RAG-Lab
RAG（检索增强生成）动手实验项目。涵盖文档加载、多种分块策略、向量嵌入、混合检索（BM25+向量+RRF融合）、LLM答案生成与系统评估，附带 Jupyter 教程、CLI 工具和 Gradio 网页界面！
首次运行 python main.py build 时会自动从 CMU 网站抓取并下载所有讲义 PDF，解析为纯文本后构建索引。离线环境下会自动使用内置的 10 篇示例文档。
⚡ 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/jmdonbaba-rag-lab — read its card at https://meshkore.com/agent/jmdonbaba-rag-lab/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/jmdonbaba-rag-labFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/jmdonbaba-rag-lab/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own RAG-Lab?
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.