@Ryrenz: Guys, I found another gem of a course: Build a Production-Grade RAG System from Scratch in 7 Weeks — 7.7k stars on GitHub, hands-on coding throughout, not a slides-only course. Most RAG tutorials out there jump straight to vector search; the demo works but crashes in production. This course follows the real path used in companies...

X AI KOLs Timeline Tools

Summary

A 7-week course with 7.7k stars on GitHub, building a production-grade RAG system from scratch, covering Docker, FastAPI, hybrid search, LangGraph agentic RAG, and a Telegram bot, with hands-on coding throughout.

Guys, I found another gem of a course: Build a Production-Grade RAG System from Scratch in 7 Weeks 7.7k stars on GitHub, hands-on coding throughout, not a slides-only course Most RAG tutorials out there jump straight to vector search; the demo works but crashes in production. This course follows the real path used in companies: In the first week, set up the infrastructure with Docker, FastAPI, PostgreSQL, OpenSearch, and Airflow, then honestly implement BM25 keyword retrieval, layer on semantic vectors for hybrid search, and finally use LangGraph for agentic RAG, plus a Telegram bot for quick questions. The output after completing the course is not a demo — it's a complete system that automatically fetches arXiv papers and answers research questions. The fastest way to learn RAG is to build it completely from scratch. GitHub:
Original Article
View Cached Full Text

Cached at: 07/15/26, 03:58 PM

A Learner-Focused Journey into Production RAG Systems

Learn to build modern AI systems from the ground up through hands-on implementation

Master the most in-demand AI engineering skills: RAG (Retrieval-Augmented Generation)

Complete Week 7 architecture showing Telegram bot integration with the agentic RAG system

Detailed LangGraph workflow showing decision nodes, document grading, and adaptive retrieval

🎉 Ready to Start Your AI Engineering Journey?

Begin with the Week 1 setup notebook and build your first production RAG system!

For learners who want to master modern AI engineering

Built with love by Shirin Khosravi Jam & Shantanu Ladhwe

Similar Articles

@mate_mattt: I built a real, runnable RAG project and a Notebook RAG practical course, breaking down RAG pixel by pixel: Markdown chunking → FTS5 / BM25 → Embedding vector search → Hybrid recall RRF → Cross-Encod…

X AI KOLs Timeline

This is a hands-on project for learning local RAG retrieval core from scratch, including Notebook and real runnable code. It covers the complete workflow: Markdown chunking, BM25, Embedding vector search, hybrid recall RRF, Cross-Encoder re-ranking, and comes with evaluation metrics.

jamwithai/production-agentic-rag-course

GitHub Trending (daily)

A learner-focused hands-on course that teaches building production-grade RAG systems from scratch, covering keyword search, hybrid retrieval, agentic RAG with LangGraph, and Telegram bot integration.

@axichuhai: Hey everyone, I've found another GitHub treasure open-source project — hello-agents has shot straight to the top of the GitHub trending list and is still climbing! It systematically organizes AI and Agent from theory to practice into an open-source curriculum, covering Agentic RL, SFT, …

X AI KOLs Timeline

Discovered an open-source GitHub project hello-agents, which organizes a complete open-source course from theory to practice on AI Agents, covering core skills like Agentic RL, SFT, GRPO, and has reached the top of GitHub trending.

@sitinme: GitHub 30k stars, do RAG without vector databases and with higher accuracy! Anyone doing RAG has probably experienced this: the vector database returns content that "looks relevant" but isn't the answer you're looking for. Especially with long documents like contracts, financial reports, technical manuals, when you ask "What was Q3 revenue?", it returns a paragraph about "company business overview." Similarity ≠ relevance—this is the fundamental problem with vector retrieval. PageIndex's solution is straightforward and brute-force: skip vectors, use reasoning.

X AI KOLs Timeline

Introduces an open-source project with 30k stars on GitHub that achieves RAG through reasoning instead of vector databases, claiming higher accuracy and solving the problem of similarity not equating to relevance.