justin/hvm-docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

rag: resilient embedder — rotate/split on endpoint errors; 4-GPU embed pool (#8)

Browse Source
This commit was merged in pull request #8.
This commit is contained in:
Justin Paul
2026-06-10 15:47:01 -04:00
parent 41d431670f
commit 53b9d348d8
3 changed files with 40 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitea/workflows/image-only.yml
+1 -1
View File
@@ -22,7 +22,7 @@ env:
# Two GPU-pinned Ollama containers on the Gitea host — same infra
# zerto-docs uses. :11435 = Titan X, :11436 = 1080 Ti. Indexer
# round-robins per batch.
OLLAMA_URLS: http://192.168.0.2:11435,http://192.168.0.2:11436
OLLAMA_URLS: http://192.168.0.2:11435,http://192.168.0.2:11436,http://192.168.0.125:11434,http://192.168.0.126:11434
EMBED_MODEL: nomic-embed-text
PRODUCT_NAME: hvm
.gitea/workflows/refresh.yml
+1 -1
View File
@@ -34,7 +34,7 @@ env:
# :11435 owns the Titan X, :11436 owns the 1080 Ti; the indexer
# round-robins per batch so both cards run in parallel. The host's
# primary Ollama on :11434 is left alone for OpenWebUI etc.
OLLAMA_URLS: http://192.168.0.2:11435,http://192.168.0.2:11436
OLLAMA_URLS: http://192.168.0.2:11435,http://192.168.0.2:11436,http://192.168.0.125:11434,http://192.168.0.126:11434
EMBED_MODEL: nomic-embed-text
PRODUCT_NAME: hvm