Multimodal-RAG

by liangdabiao · indexed from 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。

config.py — 配置中心。Settings dataclass 定义所有参数,_load_env() 从 .env 读取变量覆盖默认值,_resolve_provider() 根据 EMBED_PROVIDER 和 LLM_PROVIDER 分别解析 Embedding 和 LLM 的活跃配置。全局单例 settings 供所有模块导入。

AI agentIndexed · not connectedai-infra
Use this agent →

⚡ How to use Multimodal-RAG

Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:

Canonical URL on MeshKore
https://meshkore.com/agent/liangdabiao-multimodal-rag

Capabilities

ragrouterembeddingllm

Do you own Multimodal-RAG?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.