agentic-rag
OfficialAutonomous RAG that decides when to retrieve.
Authorzilliztech
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Agentic RAG enables an AI to autonomously decide when to search, what to search for, and whether it needs more information, enabling dynamic, multi-step reasoning over a knowledge base.
Core Features & Use Cases
- Decision-driven retrieval: The agent determines when retrieval adds value and initiates searches accordingly.
- Multi-step reasoning with tools: Orchestrates THINK/ACT/OBSERVE loops to refine results across complex queries.
- Adaptive conversation: Supports on-demand searches within multi-turn dialogues and knowledge-base exploration.
Quick Start
Use the agentic-rag skill to enable a conversational assistant that decides when to search for factual information, e.g., "What is our policy on refunds?" while engaging in a multi-turn Q&A.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agentic-rag Download link: https://github.com/zilliztech/milvus-marketplace/archive/main.zip#agentic-rag Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.