MongoDB Atlas 支持数据库内自动生成向量嵌入
Finally, a database can generate its own embeddings now.
Finally, a database can generate its own embeddings now.
终于，数据库现在可以自己生成嵌入向量了。
When you add semantic search to an app, the standard step is to wire up an external embedding service, sync the vectors to a separate store, and write glue to keep everything updated as data changes.
当你向应用添加语义搜索时，标准步骤是接入外部嵌入服务，将向量同步到单独的存储中，并编写胶水代码以在数据变化时保持一切更新。
While this is a standard setup, problems show up later when your data changes, but your pipeline has already run, and search quality starts degrading in ways that are hard to pin down because nothing is explicitly broken.
虽然这是标准设置，但问题会在之后出现：当你的数据发生变化，而你的管道已经运行完毕，搜索质量开始以难以定位的方式下降，因为没有任何东西明确损坏。
MongoDB Atlas handles this with auto-embedding.
MongoDB Atlas 通过自动嵌入处理了这个问题。
You point an index at a text field, specify a Voyage AI model, and Atlas generates the vectors inside the database.
你将索引指向一个文本字段，指定一个 Voyage AI 模型，Atlas 就会在数据库内部生成向量。
When a document changes, it re-embeds itself automatically, so that the search always stays grounded to the current context.
当文档发生变化时，它会自动重新嵌入，从而使搜索始终基于当前上下文。
I tested this against MongoDB's sample movies collection, 21,000 plots indexed with one config.
我针对 MongoDB 的示例电影集进行了测试，用一条配置索引了 21,000 个情节。
A plain English query about dystopian machine-controlled futures returned semantically relevant results, despite having no keyword overlap.
一个关于反乌托邦机器控制未来的普通英语查询返回了语义相关的结果，尽管没有关键词重叠。
You can try it yourself here: https://fandf.co/4bswaPj.
你可以在这里亲自尝试：https://fandf.co/4bswaPj。
One index config replaced the embedding service, the vector store, and the sync layer you used to maintain separately.
一个索引配置取代了嵌入服务、向量存储和同步层，而这些以前需要你单独维护。
The video below depicts this in action, and I worked with the MongoDB team to put this together.
下面的视频展示了这一过程，我与 MongoDB 团队合作制作了这段视频。
I have also put together a full LLM engineering roadmap covering what it actually takes to build and ship production AI systems in 2026.
我还整理了一份完整的 LLM 工程路线图，涵盖在 2026 年构建和交付生产级 AI 系统实际需要的内容。
Read it below.
在下面阅读。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力