HomeGoogle Unveils Gemini Embedding2: Native Multimodal Model Unifies Semantic Spaces
Google has recently unveiled its new native multimodal embedding model, Gemini Embedding2. It can map text, images, videos, audio, and PDF documents into a shared semantic vector space, designed to streamline complex AI data workflows and improve multimodal retrieval and understanding. This represents a key advancement for Google in embedding technology, transitioning from single-modality text to unified multimodal semantic modeling.
Previously, in July 2025, Google introduced the gemini-embedding-001 text embedding model. It supported over 100 languages and achieved top results on the MTEB multilingual benchmark. The new Gemini Embedding2 builds on the Gemini architecture but significantly expands its scope. It now processes five different modalities—text, images, video, audio, and PDFs—and projects them into a single vector space. This allows for direct semantic comparisons across different types of media without needing multiple specialized models or extra processing steps. This capability is particularly valuable for applications like semantic search, retrieval-augmented generation (RAG), sentiment analysis, and data clustering.
Regarding input capabilities, the new model supports up to 8192 text tokens, quadruple the previous 2048-token limit. It can handle up to six PNG or JPEG images per request, videos up to 120 seconds long, and PDF documents up to six pages. A notable feature is Gemini Embedding2's native support for audio processing, eliminating the need for speech-to-text conversion and avoiding potential information loss from transcription. Google also introduced "interleaved input" technology, enabling developers to combine multiple modalities in one request—like mixing images with descriptive text—to better capture the semantic relationships between them.
Architecturally, the model continues to employ Matryoshka Representation Learning (MRL). This technique uses a hierarchical structure to dynamically adjust vector dimensions. The default embedding dimension is 3072, with optional configurations of 1536 and 768 available, giving developers flexibility to balance retrieval accuracy with storage efficiency.
Google's benchmark results indicate that Gemini Embedding2 delivers leading performance across text, image, video, and speech tasks. For instance, in text-video retrieval, it scores 68.8, outperforming Amazon Nova2Multimodal Embeddings (60.3) and Voyage Multimodal3.5 (55.2). In text-image comparison, it achieves a score of 93.4, significantly ahead of Amazon's model score of 84.0.
Gemini Embedding2 is currently accessible to developers via the Gemini API and Vertex AI. It integrates with popular frameworks and vector databases like LangChain, LlamaIndex, Haystack, Weaviate, Qdrant, ChromaDB, and Vector Search. To help developers get started, Google provides interactive Colab notebooks and lightweight multimodal semantic search demonstrations.
The competition in multimodal embedding is heating up. Notably, in late February of this year, the AI search engine Perplexity released its open-source embedding models, pplx-embed-v1 and pplx-embed-context-v1.
Related article
Stripe to Acquire OpenRouter as AI Model Routing Gains Momentum
Stripe has agreed to acquire OpenRouter, an AI model-routing platform that gives developers access to hundreds of models through a single interface. The deal adds model selection and routing to Stripe’s existing work around AI usage and token-based b
Former OpenAI Researcher Barrett Zoph Returns to Google to Support Gemini Development
Barret Zoph, who previously abruptly left and joined OpenAI due to a disagreement with Thinking Machines Lab CEO Miriam Mularati, has once again changed employers. Alphabet's Google announced that Zoph will return as Vice President of Research, bring
How Recursive Intelligence Raised $335M at $4B Valuation in 4 Months
The co-founders of startup Ricursive Intelligence seemed destined to be co-founders.Anna Goldie, CEO, and Azalia Mirhoseini, CTO, are so well-known in the AI community that they were among those AI engineers who “got those weird emails from Zuckerber
Related Special Topic Recommendations
Design & Art
Top AI Illustration Tools: Create Editorial Scenes and Cover Art Faster
2026 Latest Top-rated AI Illustration Tools: Our curated list features the best powerfully designed tools for creating stunning editorial scenes and eye-catching cover art quickly. Each option has gone through rigorous real-world tests, offering a free vs paid comparison to help you find the perfect match for your workflow. Try these must-try solutions today to unlock your AI edge and boost your creative productivity. Explore now at XIX.AI.
