Red Hat Summit logo AnsibleFest logo
Agentic AI in Red Hat AI!
You are userX
Links
OpenShift AI Dashboard OpenShift Console

Navigation

    • 1. Background
      • 1.1 Setting the stage
      • 1.2 Current Process
      • 1.3 Proposed Improvements
      • 1.4 Examples from prototype
      • 1.5 Preparing Environment and Next Steps
    • 2. Agentic AI Overview
      • 2.1 What is an LLM?
      • 2.2 What are the limitations of LLMs?
      • 2.3 What is Agentic AI?
      • 2.3 Why is it important to my organization?
    • 3. Advance LLM Patterns
      • 4.1 Non-Agentic Patterns
      • 4.2 Tools Usage from LLM Perspective
      • 4.3 Chain of Thought
      • 4.4 React Prompting
      • 4.5 Retrieval Augmented Generation (RAG)
    • 4. Agentic AI Frameworks
      • 3.1 AI Agents Frameworks
      • 3.2 LangGraph
      • 3.3 AutoGen Framework
      • 3.4 CrewAI
      • 3.5 LlamaIndex
      • 3.6 Bee
    • 5. Agentic-AI-Based Integrations
      • 5.1 What is an AI Agent?
      • 5.2 Agentic Architectures
      • 5.3 Agentic Routing
      • 5.4 Tool-Calling Agents
      • 5.5 SQL Retriever Agents
      • 5.6 ReAct Implementation
      • 5.6 Deploying Agents From Notebook to Production
    • 6. Advanced Agentic AI
      • 6.1 Multi-Agent Collaboration
      • 6.2 Building Supervisors
      • 6.3 Human in the Loop
      • 6.4 Planning Agents
      • 6.5 Reflection Agents
    • 7. Enhance RAG with Agentic AI
      • 7.1 Agentic RAG
      • 7.2 Self RAG
    • 8. End of Lab
      • 8.1 Thanks
  • Navigation
    • default
  • 5. Agentic-AI-Based Integrations
  • 5.6 Deploying Agents From Notebook to Production
Edit this Page

Deploying Agents from Notebook to Production

TBD

5.6 ReAct Implementation 6.1 Multi-Agent Collaboration

Powered by

Demo Platform