Search AI Products and News

Neo4j has introduced a significant upgrade to its fully managed cloud graph database service AuraDB, greatly enhancing usability and data processing efficiency, achieving a 15-fold improvement in data reading capability. The upgraded version introduces a generative AI assistant that uses OpenAI’s large language model to provide real-time query optimization, explanations, and suggestions, helping users quickly extract data insights by generating Cypher query code with just natural language questions. Additionally, the new NeoDash tool allows users to operate without coding.

MathGPTPro is an advanced AI math learning tool that focuses on instant answering capabilities, supporting both image uploads and text inputs. It provides detailed solutions to math problems with a significantly higher accuracy than similar models. Its knowledge graph feature helps users track learning progress, identify strengths and areas for improvement, and achieve personalized learning. The product also includes real-time chat functionality and step-by-step guidance, making it easier to understand the problem-solving process and providing personalized learning suggestions to enhance the learning experience. It supports various input methods, including images, text, and LaTeX.

AutoAlign is an innovative knowledge graph alignment method designed to address the entity recognition challenges of different knowledge graphs. It constructs predicate proximity graphs using large language models to automatically identify similar predicates, achieving entity alignment between knowledge graphs. Without the need for manual seed alignment, it significantly enhances alignment efficiency and accuracy through predicate alignment, entity alignment, and a joint learning mechanism. In entity alignment tasks, AutoAlign outperforms existing methods and shows potential in applications such as knowledge graph completion.

How to transform chaotic data into useful information is becoming increasingly important. Recently, Neo4j introduced a brand-new tool – the Neo4j LLM Knowledge Graph Builder, which can easily convert unstructured data into structured knowledge graphs, making data processing more efficient.Product Access: https://top.aibase.com/tool/llm-graph-builder The Neo4j LLM Knowledge Graph Builder leverages a series of powerful machine learning models, including OpenAI, Gemini, Llama3, etc. Through these

Samsung Electronics has announced the acquisition of the UK-based AI startup Oxford Semantic Technologies to enhance its competitiveness in the field of artificial intelligence. Oxford Semantic Technologies is renowned for its knowledge graph technology, which is akin to human thinking, organizing data into interconnected networks for rapid information retrieval and personalized recommendations. The company's flagship product, RDFox, is hailed as one of the world's fastest knowledge graph and se

On July 10th, the AI assistant "Stellar Flow" was officially launched, designed specifically for research professionals, university faculty, and students. "Flow" aims to serve as a smart search assistant for users, offering multifunctional services including intelligent search, knowledge Q&A, smart reading, and creative assistance, with the goal of enhancing efficiency in work and study. "Flow's" official website showcases multiple features of this product. In the field of academic research, rea

Is it possible to have a universal graph model that can predict toxicity based on molecular structure while also providing friend recommendations in social networks? Or one that can predict the citations of different authors to uncover human aging mechanisms in gene networks? It turns out, this model was jointly proposed by Professor Chen Yixin's team from Washington University in St. Louis, Zhang Muhan from Peking University, and researchers such as Tao Dacheng from JD.com Research Institute.

The Graph plans to introduce a new AI-assisted querying feature, which includes the introduction of Firehose and Substreams for providing verifiable data and access to Ethereum archived data solutions. The Graph is dubbed the Google of Web3.

RA-DIT improves the ability of language models to utilize retrieval information and provide relevant results from the retriever through a two-stage fine-tuning process. RA-DIT outperforms existing retrieval-augmented models in knowledge-intensive zero-shot and few-shot testing. The RA-DIT65B model shows improved performance in tasks that require knowledge, demonstrating the effectiveness of fine-tuning. The enhancement of retrieval capabilities brought by RA-DIT has shown good results in knowledge-intensive evaluations, confirming the effectiveness of fine-tuning.