sendnrw/glpi-neuroforge-mega
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update-1.6.2
ci / test (services/knowledge) (push) Successful in 47s
Details
ci / test (services/agent) (push) Successful in 55s
Details
ci / test (platform/neuroforge) (push) Successful in 56s
Details
ci / docker-build (push) Failing after 1m10s
Details
ci / test (services/control) (push) Successful in 1m26s
Details
release-tag / release-image (push) Successful in 6m43s
Details

Browse Source
This commit is contained in:
groot
2026-09-09 12:55:35 +02:00
parent e0bf42bf32
commit d18405ed2e
48 changed files with 8062 additions and 1111 deletions
Download Patch File Download Diff File Expand all files Collapse all files
services/agent/.env.example
+3 -1
View File
@@ -290,6 +290,8 @@ OLLAMA_REQUIRE_EMBEDDING_MODEL=true
# OLLAMA_MODEL=qwen3:8b
# Embedding-Modell für RAG.
OLLAMA_EMBEDDING_MODEL=embeddinggemma
# Optional: Bearer token sent as Authorization: Bearer <token> to Ollama-compatible endpoints.
OLLAMA_API_KEY=
# Modellspezifisches Retrieval-Prompting.
# auto = Modell automatisch erkennen; für embeddinggemma empfohlen.
@@ -799,4 +801,4 @@ QUEUE_SIZE=256
# Ticketpipelines gleichzeitig verteilen, wie Worker aktiv sind. Für drei
# gleichartige Nodes ist WORKERS=3 ein sinnvoller Lasttest; jeder Node bleibt
# zusätzlich durch OLLAMA_NODE_MAX_INFLIGHT begrenzt.
WORKERS=2
WORKERS=2