LHRLAB/Graph-R1

Graph-R1 lets language models reason over knowledge graphs using multi-turn interactions and reinforcement learning for better question answering

View on index

Related repos

• turns text into knowledge graphs
• real-time knowledge graphs for AI agents
• open-source reinforcement learning for language models
• reinforcement learning library for training large language models, supports many RL algorithms, integrates with LLM tools, scales to models with up to 671B parameters
• post-training recipe using RL to boost reasoning in language models
• tool for building and managing knowledge graphs with RAG workflows
• Graph RAG conversational knowledge base tool using TiDB
• Transforms unstructured text into knowledge graphs for LLM-powered data analysis
• lightweight GraphRAG implementation for building knowledge graph-based retrieval with LLMs
• Step-by-step code for adding reasoning to a pre-trained LLM, with hands-on examples and explanations