Google has expanded its Gemini API File Search tool to support multimodal RAG systems, allowing developers to process both text and visual data. This update, powered by the Gemini Embedding 2 model, enables more context-aware agents and offers custom metadata filtering for improved search accuracy and speed. Additionally, the tool now provides page citations to enhance transparency and verifiability by linking responses directly to their source documents. AI
影响 Enhances RAG system capabilities by enabling multimodal data processing and improving transparency, potentially accelerating development for AI applications.
排序理由 Product update to an existing API feature.
在 Hacker News — AI stories ≥50 points 阅读 →
AI 生成摘要 · Google Gemini · 来自 8 个来源。 我们如何撰写摘要 →