesTriputranto99/Gemini-AI", "homepage": "https://support.google.com/?p=o_gemini_apps", "size": 2397, "stargazers_count": 0, "watchers_count": 0, "language": null, "has_issues": true, "has_projects": true, "has_downloads": true, "has_wiki": true, "has_pages": true, "has_discussions": false, "forks_count": 0, "mirror_url": null, "archived": false, "disabled": false, "open_issues_count": 0, "license": { "key": "mit", "name": "MIT License", "spdx_id": "MIT", "url": "https://api.github.com/licenses/mit", "node_id": "MDc6TGljZW5zZTEz" }, "allow_forking": true, "is_template": true, "web_commit_signoff_required": true, "topics": [ "application", "gemini-ai", "google", "license", "privacy-protection", "siteserver", "support", "terms", "translate", "webapp" ], "visibility": "public", "forks": 0, "open_issues": 0, "watchers": 0, "default_branch": "main" },
This page shows you how to set up your development environment to use MediaPipe Tasks in your JavaScript web applications.
Supported platforms and versions To create web applications with MediaPipe Tasks, your development environment requires the following:
Chrome or Safari browser A web application that uses Node.js and NPM. Alternatively, you can use script tags to access MediaPipe Tasks through a content delivery network (CDN). MediaPipe Tasks dependencies MediaPipe Tasks provides three prebuilt libraries for vision, text, and audio. Depending on the MediaPipe Task used by the app, import the vision, text, or audio library into your development project.
Attention: This MediaPipe Solutions Preview is an early release. Learn more. Generative AI tasks The MediaPipe Tasks Generative AI module contains tasks that handle image or text generation. To import the MediaPipe Tasks Generative AI libraries, import the following dependencies into your development project.
LLM Inference API The MediaPipe LLM Inference task is contained within the tasks-genai library.
npm install @mediapipe/tasks-genai If you want to deploy to a server, you can use a content delivery network (CDN) service, such as jsDelivr, to add code directly to your HTML page.
<script src="https://cdn.jsdelivr.net/npm/@mediapipe/tasks-genai/genai_bundle.cjs" crossorigin="anonymous"></script> Vision tasks The MediaPipe Tasks vision module contains tasks that handle image or video inputs. To import the MediaPipe Tasks vision library, import the following dependency to your into your development project.npm install @mediapipe/tasks-vision If you want to deploy to a server, you can use a content delivery network (CDN) service, such as jsDelivr, to add code directly to your HTML page.
<script src="https://cdn.jsdelivr.net/npm/@mediapipe/tasks-vision/vision_bundle.js" crossorigin="anonymous"></script> Text tasks The MediaPipe Tasks text module contains tasks that handle string inputs. To import the MediaPipe Tasks text library, import the following dependency to your into your development project.npm install @mediapipe/tasks-text If you want to deploy to a server, you can use a content delivery network (CDN) service, such as jsDelivr, to add code directly to your HTML page.
<script src="https://cdn.jsdelivr.net/npm/@mediapipe/tasks-text/text_bundle.js" crossorigin="anonymous"></script> Audio tasks The MediaPipe Tasks audio module contains tasks that handle sound inputs. To import the MediaPipe Tasks audio library, import the following dependency to your into your development project.npm install @mediapipe/tasks-audio If you want to deploy to a server, you can use a content delivery network (CDN) service, such as jsDelivr, to add code directly to your HTML page.
<script src="https://cdn.jsdelivr.net/npm/@mediapipe/tasks-audio/audio_bundle.js" crossorigin="anonymous"></script> BaseOptions configuration The BaseOptions allow for general configuration of MediaPipe Task APIs.Option name Description Accepted values modelAssetBuffer The model asset file contents as a Uint8Array typed array. Uint8Array modelAssetPath The path of the model asset to open and map into memory. TrustedResourceUrl Delegate Enables hardware acceleration through a device delegate to run the MediaPipe pipeline. Default value: CPU. [CPU, GPU] Troubleshooting For help with technical questions related to MediaPipe, visit the discussion group or Stack Overflow for support from the community. To report bugs or make feature requests, file an issue on GitHub.
Was this helpful?
Send feedback Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
bookmark_border Google's common crawlers are used to find information for building Google's search indexes, perform other product specific crawls, and for analysis. They always obey robots.txt rules when crawling automatically. The general technical properties of Google's crawlers also apply to the common crawlers.
