Skip to main content
RAGLight 4 is a Python framework and does not ship an interactive command-line application. The public APIs are designed to be embedded in a CLI, worker, notebook, web service, or desktop app. The repository’s runnable examples are the shortest copy-and-paste entry points:
  • local Ollama classic RAG with directory ingestion;
  • hosted OpenAI classic RAG;
  • an OpenAI-compatible custom endpoint;
  • agentic RAG with custom tools and agents;
  • MCP tool discovery and execution.
Run an example from a checkout with:
For an application CLI, parse paths and provider choices in the delivery layer, construct the components, call pipeline.ingest(...), and then use a session for the chat loop. This keeps the framework API independent from a particular terminal UX or configuration convention. See Getting started for a complete local program.