Tag: Knowledge graph

Minicule is a platform for EBV research and scientific discovery. It can help users transform complex data into clear knowledge maps and accelerate the research discovery process. This product provides researchers in the life sciences with powerful data visualization and collaboration tools.

SophistAI is an AI-driven learning assistant that transforms chaotic learning materials into structured interactive knowledge graphs to help users learn and prepare for exams more efficiently. It provides functions such as intelligent progress tracking, deep mining of subtopics, and automatic progress completion.

Yuxi-Know is a knowledge graph question and answer system based on the large model RAG knowledge base, built using Llamaindex + VueJS + Flask + Neo4j. It supports OpenAI, model calling of domestic mainstream large model platforms and local vllm deployment, and can realize functions such as knowledge base question and answer, knowledge graph retrieval and network retrieval. The main advantages of this system are its flexible adaptation to multiple models, support for multiple knowledge base formats, and powerful knowledge graph integration capabilities. It is suitable for enterprises and research institutions that require efficient knowledge management and intelligent question and answer, and has high technological advancement and practicality.

AI Mode is an experimental feature in Google Search developed based on the Gemini 2.0 model. It provides users with deeper and more comprehensive search results through advanced reasoning and multi-modal capabilities. This feature is designed to help users handle complex multi-part problems more efficiently and provide high-quality responses through real-time data and knowledge graphs. The launch of AI Mode reflects Google’s continued innovation in improving the search experience and also demonstrates the potential of generative AI in information retrieval.

Graphiti is a technical model focused on building dynamic time-series knowledge graphs, designed to handle changing information and complex relationship evolution. It supports knowledge extraction from unstructured text and structured JSON data by combining semantic search and graph algorithms, and enables point-in-time queries. Graphiti is the core technology of Zep's memory layer, supporting long-term memory and state-based reasoning. It is suitable for application scenarios that require dynamic data processing and complex task automation, such as sales, customer service, health, finance and other fields.

kg-gen is an artificial intelligence-based tool capable of extracting knowledge graphs from ordinary text. It supports processing text input ranging from single sentences to lengthy documents, and can process messages in conversational format. This tool uses advanced language models and structured output technology to help users quickly build knowledge graphs, and is suitable for fields such as natural language processing, knowledge management, and model training. kg-gen provides a flexible interface and multiple functions, aiming to simplify the knowledge graph generation process and improve efficiency.

KET-RAG (Knowledge-Enhanced Text Retrieval Augmented Generation) is a powerful retrieval-enhanced generation framework that combines knowledge graph technology. It achieves efficient knowledge retrieval and generation through multi-granularity indexing frameworks such as knowledge graph skeleton and text-keyword bipartite graph. This framework significantly improves retrieval and generation quality while reducing indexing costs, and is suitable for large-scale RAG application scenarios. KET-RAG is developed based on Python, supports flexible configuration and expansion, and is suitable for developers and researchers who need efficient knowledge retrieval and generation.

VideoRAG is an innovative retrieval-enhanced generative framework specifically designed to understand and process extremely long contextual videos. It enables understanding of videos of unlimited length by combining graph-driven text knowledge anchoring and hierarchical multi-modal context encoding. The framework can dynamically construct knowledge graphs, maintain semantic coherence of multiple video contexts, and optimize retrieval efficiency through an adaptive multi-modal fusion mechanism. VideoRAG's key benefits include efficient processing of extremely long-context videos, structured video knowledge indexing, and multi-modal retrieval capabilities, enabling it to provide comprehensive answers to complex queries. This framework has important technical value and application prospects in the field of long video understanding.

Data Commons is a powerful public data platform that aims to provide a unified knowledge graph by integrating global public data to help users easily explore and analyze data. Initiated by Google, it supports the integration of multiple data sources and provides a wealth of visualization tools and API interfaces to facilitate users' data exploration and research. The main advantage of Data Commons is the standardization and unification of data. Users can quickly obtain and analyze data through its powerful tools without complex pre-processing. In addition, it supports community contributions, where users can share their analysis and insights to jointly promote the development of data science. Data Commons is suitable for researchers, data analysts, policymakers, and any group that needs public data to support decision-making. Its free access model lowers the threshold for data use and promotes the widespread dissemination and application of data.

Potpie is a technology platform for developers that helps developers with tasks such as debugging, testing, system design, code review, and document generation by building AI agents based on code bases. This product leverages powerful knowledge graph technology to enable AI agents to deeply understand the context of the code base, thereby providing high-precision engineering task execution capabilities. The main advantage of Potpie is its high degree of customization and easy integration, which can significantly improve development efficiency and code quality. The product offers a free trial, and open source versions are available.

