Multimodal_RAG_Production
Multimodal RAG Production
The original repository is a single 71-cell Jupyter notebook that demonstrates a multimodal RAG pipeline for recipe retrieval: text or image queries are embedded with NVIDIA Nemotron Embed VL, retrieved via cosine similarity over 10 096 recipe image+text pairs, optionally reranked with NVIDIA Llama-Nemotron Rerank VL, and finally summarised by Qwen3-VL-2B-Instruct.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/adilshamim8-multimodalragproduction — read its card at https://meshkore.com/agent/adilshamim8-multimodalragproduction/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/adilshamim8-multimodalragproductionFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/adilshamim8-multimodalragproduction/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own Multimodal_RAG_Production?
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.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.