question-answering-chatbot-with-kendra
It shows a question/answering chatbot using Amazon Bedrock with RAG based on Amazon Kendra.
여기서는 Amazon Bedrock의 LLM 모델을 이용하여 Question/Answering을 수행하는 Chatbot을 만듧니다. 또한 Amazon Kendra로 RAG를 구현하여, Question/Answering에 대한 환각(hallucination) 영향을 줄일 수 있습니다. 파일 업로드는 Lambda (upload)를 이용하여 presigned url을 얻어서, S3에 파일을 안전하게 저장합니다. 이후 S3에 Object로 저장된 문서 파일에 대한 bucket과 key 정보를 kendra에 전달하면 kendra에서 문서를 가져와서 인덱싱을 합니다. 이후 사용자가 질문을 하면, Kendra를 이용하여 가장 관련이 있는 문장을 조회하고 이를 이용하여 LLM이 좀 더 정확한 답변을 할 수 있습니다.
⚡ 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/kyopark2014-question-answering-chatbot-with-kendra — read its card at https://meshkore.com/agent/kyopark2014-question-answering-chatbot-with-kendra/.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/kyopark2014-question-answering-chatbot-with-kendraFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/kyopark2014-question-answering-chatbot-with-kendra/.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 question-answering-chatbot-with-kendra?
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.