ci: use zerto-docs's load-balanced Ollama GPU pool on the Gitea host

Match the OLLAMA_URLS pattern from zerto-docs-rag so every docs MCP
build fans out across the same two GPU-pinned Ollama containers on
192.168.0.2 (:11435 Titan X, :11436 1080 Ti). The host's primary
Ollama on :11434 is left alone for OpenWebUI.

rag.embeddings now reads OLLAMA_URLS (plural CSV) preferentially with
fallback to OLLAMA_URL, defaulting to http://192.168.0.2:11434 — same
shape as zerto's embeddings.py. The OllamaEmbeddings class already
round-robins per batch, so both GPUs run in parallel during the
chroma rebuild.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-22 13:22:59 -04:00
parent fd376fab77
commit 6b11993688
3 changed files with 31 additions and 9 deletions
+21 -4
View File
@@ -3,8 +3,15 @@
Swappable: implement the same `embedding_function()` interface returning
a Chroma `EmbeddingFunction` and the rest of the pipeline doesn't care.
Defaults (override via env):
OLLAMA_URL one or more comma-separated URLs (load-balanced)
Env-configurable (matches the zerto-docs-rag pattern so the same Gitea
runner + GPU-pinned Ollama containers can serve every docs MCP build):
OLLAMA_URLS comma-separated list, load-balanced round-robin per batch.
Preferred — set in the CI workflow to fan out across two
GPU-pinned Ollama containers on the Gitea host.
OLLAMA_URL single endpoint, fallback when OLLAMA_URLS is unset.
Default http://192.168.0.2:11434 (the host where the GPUs
live in Justin's lab).
EMBED_MODEL model name; default 'nomic-embed-text'
EMBED_DIM expected embedding dim; default 768 (nomic-embed-text)
"""
@@ -19,8 +26,18 @@ from chromadb import EmbeddingFunction, Documents, Embeddings
log = logging.getLogger(__name__)
OLLAMA_URLS = [u.strip() for u in os.environ.get("OLLAMA_URL",
"http://localhost:11434").split(",") if u.strip()]
DEFAULT_OLLAMA_URL = "http://192.168.0.2:11434"
def _resolve_urls() -> list[str]:
raw = os.environ.get("OLLAMA_URLS", "").strip()
if raw:
return [u.strip().rstrip("/") for u in raw.split(",") if u.strip()]
single = os.environ.get("OLLAMA_URL", DEFAULT_OLLAMA_URL).strip().rstrip("/")
return [single]
OLLAMA_URLS = _resolve_urls()
EMBED_MODEL = os.environ.get("EMBED_MODEL", "nomic-embed-text")
EMBED_DIM = int(os.environ.get("EMBED_DIM", "768"))