[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-gemini-file-search-multimodal-rag-embedding-2":3,"news-related-9ccc9f40-1004-417f-a245-9dafdc441d19":36},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"9ccc9f40-1004-417f-a245-9dafdc441d19","Google Gemini API File Search升级：原生支持多模态检索，开启RAG新范式","2026年5月5日，Google宣布Gemini API的File Search工具完成重大升级，正式支持多模态检索能力。这一更新基于Gemini Embedding 2模型，让开发者可以同时理解和检索图像与文本内容。\\n\\n此前的File Search仅支持纯文本检索，开发者需要借助外部工具将图像转文本后再处理。现在，Gemini可以直接看懂原始图片，通过自然语言描述查找视觉资产。例如，输入一张色调温暖的广告海报，系统就能从图库中找出匹配项，而不再依赖文件名或Alt文本。这对需要管理大量视觉素材的企业来说，意味着检索逻辑的范式转变。\\n\\n升级版File Search还带来了两个实用新功能：自定义元数据过滤可以为文件附加键值标签，查询时直接限定范围，显著降低噪声；页级引用让AI回答的每一条信息都能追溯到原始PDF的页码，提升透明度，便于事实核查。\\n\\n多模态检索能力改变了RAG系统的设计思路——过去需要分别处理文本和图像的索引，现在可以统一做语义检索，简化架构的同时提升召回质量。这是Google将Gemini多模态能力落地到生产工具的一次务实推进，File Search从找文档升级为理解内容，RAG的工作方式也随之改变。","https:\u002F\u002Fblog.google\u002Finnovation-and-ai\u002Ftechnology\u002Fdevelopers-tools\u002Fexpanded-gemini-api-file-search-multimodal-rag\u002F","3318cb52-f01e-4c9e-a34a-5dbc9fa986f2",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"40269b40-7942-4650-9672-ed2e6524d37a","ai-technology",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"a9524a82-a7c5-4daa-bb4b-a7ee77bb0b94","gemini",{"id":18,"name":19,"slug":19,"description":13,"color":13},"8cf7490f-2449-4ba7-be19-61befa0d92b4","google",{"id":21,"name":22,"slug":22,"description":13,"color":13},"499f4b56-819d-49a3-9609-33e775143b86","multimodal",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"f95475c0-937d-4b54-8c38-063d56f2f4cc","en","Gemini API File Search goes multimodal-native for RAG","On May 5, 2026, Google announced a major upgrade to the Gemini API's File Search tool, officially supporting multimodal retrieval. The update is based on the Gemini Embedding 2 model, letting developers simultaneously understand and retrieve image and text content.\n\nPreviously, File Search only supported pure-text retrieval, requiring developers to use external tools to convert images to text before processing. Now, Gemini can directly read original images, finding visual assets via natural-language descriptions. For example, inputting a warm-toned advertising poster, the system can find matching items from the image library, no longer relying on file names or alt text. For enterprises needing to manage large amounts of visual material, this means a paradigm shift in retrieval logic.\n\nThe upgraded File Search also brings two practical new features: custom metadata filtering lets you attach key-value tags to files, and queries can directly limit scope, significantly reducing noise; page-level citations let every piece of information in the AI's answer be traced back to a specific page of the original PDF, improving transparency and making fact-checking easier.\n\nMultimodal retrieval capability changes the design thinking of RAG systems — in the past, text and image indexes had to be handled separately, but now unified semantic retrieval is possible, simplifying architecture while improving recall quality. This is a pragmatic step by Google to land Gemini's multimodal capabilities into production tools, with File Search upgrading from finding documents to understanding content, and the way RAG works changing accordingly.","gemini-file-search-multimodal-rag-embedding-2","2026-05-13T01:00:00Z","2026-05-13T01:04:57.154461Z","2026-08-19T02:08:40.142862Z",true,"agent",97,{"items":37},[38,43,48,53,58,63],{"id":39,"title":40,"news_slug":41,"published_at":42},"314eb288-1ebb-4e32-825d-4eee55e78391","Google AI 眼镜上手体验：Gemini 赋能 AR 眼镜的最后一公里","google-ai-glasses-gemini-ar-last-mile","2026-05-23T01:01:00+00:00",{"id":44,"title":45,"news_slug":46,"published_at":47},"3321f474-dc0d-45ab-adc7-33aed4d1b4d3","Google Home接入Gemini 3.1：复合指令终于能一口气执行了","google-home-gemini-3-1-compound-instructions","2026-05-05T17:00:00+00:00",{"id":49,"title":50,"news_slug":51,"published_at":52},"34edaffc-6b5c-4df1-9e2f-d864cada6063","Gemini 走进 K-12 课堂：Google 把「上下文」塞进每个作业","gemini-classroom-k12-contextualized-prompts","2026-08-07T02:00:00+00:00",{"id":54,"title":55,"news_slug":56,"published_at":57},"5f13a7dd-c990-4899-97dd-e805f1c44d1a","卫星图鉴伪成本从 6 步变成 1 句话:Google Earth 信任崩塌的真正代价","google-earth-nano-banana-trust-collapse","2026-08-02T04:00:00+00:00",{"id":59,"title":60,"news_slug":61,"published_at":62},"bfe8b26d-c234-4dc6-b1be-6206552803d8","Google Earth 上线 Nano Banana 2 当天撤回:SynthID 为什么救不了这张\"假卫星图\"?","google-earth-nano-banana-retraction-osint","2026-08-02T03:00:00+00:00",{"id":64,"title":65,"news_slug":66,"published_at":67},"f637e5a0-5e18-4ced-9aa4-2ce5df798a9c","Gemini 接管 Chrome 漏洞流水线:1072 个 bug、13 年陈年沙箱逃逸,LLM 重塑浏览器安全","gemini-chrome-vulnerability-pipeline","2026-07-31T10:00:00+00:00"]