conjurer: wepnij oba boty w Ollamę (192.168.1.72:11434) #23

Merged
gitea merged 2 commits from conjurer-ollama-endpoint into master 2026-08-24 15:40:07 +00:00
2 changed files with 16 additions and 0 deletions
Showing only changes of commit a802b90617 - Show all commits
+8
View File
@@ -36,6 +36,14 @@ spec:
# Pick a model at runtime with: $gadaj_teraz ollama <model>
# ($modele_ai lists what the server actually has pulled).
- { name: CONJURER_OLLAMA_URL, value: "http://192.168.1.72:11434" }
# The server currently has exactly one model pulled (verified via
# /v1/models): gemma4:e2b. Without this the built-in default
# (llama3.1:8b) would be requested and every reply would fail.
- { name: CONJURER_OLLAMA_MODEL, value: "gemma4:e2b" }
# Self-hosted generation is far slower than a hosted API, especially
# the first request after the model is evicted from VRAM. Applies to
# every backend, so keep it only as high as you actually need.
- { name: CONJURER_AI_TIMEOUT_SECONDS, value: "240" }
volumeMounts:
- { name: data, mountPath: /data }
- { name: netrc, mountPath: /secrets, readOnly: true }
+8
View File
@@ -56,6 +56,14 @@ spec:
# Pick a model at runtime with: $gadaj_teraz ollama <model>
# ($modele_ai lists what the server actually has pulled).
- { name: CONJURER_OLLAMA_URL, value: "http://192.168.1.72:11434" }
# The server currently has exactly one model pulled (verified via
# /v1/models): gemma4:e2b. Without this the built-in default
# (llama3.1:8b) would be requested and every reply would fail.
- { name: CONJURER_OLLAMA_MODEL, value: "gemma4:e2b" }
# Self-hosted generation is far slower than a hosted API, especially
# the first request after the model is evicted from VRAM. Applies to
# every backend, so keep it only as high as you actually need.
- { name: CONJURER_AI_TIMEOUT_SECONDS, value: "240" }
volumeMounts:
- { name: data, mountPath: /data }
- { name: netrc, mountPath: /secrets, readOnly: true }