I’m using the llama.cpp server with the all-MiniLM-L6-v2 model to get vectors. I’m connecting it to the Qdrant OpenAI node and configuring it to work with my local llama.cpp server. When executing ‘Insert Documents’, I get the error ‘Cannot read properties of undefined (reading ‘0’)’. At the same time, I separately tested requests to llama.cpp with this model using the http_request node - everything works perfectly, I get vectors in the response. The logs also don’t provide any information about the nature of the problem - even in N8N_LOG_LEVEL: ‘debug’ mode.
(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)
Share the output returned by the last node
- n8n version: 1.90.2 (self-hosted)
- Database (default: SQLite): SQLite
- n8n EXECUTIONS_PROCESS setting (default: own, main): main
- Running n8n via (Docker, npm, n8n cloud, desktop app): npm
- Operating system: Debian 12