Google AI Developers's banner

Google AI Developers

@googleaidevs • 114,203 subscribers

AI for every developer. So what will you build?

Shorts

Gemini Embedding 2 is now generally available in the Gemini API and Vertex AI! Start building with our first natively multimodal embedding model, now equipped with the stability and optimizations required for production apps.

Gemini Embedding 2 is now generally available in the Gemini API and Vertex AI! Start building with our first natively multimodal embedding model, now equipped with the stability and optimizations required for production apps.

812,345 Aufrufe

Now that Gemini Embedding 2 is GA, let’s explore what the model unlocks — from agentic multimodal RAG to visual search — as it maps text, images, video, audio, and documents into a unified embedding space.

Now that Gemini Embedding 2 is GA, let’s explore what the model unlocks — from agentic multimodal RAG to visual search — as it maps text, images, video, audio, and documents into a unified embedding space.

62,190 Aufrufe

Try 👁 Agentic Vision with Gemini 3 Flash in Google AI Studio or Vertex AI. This new capability enables the model to effectively use code and reasoning to improve performance for common vision tasks. See Agentic Vision in action:

Try 👁 Agentic Vision with Gemini 3 Flash in Google AI Studio or Vertex AI. This new capability enables the model to effectively use code and reasoning to improve performance for common vision tasks. See Agentic Vision in action:

174,885 Aufrufe

Some fun examples of Co-draw with Gemini 2.0 native image generation (make your own doodle with the link below)👇🧵

Some fun examples of Co-draw with Gemini 2.0 native image generation (make your own doodle with the link below)👇🧵

245,519 Aufrufe

See how Gemini 3 Flash and Vision-Language-Action (VLA) models work together to teach a robot how to play the board game First Orchard. This project shows how to use Gemini as the “brain” for tracking game rules and state, while the VLA handles complex physical manipulations like picking and placing fruit 🍎

See how Gemini 3 Flash and Vision-Language-Action (VLA) models work together to teach a robot how to play the board game First Orchard. This project shows how to use Gemini as the “brain” for tracking game rules and state, while the VLA handles complex physical manipulations like picking and placing fruit 🍎

26,640 Aufrufe

See Gemini 2.0's creative coding abilities! Watch how it can mimic an object's behavior in this demo by Trudy Painter ↓

See Gemini 2.0's creative coding abilities! Watch how it can mimic an object's behavior in this demo by Trudy Painter ↓

59,261 Aufrufe

YouTube link support is now available within the Gemini API and Google AI Studio. This update lets developers leverage the vast repository of video content on YouTube for analysis, summarization, and more. →

YouTube link support is now available within the Gemini API and Google AI Studio. This update lets developers leverage the vast repository of video content on YouTube for analysis, summarization, and more. →

42,571 Aufrufe

Veo 2 is now GA in Gemini API. Use text or image prompts to generate high-quality videos within your apps. 🎬 Read the docs:

Veo 2 is now GA in Gemini API. Use text or image prompts to generate high-quality videos within your apps. 🎬 Read the docs:

40,028 Aufrufe

✍️tldraw is using Gemini 3 Flash to power its natural language computer, tldraw computer. Networks of components on an infinite canvas each use Gemini to process data and generate content that flows into other components. These flows are faster, smarter, and more reliable with Gemini 3 Flash.

✍️tldraw is using Gemini 3 Flash to power its natural language computer, tldraw computer. Networks of components on an infinite canvas each use Gemini to process data and generate content that flows into other components. These flows are faster, smarter, and more reliable with Gemini 3 Flash.

12,450 Aufrufe

Relive the 90s with this starter app in Google AI Studio → Chat, browse, paint, and add your own apps to this retro desktop simulator coded with Gemini 2.5 Pro. Show us what you build with #Gemini95

Relive the 90s with this starter app in Google AI Studio → Chat, browse, paint, and add your own apps to this retro desktop simulator coded with Gemini 2.5 Pro. Show us what you build with #Gemini95

17,863 Aufrufe

Craft a custom recommendation algorithm with Keras Recommenders. This new library contains APIs designed for ranking, retrieval, and starter examples for writing and training your first recommender →

Craft a custom recommendation algorithm with Keras Recommenders. This new library contains APIs designed for ranking, retrieval, and starter examples for writing and training your first recommender →

14,826 Aufrufe

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Start building with Gemini Embedding 2, our most capable and first fully multimodal embedding model built on the Gemini architecture. Now available in preview via the Gemini API and in Vertex AI.

Start building with Gemini Embedding 2, our most capable and first fully multimodal embedding model built on the Gemini architecture. Now available in preview via the Gemini API and in Vertex AI.

Google AI Developers

30,483,135 Aufrufe • vor 2 Monaten

Control a robot in simulation with the Gemini Robotics Embodied Reasoning model 🤖 Direct tasks like object localization and placement by simply prompting a robotic arm to pick up and place objects.

Control a robot in simulation with the Gemini Robotics Embodied Reasoning model 🤖 Direct tasks like object localization and placement by simply prompting a robotic arm to pick up and place objects.