GraphAgent is an automated agent pipeline designed to handle explicit graph dependencies and implicit graph-enhanced semantic interdependencies to accommodate prediction tasks (e.g. node classification) and generation tasks (e.g. text generation) in real-world data scenarios. It consists of three key components: a graph generation agent that builds knowledge graphs to reflect complex semantic dependencies; a planning agent that interprets different user queries and formulates corresponding tasks; and an execution agent that efficiently executes planned tasks and automates tool matching and invocation. GraphAgent reveals complex relational information and data semantic dependencies by integrating language models and graph language models.

StoryWeaver is a unified world model designed for knowledge-enhanced story character customization, designed to enable single and multi-character story visualization. This model is based on the AAAI 2025 paper and can handle the customization and visualization of characters in stories through a unified framework, which is of great significance to the fields of natural language processing and artificial intelligence. The main advantages of StoryWeaver include its ability to handle complex story situations and its ability to be continuously updated and expanded on its functionality. Product background information shows that the model will continue to update arXiv papers and add more experimental results.

Depth AI is an artificial intelligence product built by engineers. It can answer deep technical questions by building a knowledge graph of the code base, and supports the deployment of customized AI assistants in different work scenarios. Product background information shows that Depth AI is designed to help engineers and development teams understand and use code libraries more efficiently, and improve team productivity by integrating into existing tools and workflows, such as Slack, GitHub Copilot, Jira, etc. Key product benefits include in-depth technical question answering, comprehensive code graph understanding, abstract reasoning capabilities, and latent spatial interaction. Depth AI provides enterprise-grade security and compliance features to keep data safe and does not use customer data for model training.

WhyHow Knowledge Graph Studio is an open source platform designed to simplify the process of creating and managing RAG-native knowledge graphs. The platform provides rule-based entity parsing, modular graph construction, flexible data ingestion, and API-first design, and supports SDKs. It is built on NoSQL database and provides a flexible and scalable storage layer to make data retrieval and traversal of complex relationships easy. The platform is suitable for processing structured and unstructured data and building exploratory graphs or highly patterned constrained graphs. It is designed to achieve scale and flexibility and is suitable for experimentation and large-scale use.

Graphusion is a pipeline tool for extracting knowledge graph triples from text. It builds a knowledge graph through a series of steps, including concept extraction, candidate triple extraction, and triple fusion. The importance of this tool lies in its ability to help researchers and developers automate the extraction of structured information from large amounts of textual data to support knowledge management and data science projects. The main advantages of Graphusion include its automated processing capabilities, adaptability to different data sets, and flexible configuration options. Product background information shows that Graphusion was developed by tdurieux, and relevant code and documentation can be found on GitHub. Currently, the tool is free, but specific pricing strategies may change based on updates and maintenance by developers.

KAG (Knowledge Augmented Generation) is a professional domain knowledge service framework that aims to bidirectionally enhance large language models and knowledge graphs through the advantages of knowledge graphs and vector retrieval, and solve the problems of RAG (Retrieval Augmentation Generation) technology such as the large gap between vector similarity and knowledge reasoning correlation, and its insensitivity to knowledge logic. KAG's performance on multi-hop question answering tasks is significantly better than methods such as NaiveRAG and HippoRAG. For example, the F1 score on hotpotQA increased by 19.6% and on 2wiki by 33.5%. KAG has been successfully used in two professional knowledge question and answer tasks of Ant Group, including government question and answer and health question and answer. Compared with the RAG method, the professionalism has been significantly improved.

Knowledge Table is an open source toolkit designed to simplify the process of extracting and exploring structured data from unstructured documents. It enables users to create structured knowledge representations such as tables and charts through a natural language query interface. The toolkit features customizable extraction rules, fine-tuned formatting options, and data provenance displayed through the UI to accommodate a variety of use cases. Its goal is to provide business users with a familiar spreadsheet interface, while providing developers with a flexible and highly configurable backend, ensuring seamless integration with existing RAG workflows.

GraphReasoning is a project that uses generative artificial intelligence technology to transform 1,000 scientific papers into knowledge graphs. Through structured analysis, calculating node degrees, identifying communities and connectivity, and evaluating clustering coefficients and betweenness centralities of key nodes reveal fascinating knowledge architectures. The graph is scale-free, highly interconnected, and can be used for graph reasoning, using transitive and isomorphic properties to reveal unprecedented interdisciplinary relationships for answering questions, identifying knowledge gaps, proposing unprecedented materials designs, and predicting material behavior.

