harald/nixcfg
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

feat(rag): install on m4 and amd, default endpoints to sgx

Browse source 
Add the rag CLI to the m4 and amd hosts and point its default API_BASE
and QDRANT_URL at sgx (where the gateway and Qdrant run) instead of
localhost. The services live on sgx, so a localhost default only worked
there; sgx resolves to itself on sgx, so this default is correct on every
host and leaves only RAG_API_KEY to set.
This commit is contained in:
Harald Hoyer 2026-05-22 08:43:26 +02:00
parent fc3e40686a
commit 89c82cf804
3 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
packages/rag/default.nix
View file

@ -22,9 +22,9 @@ writers.writePython3Bin "rag"
from qdrant_client import QdrantClient
from qdrant_client.models import Distance, PointStruct, VectorParams
API_BASE = os.environ.get("RAG_API_BASE", "http://localhost:4001/v1")
API_BASE = os.environ.get("RAG_API_BASE", "http://sgx:4001/v1")
API_KEY = os.environ.get("RAG_API_KEY", "none")
QDRANT_URL = os.environ.get("RAG_QDRANT_URL", "http://localhost:6333")
QDRANT_URL = os.environ.get("RAG_QDRANT_URL", "http://sgx:6333")
EMBED_MODEL = os.environ.get("RAG_EMBED_MODEL", "bge-m3")
CHAT_MODEL = os.environ.get("RAG_CHAT_MODEL", "coder")
DEFAULT_COLLECTION = os.environ.get("RAG_COLLECTION", "docs")