jamwithai / production-agentic-rag-course

2025-08-06 · Source: Github Trending: All languages · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Advanced, long

Summary

The "Mother of AI Project: Phase 1 RAG Systems: arXiv Paper Curator" is a comprehensive, learner-focused course designed to teach the development of production-grade Retrieval-Augmented Generation (RAG) systems. It guides participants through building an AI research assistant that fetches, understands, and answers questions from academic papers. The curriculum spans seven weeks, covering infrastructure setup with Docker, FastAPI, PostgreSQL, OpenSearch, and Airflow; automated data ingestion from arXiv using Docling; BM25 keyword search; intelligent chunking and hybrid search with Jina AI embeddings; complete RAG pipeline integration with local Ollama LLMs and a Gradio interface; production monitoring with Langfuse and Redis caching; and advanced agentic RAG with LangGraph and Telegram bot integration. The project emphasizes building a solid search foundation before adding AI enhancements.

Key takeaway

For AI/ML Engineers and Software Engineers building RAG systems, this course provides a structured, hands-on path to master production-grade implementations. You will gain practical skills in setting up robust infrastructure, optimizing search, integrating local LLMs, and deploying agentic RAG with monitoring and caching. This approach ensures you build scalable and reliable AI applications, avoiding common pitfalls of AI-first development.

Key insights

Building production RAG systems requires a solid search foundation before integrating advanced AI components.

Principles

• Prioritize keyword search fundamentals.
• Implement hybrid retrieval for robust results.
• Ensure observability and performance monitoring.

Method

The course outlines a 7-week progression: infrastructure, data ingestion, keyword search, hybrid search, LLM integration, monitoring/caching, and agentic RAG with a Telegram bot.

In practice

• Use Docker Compose for infrastructure setup.
• Integrate Langfuse for RAG pipeline tracing.
• Implement Redis for caching to optimize performance.

Topics

• Retrieval-Augmented Generation
• Agentic AI
• Hybrid Search
• Production Monitoring
• LangGraph

Code references

• jamwithai/production-agentic-rag-course
• jamwithai/arxiv-paper-curator

Best for: Machine Learning Engineer, AI Engineer, Software Engineer

Related on AIssential

• Building a Production-Ready Agentic Chatbot Course [3/30]: Designing Production-Ready RAG Pipeline — A production RAG pipeline requires a multi-stage approach beyond simple vector search to ensure reliable information retrieval.
• Stop Building “Naive RAG” — Here Are the 12 Retrieval Architectures Powering Production AI ||… — RAG is a category, not a single technique; choose architectures based on query and knowledge base characteristics.
• I Just Built an Agentic RAG System From Scratch — Here’s What I Learned — Agentic RAG systems empower LLMs to autonomously refine searches, significantly improving answer quality and efficiency.
• Expert Guide to Building RAG Systems in 2026* — RAG systems have evolved significantly, requiring advanced architectures and comprehensive optimization for future effectiveness.
• Building a Production-Ready RAG Pipeline — Only 10 Seats Left — The workshop focuses on transforming basic RAG systems into robust, production-ready pipelines through advanced techniques and system integration.
• The RAG era is ending for agentic AI — a new compilation-stage knowledge layer is what comes next — Agentic AI requires pre-compiled, task-specific knowledge artifacts, moving beyond traditional RAG's inference-time reasoning.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Github Trending: All languages.