4. Voice RAG Agent Learn how to build a real-time Voice RAG Agent, step-by-step. Check this out: https://
github.com/patchy631/ai-e
ngineering-hub/tree/main/rag-voice-agent
…
CODE
-
Building a Real-Time Voice RAG Agent Step-by-Step
By
–
-
Building a 100% Local Deep Research Tool with MCP
By
–
5. MCP-powered deep researcher Learn how you can build a 100% local deep research. Repo → https://
github.com/patchy631/ai-e
ngineering-hub/tree/main/Multi-Agent-deep-researcher-mcp-windows-linux
… -
Building Video RAG with MCP for Interactive Video Chat
By
–
2. MCP-powered RAG over videos Learn how to build a video RAG that ingests a video and lets you chat with it. It also fetches the exact video chunk where an event occurred. Check this out: https://
github.com/patchy631/ai-e
ngineering-hub/tree/main/mcp-video-rag
… -
Local Multimodal RAG with DeepSeek Janus-Pro for Complex Documents
By
–
3. Mumtimodal RAG Build a 100% local RAG over complex real-world docs with images, tables, text, and complex layouts. Powered by DeepSeek Janus-Pro. Check this out: https://
github.com/patchy631/ai-e
ngineering-hub/tree/main/deepseek-multimodal-RAG
… -
Building Agentic RAG Pipelines with Dynamic Context Retrieval
By
–
1. Agentic RAG Build a RAG pipeline with agentic capabilities that can dynamically fetch context from different sources, like a vector DB and the internet. Check this out: https://
github.com/patchy631/ai-e
ngineering-hub/tree/main/agentic_rag
… -
Free LLM 101 Course: Essential AI Foundation for Coders
By
–
Excited to release the first video lesson of our new course FOR FREE: LLM 101: The LLM/AI Foundation Every Coder Needs to Know! TL;DR: A 2-hour session covering the "foundational theory" (the thing we believe you need to know, not the math or how parallelization is engineered)
-
Google Gemini API Launches Caching Feature for Developers
By
–
Learn more about caching in the Gemini API: https://
ai.google.dev/gemini-api/doc
s/caching
… and big shoutout to the folks across our infra, serving, API, and product teams for landing this! -
True AI Researchers Show Commitment Through Code and Experiments
By
–
My favorite thing an old OpenAI buddy of mine told me is, whenever he hears that someone is a “great AI researcher”, he just directly spends 5 minutes looking at that person‘s PRs and wandb runs. People can do all kinds of politics and optical shenanigans, but at the end of the day code and experiments don't lie. I checked out some of the diehard AI researchers and there are very few days where they haven’t launched an experiment
→ View original post on X — @_jasonwei, 2025-06-21 20:37 UTC
