EMBED_URL in rag.py hardcoded the IP and port instead of using LLAMA_SERVER_BASE, so the env var JARVISCHAT_LLAMA_SERVER_BASE was ignored for embedding requests.
3.0 KiB
3.0 KiB
EMBED_URL in rag.py hardcoded the IP and port instead of using LLAMA_SERVER_BASE, so the env var JARVISCHAT_LLAMA_SERVER_BASE was ignored for embedding requests.