10 tools
xix.ai
Education and Learning
Top AI Tutors for Exam Prep: Practice Math, Science, and English
2026 Latest Top-Rated Best AI Tutors for Exam Prep are here on XIX.AI! Our curated list features powerful game-changing tools that offer free vs paid comparison, real-world tests, and weekly updated rankings. They help boost your writing efficiency, simplify complex topic learning, and unlock your academic potential. Explore now to Discover your perfect exam prep tool and Start creating today to Unlock your AI edge!
10 tools
xix.ai
Finance
AI Budget Planning Tools for Personal Money Management
2026 Latest Best Top-Rated AI Budget Planning Tools for Personal Money Management are here on XIX.AI! This curated collection features powerful, game-changing solutions that help you conduct real-world tests, understand spending habits, and create personalized plans to boost productivity. Enjoy a free vs paid comparison along with detailed rankings. Must-try tools designed to simplify money management and unlock your AI edge. Explore now!
11 tools
xix.ai
Health & Wellness
AI Sleep Tracking Assistants: Improve Recovery with Better Bedtime Habits
2026 Latest Best Top-Rated AI Sleep Tracking Assistants curated for ultimate recovery. This fully updated weekly guide features powerful tools that deliver real-world tests, free vs paid comparison, and detailed rankings to help you find the must-try solution that boosts sleep quality and supports better bedtime habits. Explore now at XIX.AI to Unlock your AI edge.
10 tools
xix.ai
Data Analysis
AI SQL Copilots for Product and Revenue Analytics
2026 Latest Best Top-Rated AI SQL Copilots for Product and Revenue Analytics! XIX.AI has curated a powerful, game-changing collection of must-try tools that undergo real-world tests through weekly updated rankings. These tools help users boost productivity significantly by accelerating data analysis, streamlining complex queries, and generating accurate insights to drive smarter business decisions. Explore now to Discover your perfect tool for unlocking your AI edge!
14 tools
xix.ai
Education and Learning
Best AI Homework Helpers That Teach: Learn Concepts, Not Just Answers
2026 Latest Best Top-Rated AI Homework Helpers That Teach Core Concepts Not Just Answers Powerful Tools for Students Must-Try Curated List Weekly Updated Free vs Paid Comparison Real-World Tests Accurate Rankings to Help You Unlock Your Full Learning Potential Explore now to Discover your perfect tool for smarter studying.
10 tools
xix.ai
Comments (0)
0/500
Google has recently unveiled its new native multimodal embedding model, Gemini Embedding2. It can map text, images, videos, audio, and PDF documents into a shared semantic vector space, designed to streamline complex AI data workflows and improve multimodal retrieval and understanding. This represents a key advancement for Google in embedding technology, transitioning from single-modality text to unified multimodal semantic modeling.
Previously, in July 2025, Google introduced the gemini-embedding-001 text embedding model. It supported over 100 languages and achieved top results on the MTEB multilingual benchmark. The new Gemini Embedding2 builds on the Gemini architecture but significantly expands its scope. It now processes five different modalities—text, images, video, audio, and PDFs—and projects them into a single vector space. This allows for direct semantic comparisons across different types of media without needing multiple specialized models or extra processing steps. This capability is particularly valuable for applications like semantic search, retrieval-augmented generation (RAG), sentiment analysis, and data clustering.
Regarding input capabilities, the new model supports up to 8192 text tokens, quadruple the previous 2048-token limit. It can handle up to six PNG or JPEG images per request, videos up to 120 seconds long, and PDF documents up to six pages. A notable feature is Gemini Embedding2's native support for audio processing, eliminating the need for speech-to-text conversion and avoiding potential information loss from transcription. Google also introduced "interleaved input" technology, enabling developers to combine multiple modalities in one request—like mixing images with descriptive text—to better capture the semantic relationships between them.
Architecturally, the model continues to employ Matryoshka Representation Learning (MRL). This technique uses a hierarchical structure to dynamically adjust vector dimensions. The default embedding dimension is 3072, with optional configurations of 1536 and 768 available, giving developers flexibility to balance retrieval accuracy with storage efficiency.
