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

update-1.6.2c
ci / test (services/control) (push) Successful in 49s
Details
ci / test (services/knowledge) (push) Successful in 50s
Details
ci / test (platform/neuroforge) (push) Successful in 54s
Details
ci / test (services/agent) (push) Successful in 1m0s
Details
ci / docker-build (push) Failing after 1m10s
Details
release-tag / release-image (push) Successful in 6m33s
Details

Browse Source
This commit is contained in:
groot
2026-09-09 15:27:42 +02:00
parent f776b2322a
commit faa416ac89
20 changed files with 352 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+6
View File
@@ -82,6 +82,10 @@ NEUROFORGE_WORKER_OLLAMA_API_KEY=
NEUROFORGE_OLLAMA_API_KEY=
OLLAMA_TIMEOUT=10m
OLLAMA_MAX_CONCURRENT=1
# Explicit chat context for Agent requests. Prevents a gateway/server default
# (often 4k on smaller VRAM profiles) from truncating structured JSON.
# gemma4 can use larger values such as 32768/65536/131072 when the runtime supports it.
OLLAMA_NUM_CTX=8192
OLLAMA_NUM_PREDICT=768
OLLAMA_JSON_RETRIES=1
OLLAMA_KEEP_ALIVE=10m
@@ -438,6 +442,8 @@ KNOWLEDGE_EMBEDDING_PROFILE=auto
# OLLAMA_MAX_CONCURRENT bleibt als Legacy-Alias für
# OLLAMA_NODE_MAX_INFLIGHT erhalten, falls der neue Wert nicht gesetzt ist.
# Explizite Kontextgröße für Agent-Chatrequests.
# OLLAMA_NUM_CTX=8192 # already configured in SHARED OLLAMA RUNTIME above
# Maximale Anzahl generierter Tokens für strukturierte Antworten.
# OLLAMA_NUM_PREDICT=768 # already configured in SHARED OLLAMA RUNTIME above
# Wiederholungen bei semantisch/strukturell fehlerhaftem Modell-JSON.