Short answer:
An LLM is the AI “brain” that understands and generates text. RAG (Retrieval-Augmented Generation) is the process AskTuring uses to ground that brain in your documents, so answers are relevant, accurate, and specific to your data.
Full explanation
In AskTuring, the Large Language Model (LLM) is the engine that reads your question, understands its meaning, and produces a response. We let you choose which LLM you want to use for your responses — so you can pick the one that best matches your needs for style, speed, or depth.
RAG, or Retrieval-Augmented Generation, is how AskTuring keeps the LLM focused on your actual documents instead of guessing from general knowledge. Here’s how it works - when you ask a question, AskTuring looks through your chosen set of documents to find the most relevant information. It then gives that information to the LLM, which uses it to write an answer that’s specific to you. This keeps responses accurate and on-topic.
This means you can control exactly how the AI works for you:
Index only – The LLM uses only your indexed documents.
Index + AI – The LLM blends your documents with its broader training knowledge.
AI only – The LLM answers purely from its general knowledge, without pulling from your Index.
Why it matters
RAG ensures that your answers are not only accurate but also grounded in the right source — whether that’s your private data, public knowledge, or both. It’s how AskTuring turns a general-purpose AI into a specialist that works for your exact use case.