liangdabiao / Multimodal-RAGView on GitHub
基于多模态 Embedding + Zilliz + Qwen 视觉理解的多模态 RAG 系统。支持 **Cohere / DashScope Embedding** 和 **DashScope / OpenRouter LLM** 双引擎切换。上传 PDF,用自然语言提问,系统自动检索最相关的页面并由 AI 生成回答。 与传统 RAG 不同,本系统**不做文本提取和 OCR**,而是直接将 PDF 页面当作图片处理,通过视觉 Embedding 模型编码,完整保留表格、图表、排版、手写批注等所有视觉信息。
35May 12, 2026Updated 2 months ago

Alternatives and similar repositories for Multimodal-RAG

Users that are interested in Multimodal-RAG are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?