Google AI Developers

1,295,911 Aufrufe • vor 3 Monaten

We’re expanding the Gemini API File Search tool 🔍 with 3 new updates that enable developers to more easily build multimodal RAG systems with enhanced precision: + Multimodal Support: By leveraging our Gemini Embedding 2 model, File Search can now reason across image and text simultaneously. + Custom Metadata Filtering: Bring structure to unstructured data by tagging files with custom key-value labels. This pre-filters your data and boosts search speed. + Exact citations: File Search can now capture and return the exact source (down to the page number) for every piece of information indexed. See multimodal File Search in action with our example app in Google AI Studio. Chat with your entire image and doc library, ask questions, and trace answers back to the source:

We’re expanding the Gemini API File Search tool 🔍 with 3 new updates that enable developers to more easily build multimodal RAG systems with enhanced precision: + Multimodal Support: By leveraging our Gemini Embedding 2 model, File Search can now reason across image and text simultaneously. + Custom Metadata Filtering: Bring structure to unstructured data by tagging files with custom key-value labels. This pre-filters your data and boosts search speed. + Exact citations: File Search can now capture and return the exact source (down to the page number) for every piece of information indexed. See multimodal File Search in action with our example app in Google AI Studio. Chat with your entire image and doc library, ask questions, and trace answers back to the source:

Google AI Developers

107,790 Aufrufe • vor 29 Tagen

Introducing Veo 3.1 Lite, now available via the Gemini API and Google AI Studio. Veo 3.1 Lite supports both Text-to-Video and Image-to-Video, and is less than half the cost of Veo 3.1 Fast.

Introducing Veo 3.1 Lite, now available via the Gemini API and Google AI Studio. Veo 3.1 Lite supports both Text-to-Video and Image-to-Video, and is less than half the cost of Veo 3.1 Fast.

Google AI Developers

149,952 Aufrufe • vor 2 Monaten

With Gemini CLI's new pseudo-terminal (PTY) support, you can run complex, interactive commands like vim, top, or git rebase -i directly within the CLI without having to exit, keeping everything in context.

With Gemini CLI's new pseudo-terminal (PTY) support, you can run complex, interactive commands like vim, top, or git rebase -i directly within the CLI without having to exit, keeping everything in context.

Google AI Developers

331,383 Aufrufe • vor 7 Monaten

Gemini 3 Flash now uses an agentic "think-act-observe" loop to solve complex visual tasks 🤖 Google DeepMind engineer Paul Ruiz demonstrates how the model runs Python code automatically to zoom and inspect items, annotate images, and re-visualize data into charts.

Gemini 3 Flash now uses an agentic "think-act-observe" loop to solve complex visual tasks 🤖 Google DeepMind engineer Paul Ruiz demonstrates how the model runs Python code automatically to zoom and inspect items, annotate images, and re-visualize data into charts.

Google AI Developers

106,695 Aufrufe • vor 3 Monaten

🔔 The Google AI Edge Gallery is now live on iOS via TestFlight. Experience the power and speed of LLMs models running entirely on-device, including support for image and audio modalities.️

🔔 The Google AI Edge Gallery is now live on iOS via TestFlight. Experience the power and speed of LLMs models running entirely on-device, including support for image and audio modalities.️

Google AI Developers

116,773 Aufrufe • vor 5 Monaten

💎 Gemma 4 31B can leverage an ADK Agent and code execution sandbox to autonomously navigate complex, ambiguous tasks. Follow along as this demo showcases: + Zero-shot code generation + Tool usage + Multi-step debugging and recovery + “Learned” multimodal output

💎 Gemma 4 31B can leverage an ADK Agent and code execution sandbox to autonomously navigate complex, ambiguous tasks. Follow along as this demo showcases: + Zero-shot code generation + Tool usage + Multi-step debugging and recovery + “Learned” multimodal output

Google AI Developers

39,423 Aufrufe • vor 1 Monat

Introducing EmbeddingGemma: our new open, state-of-the-art embedding model designed for on-device AI 📱

Introducing EmbeddingGemma: our new open, state-of-the-art embedding model designed for on-device AI 📱

Google AI Developers

153,735 Aufrufe • vor 9 Monaten

✨ What makes Gemini 2.5 Pro stand out? In this Release Notes episode, Sr. Product Manager Logan Kilpatrick and Gemini Product Lead Tulsee Doshi break down its reasoning, coding, and multimodal strengths, plus a 1M token long context. ↓ Timecodes: 1:05 Gemini 2.5 launch overview 3:19 Academic evals vs. vibe checks 6:19 The jump to 2.5 7:51 Coordinating cross-stack improvements 11:48 Role of pre/post-training vs. test-time compute 13:21 Shipping Gemini 2.5 15:29 Embedded safety process 17:28 Multimodal reasoning with Gemini 2.5 18:55 Benchmark deep dive 22:07 What’s next for Gemini 24:49 Dynamic thinking in Gemini 2.5 25:37 The team effort behind the launch

