{"slug":"embeddinggemma-2","name":"EmbeddingGemma 2","nameZh":"EmbeddingGemma 2（多模态向量模型）","category":"retrieval","categoryName":"Retrieval, vector DBs & embeddings","audience":["for-ai"],"primary":"for-ai","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"yes","officialUrl":"https://huggingface.co/google/embeddinggemma-2","repo":null,"latestVersion":null,"latestRelease":null,"stars":null,"starsAsOf":null,"description":"Google DeepMind's 0.74B multimodal embedding model: text (incl. code), images, video and audio in one 768-d space; 100+ languages, 8K context, Matryoshka truncation to 128/256/512; text-only loads just 270M, built for on-device RAG and semantic search","descriptionZh":"Google DeepMind 的 0.74B 多模态嵌入模型：文本（含代码）、图片、视频、音频映射到同一 768 维向量空间，支持 100+ 语言、8K 上下文、Matryoshka 截断到 128/256/512 维；纯文本只需加载 270M，可在手机和笔记本上跑，适合本地 RAG / 语义搜索","callMethods":[],"platforms":[],"addedAt":"2026-10-14","updatedAt":null,"topics":[],"language":null,"lastPush":null,"formerly":null,"packages":[],"recentVersions":[],"alternatives":["elasticsearch","redis","milvus","qdrant","chroma","pgvector","sentence-transformers","weaviate"],"stacks":[],"scenarios":["rag-and-documents"],"problems":[],"reasonZh":null,"sources":["editorial"],"record":"https://aimap.page/api/v1/software/embeddinggemma-2.json","pages":{"en":"https://aimap.page/en/software/embeddinggemma-2/","zh-hans":"https://aimap.page/zh-hans/software/embeddinggemma-2/"}}