This system transforms unstructured text documents into interactive knowledge graphs by using an LLM to extract knowledge in the form of Subject-Predicate-Object triplets. It features automated text chunking, entity standardization to ensure consistent naming across segments, and relationship inference to discover connections between disconnected parts of the data. The final output is an interactive HTML visualization that includes color-coded communities, node sizing based on importance metrics, and both original and inferred relationship types.
- Support for any OpenAI-compatible API endpoint including Ollama and vLLM
- Multi-pass processing for triple extraction, entity alignment, and relationship inference
- Interactive visualization with zoom, pan, and physics controls
- Community detection using the Louvain method
- Support for any OpenAI-compatible API endpoint including Ollama and vLLM
- Multi-pass processing for triple extraction, entity alignment, and relationship inference
- Interactive visualization with zoom, pan, and physics controls
- Community detection using the Louvain method
SciPhi-AI/R2R is a framework for rapid development and deployment of production-ready RAG pipelines. The framework enables the deployment, customization, extension, autoscaling, and optimization of RAG pipeline systems, making it easier for the OSS community to use them. It includes several code examples and client applications that demonstrate application deployment and interaction. The core abstractions come in the form of ingestion, embedding, RAG, and eval pipelines.
