OPEN SOURCE

–

23 February 2025 22h00

GenAI Agents Hub A comprehensive collection of GenAI agent implementations, from simple bots to complex multi-agent systems. Built with LangChain and LangGraph, this repository empowers developers across business and creative applications. Start building your agents:

Tool Ahead of Time: JSON-based Tool Calling for LangChain

By

–

23 February 2025 21h00

Tool Ahead of Time An interesting community package – using JSON generation & parsing to enable tool calling for LangChain models that don't currently support it. Enables usage with `create_react_agent` Check it out

→ View original post on X — @soumithchintala

TorchInductor Dynamic Kernel Generation Advances Tensor Compilation

By

@soumithchintala

–

23 February 2025 20h57

TorchInductor supports dynamic kernel generation, and is likely the state of the art at symbolic Tensor type systems. long gone are the days of static shape tensor compilers

→ View original post on X — @rasbt

Choose Your Own Adventure: Building LLMs with JAX

By

@rasbt

–

23 February 2025 20h56

You probably could choose your own adventure! . Eg @_nerdai_ coded the first book in Jax https://
github.com/nerdai/llms-fr
om-scratch-rs
…).

→ View original post on X — @rasbt

2025 LLM Roadmap: From Fundamentals to Production Applications

By

@rasbt

–

23 February 2025 20h41

Here’s the 2025 LLM roadmap 1. Code and train your own LLM to really understand the fundamentals
2. Train models more conveniently using production-ready libraries
3. Learn about the big-picture considerations for real-world LLM/AI apps

Embedding Fine-Tuning Guide for RAG Systems

By

–

23 February 2025 20h00

RAG Embedding Fine-Tuning Guide A practical guide demonstrating embedding model fine-tuning for RAG systems, featuring LangSmith monitoring and RAGAS metrics for performance evaluation. Check out the complete implementation https://
github.com/apatti/AIEBoot
camp/blob/main/09_Finetuning_Embeddings/Fine_tuning_Embedding_Models_for_RAG_using_RAGAS.ipynb
…

→ View original post on X — @soumithchintala

PyTorch Democratizes Fast Kernel Writing Challenge

By

@soumithchintala

–

23 February 2025 19h23

we've been working on democratizing fast kernel writing on the @PyTorch team. try the challenge, either you or your AI!

Building IntelliJ AI Assistant with Deepseek and LangChain

By

–

23 February 2025 18h00

IntelliJ AI Assistant Plugin Learn to build a coding assistant that integrates Deepseek AI into IntelliJ IDEA using LangChain. The plugin generates code and explains it in real-time, featuring Java Plugin DevKit and native IDE integration. Watch the tutorial now