RAGless answers FAQs without running an LLM at query time
RAGless is a system for finding answers in FAQ-style content. It uses a only when documents are first added, not when someone asks a question. PDF, text, and Markdown files are turned into prepared question-and-answer pairs by Gemini, with several question versions for the same answer.
Each question version is converted into an embedding and stored in a local Qdrant database. When a user asks something, the question is also converted into an embedding, the closest stored questions are searched, and scores are combined by answer ID. The system then returns the prepared answer instead of generating a new one.
This removes the runtime generation step, so there is no runtime prompt work and less risk of made-up answers by design. It can also run fully offline with Ollama by changing EMBEDDING_MODEL in the .
Key points
- Gemini is used only when documents are added, not when users ask questions.
- Prepared question versions are stored as in local Qdrant.
- At , the system searches for similar questions and returns a prepared answer.
- Scores from multiple question versions are combined under the same answer ID.
- Ollama support allows offline use by changing EMBEDDING_MODEL in the config.