n8n document agent finds the right data but still gives weak answers
An offline, on-premise n8n workflow is being used to answer questions about a company’s internal documents. The documents are stored in Qdrant as , and the qwen3 model creates those . Ollama serves the models locally.
An AI agent node answers user questions with as the chat model. The Qdrant retriever returns relevant information, but the agent does not turn that information into accurate answers. Some answers also include .
A larger chat model is not practical because the available hardware is limited, so the workflow needs accuracy improvements without moving to a heavier model.
Key points
- The setup uses n8n for an offline internal-document AI agent.
- Qdrant returns relevant retrieved data, so the main issue is not basic search failure.
- is used as the chat model, and are limited by hardware.
- The agent sometimes gives inaccurate answers and .
- Improving workflow structure may be cheaper than switching to a heavier model.