开源多模态语义搜索
1 分•作者: itstomo•5 个月前
我开发了一个多模态语义搜索（RAG）框架，它协调了 MongoDB、Pinecone、S3 存储桶、LLM API 等。<p>如果你对“语义搜索”不太熟悉，可以把它理解为 RAG。<p>为了实现对文本、图像等内容的语义搜索，我们需要在将数据发送到数据库之前对其进行预处理。<p>我的框架充当你的应用程序和现有数据库之间的中间层，所有处理都在这里进行。<p>它的主要区别在于其兼容 MongoDB 的 NoSQL 接口：你与这个 RAG 引擎的交互方式与使用 MongoDB 完全相同，同时还能受益于强大的向量搜索和文档增强功能。<p>它是开源的：https://github.com/onenodehq/onenode
查看原文
I've developed a framework for multimodal semantic search (RAG), which orchestrates MongoDB, Pinecone, S3 bucket, LLM API, etc.<p>If you are not too familiar with "semantic search," think of it as RAG.<p>To enable semantic search for text, image, etc, we need to pre-process our data before sending it to the database.<p>My framework works as a middle layer between your app and existing databases, where all the processings happen.<p>The key differentiator is its MongoDB-compatible NoSQL interface: you interact with this RAG engine exactly as you would with MongoDB, while benefiting from powerful vector search and document-augmentation capabilities.<p>It's open source: https://github.com/onenodehq/onenode