✨ What makes Gemini 2.5 Pro stand out? In this Release Notes episode, Sr. Product Manager Logan Kilpatrick and Gemini Product Lead Tulsee Doshi break down its reasoning, coding, and multimodal strengths, plus a 1M token long context. ↓ Timecodes: 1:05 Gemini 2.5 launch overview 3:19 Academic evals vs. vibe checks 6:19 The jump to 2.5 7:51 Coordinating cross-stack improvements 11:48 Role of pre/post-training vs. test-time compute 13:21 Shipping Gemini 2.5 15:29 Embedded safety process 17:28 Multimodal reasoning with Gemini 2.5 18:55 Benchmark deep dive 22:07 What’s next for Gemini 24:49 Dynamic thinking in Gemini 2.5 25:37 The team effort behind the launch

Google AI Developers

227,343 Aufrufe • vor 1 Jahr

This Gemini 2.5 agent connects to 2,700+ APIs and 10K tools using MCP and Pipedream, and at less than 100 lines of code 🤯

This Gemini 2.5 agent connects to 2,700+ APIs and 10K tools using MCP and Pipedream, and at less than 100 lines of code 🤯

Google AI Developers

165,047 Aufrufe • vor 10 Monaten

Build fully offline mobile assistants with FunctionGemma 270M. This demo parses natural language commands like “Create a calendar event for lunch tomorrow” or “Add to contacts” to execute OS actions directly on-device.

Build fully offline mobile assistants with FunctionGemma 270M. This demo parses natural language commands like “Create a calendar event for lunch tomorrow” or “Add to contacts” to execute OS actions directly on-device.

Google AI Developers

86,450 Aufrufe • vor 4 Monaten

Start building with Gemini 3 Pro, our most intelligent model with state-of-the-art reasoning and complex multimodal understanding, as well as powerful agentic and vibe coding capabilities. See more below:

Start building with Gemini 3 Pro, our most intelligent model with state-of-the-art reasoning and complex multimodal understanding, as well as powerful agentic and vibe coding capabilities. See more below:

Google AI Developers

104,898 Aufrufe • vor 6 Monaten

Gemini CLI now integrates into VS Code. Get intelligent, context-aware suggestions and native in-editor diffing to review and modify changes directly in your IDE. Learn more:

Gemini CLI now integrates into VS Code. Get intelligent, context-aware suggestions and native in-editor diffing to review and modify changes directly in your IDE. Learn more:

Google AI Developers

143,837 Aufrufe • vor 9 Monaten

Gemini 3.1 Flash TTS is our most expressive speech generation model to date. [excited] Watch this demo from Thor 雷神 ⚡️ ⬇️

Gemini 3.1 Flash TTS is our most expressive speech generation model to date. [excited] Watch this demo from Thor 雷神 ⚡️ ⬇️

Google AI Developers

24,392 Aufrufe • vor 1 Monat

The Type Motion demo on Google AI Studio transforms simple text phrases into cinematic motion text using a two-step generative process.

The Type Motion demo on Google AI Studio transforms simple text phrases into cinematic motion text using a two-step generative process.

Google AI Developers

67,206 Aufrufe • vor 4 Monaten

Watch Gemini 3 Flash transform manual ETL into a near real-time workflow. This demo shows how the model’s speed and reasoning capabilities instantly resolve mismatched sources, clean messy data, and fully automate the pipeline.

Watch Gemini 3 Flash transform manual ETL into a near real-time workflow. This demo shows how the model’s speed and reasoning capabilities instantly resolve mismatched sources, clean messy data, and fully automate the pipeline.

Google AI Developers

65,671 Aufrufe • vor 5 Monaten

Watch this ADK Agent powered by Gemma 4 31B use the Google Maps MCP Server to build a custom food tour in this demo 🍜📍 See the model in action with: -Multi-step reasoning (solving complex routes) -Multimodal logic (processing visuals and text) -Live data integration (direct connection to Google Maps)

Watch this ADK Agent powered by Gemma 4 31B use the Google Maps MCP Server to build a custom food tour in this demo 🍜📍 See the model in action with: -Multi-step reasoning (solving complex routes) -Multimodal logic (processing visuals and text) -Live data integration (direct connection to Google Maps)

Google AI Developers

28,084 Aufrufe • vor 1 Monat

Gemini 3.0 Flash makes video understanding easier for robotics. Check out this demo where an Aloha robot executes complex tasks after a video is turned into a simple list of JSON action steps.

Gemini 3.0 Flash makes video understanding easier for robotics. Check out this demo where an Aloha robot executes complex tasks after a video is turned into a simple list of JSON action steps.

Google AI Developers

47,098 Aufrufe • vor 3 Monaten

Build AR applications that recognize physical objects and provide real-time spatial guidance. Stijn Spanhove and Pavlo Tkachenko used Gemini 2.5 Pro’s multimodal vision and sound effect prompting capabilities to create an immersive experience with LEGO Smart Bricks and Snap Spectacles.

Build AR applications that recognize physical objects and provide real-time spatial guidance. Stijn Spanhove and Pavlo Tkachenko used Gemini 2.5 Pro’s multimodal vision and sound effect prompting capabilities to create an immersive experience with LEGO Smart Bricks and Snap Spectacles.

Google AI Developers

47,780 Aufrufe • vor 3 Monaten