The system processes unstructured text by chunking documents and using an LLM to identify entities, standardize their names, and extract relationships between them. It infers additional relationships between disconnected graph nodes and can connect to any OpenAI-compatible API endpoint (Ollama, LM Studio, vLLM, LiteLLM, Anthropic, Azure OpenAI, AWS Bedrock). The extracted knowledge is rendered as an interactive HTML visualization using NetworkX and PyVis.