Local Knowledge Graph is a Flask-based web application that uses the local Llama language model to process user queries, generate step-by-step reasoning, and visualize thought processes in the form of an interactive knowledge graph. It also finds and displays related questions and answers based on semantic similarity. The main advantages of the application include real-time display of the reasoning process, dynamic knowledge graph visualization, calculation and display of the strongest reasoning path, and related question and answer based on semantic similarity.

SciAgentsDiscovery is a system that utilizes multi-agent systems and large-scale ontology knowledge graphs to automate scientific research. By integrating large-scale language models, data retrieval tools, and multi-agent learning systems, it can autonomously generate and refine research hypotheses, revealing underlying mechanisms, design principles, and unexpected material properties. The system demonstrates its ability to discover interdisciplinary relationships in the field of bioinspired materials, beyond traditional human-driven research methods.

Fine AI Coding Workflows is an AI-driven software development automation platform that accelerates the development cycle through customized AI workflows. The platform is based on the Atlas knowledge graph and integrates the tools used by the team to provide AI agents with rich contextual information for more precise task execution. It supports integration with a variety of development tools, such as OpenAI, Anthropic, Sentry, GitHub, etc., aiming to improve development efficiency, code quality and problem solving speed.

muAgent is an innovative Agent framework driven by a knowledge graph engine that supports multi-Agent orchestration and collaboration technology. It uses LLM+EKG (Eventic Knowledge Graph industry knowledge bearing) technology, combined with FunctionCall, CodeInterpreter, etc., to realize the automation of complex SOP processes through canvas drag and light text writing. muAgent is compatible with various Agent frameworks on the market and has core functions such as complex reasoning, online collaboration, manual interaction, and ready-to-use knowledge. This framework has been verified in multiple complex DevOps scenarios of Ant Group.

iText2KG is a Python package designed to leverage large language models to extract entities and relationships from text documents and incrementally build consistent knowledge graphs. It has zero-shot capabilities, allowing knowledge extraction across different domains without specific training. The package includes document distillation, entity extraction, and relationship extraction modules, ensuring entities and relationships are resolved and unique. It provides visual representation of knowledge graphs through Neo4j, supporting interactive exploration and analysis of structured data.

Fact Finder is an open source intelligent question answering system that uses language models and knowledge graphs to generate natural language answers and provide evidence. The system generates Cypher queries by calling a language model, queries the knowledge graph for answers, and uses another language model call to generate the final natural language answer. Key benefits of Fact Finder include its ability to provide transparency, allowing users to view queries and evidence, and providing intuitive evidence through visual subgraphs.

Easy-RAG is a retrieval-enhanced generation (RAG) system. It is not only suitable for learners to understand and master RAG technology, but also easy for developers to use and expand independently. The system improves retrieval efficiency and generation quality by integrating technologies such as knowledge graph extraction and analysis tools, rerank reordering mechanism, and faiss vector database.

Triplex is an innovative open source model that can convert large amounts of unstructured data into structured data. Its performance in building knowledge graphs exceeds that of gpt-4o, and the cost is only one-tenth of the cost. It greatly reduces the cost of generating knowledge graphs by efficiently converting unstructured text into semantic triples, the basis for knowledge graph construction.

Memory is an open source memory layer designed for autonomous agents. It improves the agent's reasoning and learning capabilities by imitating human memory. It uses the Neo4j graph database to store knowledge, and combines the Llama Index and Perplexity models to enhance the query capabilities of the knowledge graph. The main advantages of Memory include functions such as automatic memory generation, memory modules, system improvement and retrospective memory. It is designed to integrate with existing agents with minimal developers and provide visual data for memory analysis and system improvement through the dashboard.

knowledge_graph_maker is a Python library capable of converting arbitrary text into a knowledge graph based on a given ontology. A knowledge graph is a semantic network that represents the network between real-world entities and the relationships between them. This library uses graph algorithms and centrality calculations to help users deeply analyze text content, realize connectivity analysis between concepts, and improve the depth of communication with text through graph retrieval enhanced generation (GRAG) technology.