The common crawlers generally crawl from the IP ranges published in the googlebot.jsonobject, and the reverse DNS mask of their hostname matches crawl----.googlebot.com or geo-crawl----.geo.googlebot.com.
The following list shows the common crawlers, their user agent strings as they appear in the HTTP requests, their user agent tokens for the User-agent: line in robots.txt, and the products that are affected by crawl preferences for the crawler. Some crawlers have more than o one crawler token for a rule to apply. The list is not exhaustive, it only covers the requestors that are more likely to show up in log files and that we've received questions about.
User-Agent substring in HTTP requests
Google-CloudVertexBot robots.txt User-agent token in robots.txt Google-CloudVertexBot Googlebot Example robots.txt group
user-agent: Google-CloudVertexBot allow: /archive/1Q84 disallow: /archive/ Affected products Crawling preferences addressed to the Google-CloudVertexBot user agent affect crawls requested by the site owners' for building Vertex AI Agents It has no effect on Google Search or other products. Google-Extended User-Agent in HTTP requests Google-Extended doesn't have a separate HTTP request user agent string. Crawling is done with existing Google user agent strings; the robots.txt user-agent token is used in a control capacity. robots.txt User-agent token in robots.txt Google-Extended Example robots.txt group
user-agent: Google-Extended allow: /archive/1Q84 disallow: /archive/ Affected products Google-Extended is a standalone product token that web publishers can use to manage whether their sites help improve Gemini Apps and Vertex AI generative APIs, including future generations of models that power those products. Google-Extended does not impact a site's inclusion or ranking in Google Search
Wherever you see the string Chrome/W.X.Y.Z in the user agent strings in the table, W.X.Y.Z is actually a placeholder that represents the version of the Chrome browser used by that user agent: for example, 41.0.2272.96. This version number will increase over time to match the latest Chromium release version used by Googlebot
// import { GoogleGenerativeAI } from "@google/generative-ai"; const genAI = new GoogleGenerativeAI(process.env.API_AIzaSyDLrTIyHq_3M_41muKnHzV7aqdayMx8rwM); const model = genAI.getGenerativeModel({ model: "Gemini-AI" });
const prompt = "Write a story about a magic backpack.";
const result = await model.generateContent(prompt); console.log(result.response.text());
<script type="module"> import { GoogleGenerativeAI } from "@google/generative-ai"; // Fetch your API_KEY
const API_KEY = "AIzaSyDLrTIyHq_3M_41muKnHzV7aqdayMx8rwM";
AI Overviews and your website bookmark_border AI Overviews appear in Google Search results when our systems determine that generative responses can be especially helpful — for example, when you want to quickly understand information from a range of sources, including information from across the web and Google's Knowledge Graph. No action is needed for publishers to benefit from AI Overviews.
How do links appear in AI Overviews? AI Overviews show links to resources that support the information in the snapshot, and explore the topic further. This allows people to dig deeper and discover a diverse range of content from publishers, creators, retailers, businesses, and more, and use the information they find to advance their tasks.
Google's systems automatically determine which links appear. There is nothing special for creators to do to be considered other than to follow our regular guidance for appearing in search, as covered in Google Search Essentials. About logging in Search Console For logging purposes in Search Console, links that appear in AI Overviews count toward the totals reported in the Performance report for Search results. Learn more about how clicks, impressions, and position are recorded.
How to prevent content from appearing in AI Overviews AI Overviews offer a preview of a topic or query based on a variety of sources, including web sources. As such, they are subject to Search's preview controls.
Google-Extended is not a method for managing how your content appears in Google Search. Instead, use other methods to manage your content in Search, such as robots.txt or other robot controls. Troubleshooting preview controls If you implemented preview controls and you're still seeing your content appear in AI Overviews, try the following steps:
Make sure that the preview control is correct and visible to Googlebot. To test if your implementation is correct, use the URL Inspection tool to see the HTML that Googlebot received while crawling the page. Allow time for Google to recrawl and process the change in preview controls. Remember that crawling can take anywhere from several days to several months, depending on how often our systems determine a page needs to be refreshed. If you've made changes, you can request that Google recrawl your pages
Last updated 2024-08-12 UTC