Google's benchmark results indicate that Gemini Embedding2 delivers leading performance across text, image, video, and speech tasks. For instance, in text-video retrieval, it scores 68.8, outperforming Amazon Nova2Multimodal Embeddings (60.3) and Voyage Multimodal3.5 (55.2). In text-image comparison, it achieves a score of 93.4, significantly ahead of Amazon's model score of 84.0.
Gemini Embedding2 is currently accessible to developers via the Gemini API and Vertex AI. It integrates with popular frameworks and vector databases like LangChain, LlamaIndex, Haystack, Weaviate, Qdrant, ChromaDB, and Vector Search. To help developers get started, Google provides interactive Colab notebooks and lightweight multimodal semantic search demonstrations.
The competition in multimodal embedding is heating up. Notably, in late February of this year, the AI search engine Perplexity released its open-source embedding models, pplx-embed-v1 and pplx-embed-context-v1.
Stripe to Acquire OpenRouter as AI Model Routing Gains Momentum
Stripe has agreed to acquire OpenRouter, an AI model-routing platform that gives developers access to hundreds of models through a single interface. The deal adds model selection and routing to Stripe’s existing work around AI usage and token-based b
Former OpenAI Researcher Barrett Zoph Returns to Google to Support Gemini Development
Barret Zoph, who previously abruptly left and joined OpenAI due to a disagreement with Thinking Machines Lab CEO Miriam Mularati, has once again changed employers. Alphabet's Google announced that Zoph will return as Vice President of Research, bring
How Recursive Intelligence Raised $335M at $4B Valuation in 4 Months
The co-founders of startup Ricursive Intelligence seemed destined to be co-founders.Anna Goldie, CEO, and Azalia Mirhoseini, CTO, are so well-known in the AI community that they were among those AI engineers who “got those weird emails from Zuckerber
2026 Latest Top-rated AI Illustration Tools: Our curated list features the best powerfully designed tools for creating stunning editorial scenes and eye-catching cover art quickly. Each option has gone through rigorous real-world tests, offering a free vs paid comparison to help you find the perfect match for your workflow. Try these must-try solutions today to unlock your AI edge and boost your creative productivity. Explore now at XIX.AI.
10 tools
xix.ai
2026 Latest Top-Rated Best AI Tutors for Exam Prep are here on XIX.AI! Our curated list features powerful game-changing tools that offer free vs paid comparison, real-world tests, and weekly updated rankings. They help boost your writing efficiency, simplify complex topic learning, and unlock your academic potential. Explore now to Discover your perfect exam prep tool and Start creating today to Unlock your AI edge!
10 tools
xix.ai
2026 Latest Best Top-Rated AI Budget Planning Tools for Personal Money Management are here on XIX.AI! This curated collection features powerful, game-changing solutions that help you conduct real-world tests, understand spending habits, and create personalized plans to boost productivity. Enjoy a free vs paid comparison along with detailed rankings. Must-try tools designed to simplify money management and unlock your AI edge. Explore now!
11 tools
xix.ai
2026 Latest Best Top-Rated AI Sleep Tracking Assistants curated for ultimate recovery. This fully updated weekly guide features powerful tools that deliver real-world tests, free vs paid comparison, and detailed rankings to help you find the must-try solution that boosts sleep quality and supports better bedtime habits. Explore now at XIX.AI to Unlock your AI edge.
10 tools
xix.ai
2026 Latest Best Top-Rated AI SQL Copilots for Product and Revenue Analytics! XIX.AI has curated a powerful, game-changing collection of must-try tools that undergo real-world tests through weekly updated rankings. These tools help users boost productivity significantly by accelerating data analysis, streamlining complex queries, and generating accurate insights to drive smarter business decisions. Explore now to Discover your perfect tool for unlocking your AI edge!
14 tools
xix.ai
2026 Latest Best Top-Rated AI Homework Helpers That Teach Core Concepts Not Just Answers Powerful Tools for Students Must-Try Curated List Weekly Updated Free vs Paid Comparison Real-World Tests Accurate Rankings to Help You Unlock Your Full Learning Potential Explore now to Discover your perfect tool for smarter studying.
10 tools
xix.ai
