The Last Museum: Semantic search across 5.8M artworks from major museums
Summary
The Last Museum 是一个可对全球主要博物馆的 580 万件（更新数据约 630 万件）艺术品进行语义搜索的工具，让公众通过自然语言检索海量艺术藏品。
View Cached Full Text
Cached at: 10/22/26, 03:56 PM
Similar Articles
I shipped a multimodal semantic search over 68k artworks. Modal + L40S + Qwen3-VL-Embedding
A developer built a multimodal semantic search over 68k artworks from the National Gallery of Art using Qwen3-VL-Embedding, FAISS, Modal, and Cloudflare R2. The system achieves warm response times of ~1.3s and cold starts of ~44s, supporting both text-to-image and image-to-image queries.
@MaximeRivest: This 2.2 days estimate was optimistic, we are still going! despite that, you can already try giving semantic search to …
Maxime Rivest 介绍了一个可直接供 AI agent 调用的语义搜索 API，覆盖 2008 年至今的科学文献，只需发出 GET 请求即可获得检索结果。目前仍是 demo 版本，呼吁开发者试用并反馈改进建议。
@MaximeRivest: I have embedded ALL of Science and made it available for free, so your agents can now do semantic search over the whole…
Maxime Rivest 发布了 ScienceMadeReadable：一个免费、开源的科学文献语义搜索 API，覆盖约 2 亿篇论文，可直接被 AI 代理调用，无需密钥或注册，嵌入由 LightOn 的 DenseOn 模型驱动。
@AdrianPunk115: The perfect fusion of traditional aesthetics and modern technology, this AI wave is a major win. Sac rocks.
At the invitation of Xiaohongshu's official team, collaborated with Sichuan Museum to produce a digital handbook showcasing classic artifacts. Leveraging AI technologies such as page-turning animations and 3D particle effects, it delivers an immersive Chinese cultural experience.
@svpino: 32 million records searched in 30 milliseconds. That's absurdly fast. Search performance is one of those things you hav…
Sergio Pineiro 惊叹某开源搜索工具能在 30 毫秒内检索 3200 万条记录，性能极其惊人，并且设置简单、支持模糊搜索、向量搜索和语义搜索。