NFO
Mimir, Keeper of the Well of Wisdom
Advanced RAG: Build & Deploy Production GenAI Apps
https://www.udemy.com/course/advanced-rag-build-deploy-
production-genai-apps/
Year : 2026
Language : English
Level : Intermediate Level
Category : IT & Software
Subcategory : Other IT & Software
Duration : 11h 0m
Lectures : 114
Rating : 4.8/5 (43 reviews)
Students : 314
INSTRUCTOR(S)
HEADLINE
Multi-Agent RAG, CrewAI, AutoGen, Microsoft Agent Framework,
RAG, Langchain, Deep RAG, Production RAG, RAGWire
WHAT YOU'LL LEARN
* Build a production RAG pipeline with BM25 hybrid search, RRF
fusion, and Qdrant vector database
* Build agentic RAG systems with LangChain, LangGraph self-
correcting agents, and supervisor workflows
* Build multi-agent RAG with CrewAI, Microsoft AutoGen, and
Microsoft Agent Framework
* Deploy RAG agents to AWS ECS Fargate, GCP Cloud Run, Azure,
Railway, and Render with Docker
* Build a FastAPI backend with OpenAI-compatible endpoints,
SSE
streaming, and Postman testing
* Build a production Chainlit chat UI with authentication,
chat
history, and document ingestion
* Configure RAGWire with OpenAI GPT, Groq, Google Gemini,
Ollama, and HuggingFace embeddings
* Implement LLM-driven auto metadata filtering over complex
nested document structures in Qdrant
REQUIREMENTS
* Basic Python programming knowledge (functions, classes, pip)
* Familiarity with REST APIs and using a terminal or command
line
* Basic understanding of Gen AI and Langchain concepts
WHO IS THIS COURSE FOR
* Python developers who want to build production-grade RAG
systems beyond basic tutorials
* ML engineers looking to deploy LangChain and LangGraph
agents
to AWS, GCP, or Azure
* Developers who want hands-on experience with LangGraph,
AutoGen, and CrewAI
* Backend developers who want to build OpenAI-compatible
FastAPI
endpoints for AI applications
* AI engineers who want hands-on experience with CrewAI,
AutoGen, and multi-agent frameworks
* Anyone building document search, enterprise AI assistants,
or
agentic RAG applications
DESCRIPTION
Retrieval-Augmented Generation (RAG) is at the core of every
serious AI application today. But basic RAG pipelines quickly
hit their limits when documents are large, queries are
complex,
or your application needs to run reliably in production. In
this
course, you will build RAGWire ? a production-grade RAG
toolkit
built on LangChain, Qdrant, and LangGraph ? from the ground
up.
You will start with a simple hybrid search pipeline and
progressively add advanced retrieval, metadata filtering,
agentic RAG, multi-agent frameworks, a full chat UI, and
multi-
cloud deployment. By the end of this course you will know how
to: Build a hybrid RAG pipeline with BM25 sparse + dense
retrieval and Reciprocal Rank Fusion (RRF) Configure RAGWire
with OpenAI GPT, Groq, Google Gemini, Ollama, and HuggingFace
embeddings Implement LLM-driven auto metadata filtering over
complex, nested document structures Build agentic RAG
pipelines
with LangChain agent tools, memory, and reasoning Build a
self-
correcting RAG agent that grades its own retrieval and
rewrites
queries when quality is low Build supervisor multi-agent
systems
that route queries to specialist agents using LangGraph Build
multi-agent document analysts with CrewAI, Microsoft AutoGen,
and Microsoft Agent Framework Build a production Chainlit chat
UI with authentication, chat history, and document upload
Build
a FastAPI backend with OpenAI-compatible /v1/chat/completions
endpoints and SSE streaming Deploy RAG agents to Render,
Railway, AWS ECS Fargate, GCP Cloud Run, and Azure Secure
production APIs with API keys and protect credentials with
Docker .dockerignore This is a hands-on, code-first course.
Every section produces working, runnable code that you can
adapt
to your own documents and use cases.
