GenAI

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps. - TencentQQGYLab/AppAgent

Weights & Biases, developer tools for machine learning

After completing our multi-turn tokenization and masking refactoring, we eliminated a critical bottleneck that was preventing us from building a more consistent and flexible rollout system for our Agent RL research. This breakthrough enabled us to implement a LangGraph-based rollout for VeRL in just a few days, which we’ve already successfully deployed in our Agent RL experiments. In this article, I’ll share our journey from VeRL’s native multi-turn implementation to our new LangGraph-based solution, explaining both the motivations driving this evolution and the technical details of our implementation.

LlamaIndex is a simple, flexible framework for building knowledge assistants using LLMs connected to your enterprise data.

Context Engineering Guide By DAIR.AI Academy Table of Contents What is Context Engineering? Context Engineering is Action System Prompt Instructions User Input Structured Inputs and Outputs Tool Calling RAG & Memory State & Historical Context Advanced Context Engineering Resources What is Co...

Fall 2024

From BM25 to RAG: Everything I learned about vector databases, embedding models, and vector search - and everything in between.

A Blog post by Sara Han Díaz on Hugging Face

Context Engineering is the new skill in AI. It is about providing the right information and tools, in the right format, at the right time.

TL;DR Agents need context to perform tasks. Context engineering is the art and science of filling the context window with just the right information at each step of an agent’s trajectory. In this post, we break down some common strategies — write, select, compress, and isolate — for context engineering

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

See how Exa used LangGraph and LangSmith to build a multi-agent web research system to process research queries

A deep dive into the methods, fine-tuning pipeline, and operational risks of building specialised models.

OpenAI self-leaked its Deep Research prompts and it's a goldmine of ideas! Let's analyze this in detail!

📦 Package Links & Code Examples:- 🐍 PyPI: https://pypi.org/project/graph_nd/- 📁 GitHub: https://github.com/zach-blumenfeld/graph-nd- 📚 Docs: https://grap...

Extract and generate a knowledge graph from educational curriculum information without writing a single line of code.

Created with Figma

Evaluation metrics, how to build eval datasets, eval methodology, and a review of several benchmarks.

Weaviate `1.31` implements the MUVERA encoding algorithm for multi-vector embeddings. In this blog, we dive the algorithm in detail, including what MUVERA is, how it works, and whether it might make sense for you.

This repository shares end-to-end notebooks on how to use various Weaviate features and integrations! - weaviate/recipes

This study critically distinguishes between AI Agents and Agentic AI, offering a structured conceptual taxonomy, application mapping, and challenge analysis to clarify their divergent design...

Best practices for LoRA hyperparameters and how they affect the fine-tuning process.

In-depth tutorials on LLMs, RAGs and real-world AI agent applications. - patchy631/ai-engineering-hub

Fully functional agentic deep research app with step-by-step instructions (100% opensource)

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Step-by-step guide to fine-tuning the Mistral reasoning model on a medical MCQs dataset using the Transformers framework.

The crucial layers of infrastructure that make up a production grade Agentic AI system.

I rewrote my "tech writer" agent in 7 frameworks: Agno, Autogen, Google ADK, Atomic Agents, DSPy, Langgraph, and Pydantic AI. You'll NEVER guess the winners.

To fine-tune a Sentence Transformer using triplet or contrastive loss, follow these steps: prepare data in the required