RDFox is a rule-driven artificial intelligence technology developed by three professors from the Department of Computer Science at the University of Oxford based on decades of research on knowledge representation and reasoning (KRR). Its unique features are: 1. Powerful AI reasoning capabilities: RDFox can create knowledge from data like humans, conduct reasoning based on facts, and ensure the accuracy and interpretability of results. 2. High performance: As the only knowledge graph that runs in memory, RDFox outperforms other graph technologies in benchmark tests and is able to handle complex data storage of billions of triples. 3. Scalable deployment: RDFox has extremely high efficiency and optimized footprint, and can be embedded in edge and mobile devices to run independently as the brain of AI applications. 4. Enterprise-level features: including high performance, high availability, access control, interpretability, human-like reasoning capabilities, data import and API support, etc. 5. Incremental reasoning: RDFox’s reasoning function updates instantly when data is added or deleted, without affecting performance and without the need for reloading.

GraphRAG-Ollama-UI is a local model adaptation version based on Microsoft GraphRAG, which supports the use of Ollama for local model support. It provides an interactive user interface through Gradio UI, making it easier for users to manage data, run queries and visualize results. Key advantages of this model include native model support, cost-effectiveness, interactive user interface, real-time graph visualization, file management, settings management, output exploration and logging.

llm-graph-builder is an application that uses large language models (such as OpenAI, Gemini, etc.) to extract nodes, relationships and their attributes from unstructured data (PDF, DOCS, TXT, YouTube videos, web pages, etc.), and uses the Langchain framework to create a structured knowledge graph. It supports uploading files from local machines, GCS or S3 buckets, or network resources, selecting LLM models and generating knowledge graphs.

meet-libai is a knowledge graph and AI agent project built with the Tang Dynasty poet Li Bai and his poetry as the core, combined with artificial intelligence technology. This project uses digital means to innovate the popularization and promotion of traditional culture, so that Li Bai's poetry culture can be more widely disseminated and deeply understood. The project uses natural language processing technology to build a knowledge graph containing multi-dimensional information about Li Bai's life, poetic style, artistic achievements, etc., and trains an AI agent that can interact with users in high quality, providing a novel way to learn and experience traditional culture.

Knowledge Graph RAG is an open source Python library that enhances the performance of large language models (LLMs) by creating knowledge graphs and document networks. This library allows users to search and correlate information through graph structures, providing richer context for language models. It is mainly used in the field of natural language processing, especially in document retrieval and information extraction tasks.

prettygraph is a Python-based web application developed by @yoheinakajima that showcases a new UI pattern for dynamically converting text input into a knowledge graph. This project is a rapid prototype that aims to provide a simple UI idea to generate a knowledge graph by updating text highlighting in the UI in real time.

GraphRAG (Graphs + Retrieval Augmented Generation) is a technique for enriching understanding of text datasets by combining text extraction, network analysis, and prompts and summaries from large language models (LLM). The technology will soon be open sourced on GitHub and is part of a Microsoft research project aimed at improving text data processing and analysis capabilities through advanced algorithms.

MyGO is a tool for multi-modal knowledge graph completion that improves the accuracy of completion by processing discrete modal information as fine-grained tags. MyGO uses the transformers library to embed text tags and then train and evaluate on multi-modal datasets. It supports custom data sets and provides training scripts to reproduce experimental results.

MindGraph is an open source, API-first graph-based project prototype designed to enable natural language interaction (input and output). It serves as a template for building and customizing your own CRM solution, with an emphasis on ease of integration and scalability. The main functions include: entity management, integrated triggers, search functions, and artificial intelligence preparation. It adopts a modular architecture and dynamically registers and executes various integration functions through the integration manager, giving it the ability to seamlessly integrate artificial intelligence functions. It supports flexible database integration, including in-memory database and cloud database NexusDB. Coupled with the creation of pattern-based knowledge graphs, it can automatically generate structured data from natural language input.

360AI Search is a new generation AI search engine launched by 360 Group. Through semantic understanding, knowledge graph and other technologies, it can accurately understand the user's search intention, actively ask questions to complete the information, deeply extract relevant content from massive web pages, and finally provide clear, comprehensive and accurate answers, greatly improving the convenience and accuracy of search.

360AI Search is a new generation AI search engine launched by 360 Group. Through semantic understanding, knowledge graph and other technologies, it can accurately understand the user's search intention, actively ask questions to complete the information, deeply extract relevant content from massive web pages, and finally provide clear, comprehensive and accurate answers, greatly improving the convenience and accuracy of search.

Farao AI, also known as legal artificial intelligence, is a technology that combines artificial intelligence and the legal field. It uses robots pre-trained by large language models to conduct in-depth learning and analysis of legal knowledge and cases to provide services such as legal consultation, legal document writing, and legal case studies. The emergence of Farao A| has had a profound impact on the professional provision and case research of the legal industry. It can provide faster, more accurate and comprehensive legal services, and at the same time it has brought new opportunities and challenges to the legal industry.