COURSE CONTENT
Chapter 1: Introduction
1. Introduction
2. What You Will Learn in This Course!
3. Download Code Files
4. Getting Started with The Course
5. Environment Setup - PIP, UV, Anaconda and
Requirements.txt
6. LangSmith Setup: Debug LangChain RAG Pipelines
7. Install Docker and Qdrant Vector DB Locally
8. Ollama Setup: Run Qwen 3.5 and Gemma 4 Locally
Chapter 2: Introduction to RAGWire RAG Framework
9. RAGWire Preview: Hybrid Search RAG in Production
10. RAGWire: Open-Source Production RAG Toolkit Explained
11. RAGWire Query Pipeline: Dense + Sparse Search with RRF
12. RAGWire End-to-End: Ingestion, Retrieval and Reranking
Chapter 3: RAGWire RAG Setup and First Retrieval
13. RAGWire Setup Overview: What You Will Build
14. RAGWire Installation: Python Environment Setup
15. config.yaml Part 1: Embedding Model Configuration
16. config.yaml Part 2: Qdrant and Retrieval Settings
17. config.yaml Part 3: LLM and Generation Settings
18. Run RAGWire Locally with Ollama and Qwen 3.5
19. RAGWire Jupyter Notebook: Interactive Dev Environment
20. Connect RAGWire to Qdrant Vector Database via Config
21. Document Ingestion: Chunking and Indexing into Qdrant
22. Advanced Ingestion: SHA-256 Dedup and Metadata
23. First Hybrid Search: BM25 + Dense Retrieval with Qdrant
Chapter 4: Advanced Retrieval, Metadata Filtering and Agentic
RAG
24. Advanced RAG Overview: Metadata Filtering and Agents
25. Batch Document Ingestion from a Directory with RAGWire
26. Custom Metadata Schema for Richer Document Extraction
27. Explore RAGWire APIs and Metadata for Hybrid Search
28. Hybrid Search with Manual Metadata Filtering in Qdrant
29. Hybrid Search over Complex Nested Data Structures
30. LLM-Driven Auto Metadata Filtering in Hybrid SearchLLM-
Driven Auto Metadata Filt
31. Agentic RAG Explained: Tools, Memory and Reasoning
32. Build a Simple Agentic RAG with LangChain and RAGWire
33. Filter Context Extraction for Better RAG Retrieval
34. Filter-Aware Agentic RAG: LLM-Guided Hybrid Retrieval
Chapter 5: RAGWire RAG with OpenAI, Groq, Gemini and Cloud
Qdrant
35. RAGWire Multi-Provider Overview: OpenAI, Groq, Gemini
36. RAGWire: Multi-Provider LLM and Embedding Setup
37. OpenAI: RAGWire Setup with GPT and OpenAI Embeddings
38. OpenAI: Hybrid Search and Batch Ingestion with GPT
39. Groq: RAGWire Setup for Fast LLM Inference
40. Groq: Hybrid Search with HuggingFace Embeddings
41. Gemini: RAGWire Setup with Google Gemini Embeddings
42. Gemini: Hybrid Search and Document Ingestion
43. Qdrant Cloud: Free Vector DB for RAG Ingestion
44. Qdrant Cloud: Agentic RAG with Google Gemini
Chapter 6: Real-World RAG: Gym Supplements Use Case with
Agentic RAG
45. Real-World RAG Project: Gym Supplements Use Case
46. RAG Config and Metadata Setup for Gym Supplements Data
47. Ingest Health Research Papers and Run Hybrid Search
48. Agentic RAG for Gym Supplements: End-to-End Project
Chapter 7: Production RAG Chat UI with Chainlit and RAGWire
49. Chainlit RAG Chat UI: Section Overview
50. Chainlit Intro: Build a Production-Ready RAG Chat UI
51. Add LangChain Agent Tools to a Chainlit RAG App
52. Chainlit on_chat_start: RAG Agent Initialization
53. Integrate Agentic RAG with Chainlit Chat Interface
54. Chat with RAG Agent via Production Chainlit UI
55. Document Ingestion via Chainlit Chat UI Part 1
56. Document Ingestion via Chainlit Chat UI Part 2
57. Upload Documents and Chat with RAGWire via Chainlit
