10 MCP, AI Agents, and RAG projects for AI Engineers (with code):
Post
Post
Avi Chawla on X: "10 MCP, AI Agents, and RAG projects for AI Engineers (with code):"
1️⃣ MCP-powered Agentic RAG In this project, you'll learn how to create an MCP-powered Agentic RAG that searches a vector database and falls back to web search if needed. Check the full breakdown (with code) below👇
The media could not be played.
GIF
Let's build an MCP-powered Agentic RAG (100% local):
2️⃣ A multi-agent book writer In this project, you'll build an Agentic workflow that can write a 20k word book from a 3-5 word book title. Read the walk-through thread below👇
The media could not be played.
GIF
Let's build a multi-agent book writer, powered by DeepMind's Gemma 3 (100% local):
3️⃣ RAG over audio In this project, learn how to build a RAG system capable of ingesting & understanding audio content—think podcasts, lectures & more! Check the full breakdown (with code) below👇
The media could not be played.
GIF
Let's build a RAG app over audio files with DeepSeek-R1 (running locally):
4️⃣ RAG powered by Lllama 4 Meta recently released multilingual and multimodal open-source LLMs. Learn how to build a RAG app that's powered by Llama 4. Check the full breakdown (with code) below👇
The media could not be played.
GIF
Let's build a RAG app with Meta's latest Llama 4:
5️⃣ Multimodal RAG powered by DeepSeek Janus In this project, build a local multimodal RAG using: - Colpali to understand and embed docs. - Qdrant as the vector DB. - DeepSeek Janus as the multimodal LLM. Check the full breakdown (with code) below👇
00:35
Let's build a Multimodal RAG with DeepSeek's latest Janus-Pro (100% local):
6️⃣ A mini-ChatGPT using DeepSeek-R1 In this project, build a local mini-ChatGPT using DeepSeek-R1, Ollama, and Chainlit. You could chat with it just like you chat with ChatGPT. Check the full breakdown (with code) below👇
00:23
Let's build a mini-ChatGPT that's powered by DeepSeek-R1 (100% local):
7️⃣ Corrective RAG Corrective RAG (CRAG) is a common technique to improve RAG systems. It introduces a self-assessment step of the retrieved documents, which helps in retaining the relevance of generated responses. Learn how to build it here: github.com/patchy631/ai-e…
The media could not be played.
GIF
8️⃣ Build your reasoning model In this project, learn how to train your reasoning model like DeepSeek-R1 (check the image) using: - Unsloth for efficient fine-tuning. - Llama 3.1-8B as the LLM. Check the full breakdown (with code) below👇
Let's build our own reasoning model (like DeepSeek-R1) 100% locally:*-
9️⃣ Fine-tune DeepSeek-R1 In this project, you'll fine-tune your private and locally running DeepSeek-R1 (distilled Llama variant). Check the full breakdown (with code) below👇
🔟 Build a local MCP server MCPs are here to stay. In this project, you will: - Understand MCP with a simple analogy. - Build a local MCP server and interact with it via Cursor IDE. Check the full breakdown (with code) below👇
00:10
Let's build an MCP server (100% locally):
That's a wrap! If you enjoyed this thread: Find me →
@_avichawlaEvery day, I share tutorials and insights on DS, ML, LLMs, and RAGs.
This is a treasure trove of great tutorials! Thanks for sharing Avi! 👏
