GenAI

Memory

— Jo Kristian Bergum (@jobergum)

What do apps look like when you design AI first? Starting a thread to collect some examples I've found. — Lee Robinson (@leeerob)

Explore the capabilities of AI Agents and their real-world applications. CrewAI showcases the power and versatility of AI technologies across various sectors.

[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025) - chiphuyen/aie-book

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

See how AppFolio's AI-powered copilot Realm-X has saved property managers over 10 hours per week. Learn how they improved Realm-X's performance 2x using LangSmith and built an agent architecture with LangGraph.

Neo4j’s LLM Graph Builder is an app for automatically constructing knowledge graphs from unstructured data sources. It can be run locally…

Graphs are ubiquitous data structures found in numerous real-world applications, such as drug discovery, recommender systems, and social network analysis. Graph neural networks (GNNs) have become...

Evaluating the quality of outputs from Large Language Models (LLMs) is an intricate task due to the open-ended nature of many LLM tasks…

I made a tutorial showing you how to build a contract review agentic workflow - given a vendor agreement, parse it into a set of key clauses, match it with relevant clauses from a set of guidelines (GDPR),… — Jerry Liu (@jerryjliu0)

A new tool that blends your everyday work apps into one. It's the all-in-one workspace for you and your team

This blog post presents a new modular workflow for converting PDFs and similar documents to structured data and shows you how to build end-to-end document understanding and information extraction pipelines for industry use cases.

Counting tokens is a useful task in natural language processing (NLP) that allows us to measure the length and complexity of a text. The two important use cases for counting the tokens are: controlling the length of the prompt - models has limit …

Here’s a cheat sheet of 7 of the most popular RAG architectures. Which variants did we miss? — Weaviate • vector database (@weaviate_io)

A question-based extraction approach

Awesome guide with templates

Presents MAG-V, a multi-agent framework that first generates a dataset of questions that mimic customer queries. It then reverse engineer alternate questions from responses to verify agent trajectories. Reports that the… — elvis (@omarsar0)

The whole point is to not let the agent do everything, but to do a… — Jerry Liu (@jerryjliu0)

— Pedro Domingos (@pmddomingos)

List of solutions

User profile of Nathanael on Hugging Face

This study provides an efficient approach for using text data to calculate patent-to-patent (p2p) technological similarity, and presents a hybrid framework for leveraging the resulting p2p...

Various studies have focused on feature extraction methods for automatic patent classification in recent years. However, most of these approaches are based on the knowledge from experts in related domains. Here we propose a hierarchical feature extraction model (HFEM) for multi-label mechanical patent classification, which is able to capture both local features of phrases as well as global and temporal semantics. First, a n-gram feature extractor based on convolutional neural networks (CNNs) is designed to extract salient local lexical-level features. Next, a long dependency feature extraction model based on the bidirectional long–short-term memory (BiLSTM) neural network model is proposed to capture sequential correlations from higher-level sequence representations. Then the HFEM algorithm and its hierarchical feature extraction architecture are detailed. We establish the training, validation and test datasets, containing 72,532, 18,133, and 2679 mechanical patent documents, respectively, and then check the performance of HFEMs. Finally, we compared the results of the proposed HFEM and three other single neural network models, namely CNN, long–short-term memory (LSTM), and BiLSTM. The experimental results indicate that our proposed HFEM outperforms the other compared models in both precision and recall.

Learn important prompt engineering techniques to build use cases with LLMs.