Chapter 8: FastAPI RAG Backend with OpenAI-Compatible
Endpoints
58. FastAPI RAG Backend: Section Overview
59. Multi-Agent RAG: FastAPI Backend and Chainlit Frontend
60. OpenAI-Compatible FastAPI Endpoints Explained Part 1
61. OpenAI-Compatible FastAPI Endpoints Explained Part 2
62. LangChain Agent Setup for FastAPI RAG Endpoints
63. SSE Streaming: LangChain Agent as OpenAI Endpoint
64. Build OpenAI-Compatible RAG Endpoints with FastAPI
65. Test FastAPI RAG Agent Endpoints with Postman
66. Chainlit Auth and Chat History: RAG App Setup Part 1
67. Chainlit Auth and Chat History: RAG App Setup Part 2
68. End-to-End Testing: RAG Agent and Chainlit Chat App
69. Chainlit Chat App Response Correction
Chapter 9: Multi-Agent RAG: LangGraph, CrewAI, AutoGen and
Microsoft
70. Multi-Agent RAG Overview: LangGraph, CrewAI, AutoGen
71. LangGraph Self-Correcting RAG: How It Works
72. LangGraph RAG Nodes: Write, Retrieve and Generate
73. LangGraph Self-Correcting RAG: End-to-End Testing
74. LangGraph Self-Correcting RAG: End-to-End Testing
75. LangGraph Supervisor Multi-Agent: How It Works
76. LangGraph: Build a Supervisor Multi-Agent Workflow
77. LangGraph Supervisor Workflow: End-to-End Testing
78. search_documents Tool Correction [IMP]
79. CrewAI Document Assistant RAG Agent Explained
80. CrewAI: Build a Document Assistant RAG Agent
81. CrewAI: Build a Multi-Agent Document Analyst
82. CrewAI Multi-Agent Document Analyst: E2E Testing
83. Microsoft AutoGen Multi-Agent System Explained
84. Microsoft AutoGen: Gemini Model Client Setup
85. Microsoft AutoGen: Build a Research Collaboration Team
86. Microsoft Agent Framework: Build Your First RAG Agent
87. Microsoft Agent Framework: How Multi-Agent Workflow
Works
88. Microsoft Agent Framework: Task Specialist Agents
89. Microsoft Agent Framework: Aggregate Specialist
Responses
90. Microsoft Agent Framework: End-to-End RAG Testing
Chapter 10: Deploy RAG Agent (AI App) to Production with
Docker and Render
91. Production Deployment Overview: Docker and Render
92. GitHub Repo Setup for Production RAG Agent Deployment
93. Dockerize Your RAG App: Create a Docker Container
94. Build and Inspect a Docker Image Locally for RAG
95. Docker .dockerignore: Prevent Credential Leaks in Prod
96. Deploy RAG Agent to Render: Cloud Deployment Guide
97. Test Chat Completion API on Deployed RAG Agent
98. Chat with Your Live RAG App on Render
99. Secure RAG API with API Key: Production Best Practices
100. Access Secured RAG API Endpoints with API Key
101. Chainlit: Secure API Key Access for RAG Endpoints
Chapter 11: Deploy RAG Agent on Railway, AWS ECS, GCP and
Azure
102. Cloud Deployment Overview: Railway, AWS, GCP and Azure
103. Railway: Deploy RAG Agent App to Production
104. Railway: Test RAG App with Chainlit Chat UI
105. AWS ECS and Fargate: Setup for RAG App Deployment
106. AWS ECR: Build and Push RAG App Docker Image
107. AWS ECS: Deploy RAG Agent App with Express Mode
108. AWS ECS: End-to-End Testing of Deployed RAG Agent
109. AWS ECS: Swap RAG Agent via Environment Variables
110. GCP: Configure Cloud CLI for RAG App Deployment
111. GCP Cloud Run: Deploy RAG Agent to Production
112. GCP Cloud Run: Chat with Your Deployed RAG Agent
113. Azure: Configure CLI for RAG Agent Deployment
114. Azure: Build and Deploy RAG Agent App to Production
DATES
Published : 2026-04-16
Last Updated : 2026-04-16
If you fear the truth, dont come to my well.
CRC32: 23dbdaf13d2840c19b549f76271ed77314e5f51e