QAnything is a local knowledge question and answer system that supports any file format and database. You can simply import any locally stored files in various formats and get accurate, fast, and reliable questions and answers. Currently supported formats include: PDF, Word (doc/docx), PPT, Markdown, Eml, TXT, pictures (jpg, png, etc.), web links, etc. Supported formats will continue to be added in the future. QAnything has data security and supports offline installation and use; supports cross-language Q&A in Chinese and English; supports massive data Q&A to solve the problem of large-scale data retrieval degradation; is a high-performance product-level system that can be directly used for enterprise applications; one-click installation and deployment, user-friendly experience out of the box; supports multiple knowledge base Q&A and other functions.

KG-RAG is a task-agnostic framework that combines the explicit knowledge of knowledge graphs and the tacit knowledge of large language models. Here, we utilize SPOKE, a huge biomedical knowledge graph, as the provider of biomedical context. The main feature of KG-RAG is that it extracts “prompt-related context” from the SPOKE knowledge graph, which is defined as the minimum context required to respond to user prompts.

The KnowledgeGraph GPT project aims to use OpenAI's GPT-3 model to convert unstructured text data into structured knowledge graph representation. This product has powerful functions and advantages, is reasonably priced, and is positioned to meet users' needs for structured processing of text data.

Project Knowledge Exploration is an interactive search API for structured data developed by Microsoft Research. It interprets user queries and returns relevant results via natural language input. The API supports automatic query completion, quick retrieval of matching object details, visualization using attribute histograms, and an interactive segmentation experience. This product can be widely used in various scenarios, including knowledge graphs, data analysis, intelligent search, etc.

Docker GenAI Stack is an artificial intelligence application development solution for developers. It integrates leading AI technologies and can deploy a complete AI application stack in just a few clicks to achieve code-level AI integration. GenAI Stack has built-in preconfigured large-scale language models, provides Ollama management, uses Neo4j as the default database, and can realize knowledge graph and vector search. Also equipped with the LangChain framework for orchestration and debugging, as well as comprehensive technical support and community resources. GenAI Stack makes AI application development simple and efficient, and developers can quickly build practical AI solutions.

ODIN is an Obsidian plug-in that can map users' notes to knowledge, thereby realizing functions such as intelligent question and answer and link prediction, helping users manage knowledge points and establish a comprehensive knowledge system. The key functions of ODIN include: LLM-based intelligent question and answer, which can intuitively query knowledge points in notes; global note network visualization, presenting note content in the form of a knowledge graph; semantic-based link prediction, automatically establishing associations between notes; semantic-based node prompts, discovering key knowledge points in notes, etc. ODIN can greatly improve Obsidian's knowledge management capabilities and is the author's best choice for building a personal knowledge management system.

QuillO is your digital brain that easily transforms data into dynamic knowledge graphs and uses it to create content that is unique and supports your knowledge. It combines your data with unique AI to deliver AI-enhanced, context-aware content. From writing assistance to partnerships, explore a variety of use cases. Let your unique knowledge unleash your creative potential.

Zhisou AI is a content creation tool based on artificial intelligence technology. Through intelligent semantics and knowledge graph technology, it helps users quickly generate high-quality articles, PPT and other content to improve productivity. At the same time, Zhisou AI also provides a variety of solutions, including AI+media, AI+finance, etc., to meet the needs of different fields.

SOMA is a research automation platform that analyzes medical research articles and extracts important concepts, identifies causal and correlational relationships between them, and forms a knowledge graph. Researchers can specify concept pairs and access specific research articles using system-provided literature links.

Seek AI is an intelligent search engine and AI assistant that uses advanced artificial intelligence technology to provide users with efficient and accurate search results and intelligent assistant functions. Its main functions include: intelligent search, natural language processing, knowledge graph construction, etc. The advantage of Seek AI is to provide personalized search results, improve work efficiency and save time. In terms of pricing, Seek AI offers free trials and paid packages. It is suitable for individuals and businesses and can meet the needs of different users.

NOLEJ is a decentralized skills platform powered by an AI engine that can automatically generate interactive courses and global knowledge maps. It provides a range of features to help individual educators, schools/institutions and businesses create, manage and share educational content. NOLEJ's main advantages lie in automated course generation, intelligent recommendations and the construction of a global knowledge graph. For pricing, visit the official website for details. NOLEJ is suitable for scenarios such as personal learning, educational institutions and corporate training.