gortium/infra
1
1
Fork 0
Code Issues 13 Pull Requests 21 Actions Packages Projects 1 Releases Wiki Activity

Add restricted AI worker access with deployment capabilities #1

Merged
gortium merged 10 commits from ai-worker-restricted-access into master 2026-05-11 00:48:30 +00:00
Conversation 0 Commits 10 Files Changed 9 +322 -124
11 changed files with 322 additions and 124 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit f722af7803 - Show all commits

96
modules/nixos/services/ollama_init_custom_models.nix
View File

@@ -1,67 +1,87 @@
{ pkgs, ... }: {
systemd.services.init-ollama-model = {
description = "Initialize LLM models with extra context in Ollama Docker";
after = [ "docker-ollama.service" ];
# On s'assure que Docker tourne avant de lancer ce script
after = [ "docker.service" ];
wantedBy = [ "multi-user.target" ];
script = ''
# Wait for Ollama
while ! ${pkgs.curl}/bin/curl -s http://localhost:11434/api/tags > /dev/null; do
sleep 2
done
# Fonction de création asynchrone pour ne pas bloquer le démarrage
(
echo "Starting asynchronous Ollama initialization..."
# Attente d'Ollama (maximum 120 secondes pour éviter une boucle infinie)
TIMEOUT=60
COUNT=0
while ! ${pkgs.curl}/bin/curl -s -f http://127.0.0.1:11434/api/tags > /dev/null; do
if [ $COUNT -ge $TIMEOUT ]; then
echo "Ollama did not become ready in time. Exiting."
exit 1
fi
echo "Waiting for Ollama API to be reachable..."
sleep 5
COUNT=$((COUNT + 5))
done
create_model_if_missing() {
local model_name=$1
local base_model=$2
if ! ${pkgs.docker}/bin/docker exec ollama ollama list | grep -q "$model_name"; then
echo "$model_name not found, creating from $base_model..."
create_model_if_missing() {
local model_name=$1
local base_model=$2
# We use a custom TEMPLATE block to strip the 'currentDate' function
# which is unsupported in Ollama 0.5.7 but present in Devstral's default manifest.
${pkgs.docker}/bin/docker exec ollama sh -c "cat <<EOF > /root/.ollama/$model_name.modelfile
# Vérification robuste via l'API HTTP d'Ollama plutôt que docker exec (évite les conflits de tty)
if ! ${pkgs.curl}/bin/curl -s http://127.0.0.1:11434/api/tags | ${pkgs.jq}/bin/jq -e ".models[] | select(.name == \"$model_name\")" > /dev/null; then
echo "$model_name not found, creating from $base_model..."
# Utilisation d'un fichier temporaire sur l'hôte pour l'injecter proprement dans Docker
TMP_FILE=$(mktemp)
cat <<EOF > "$TMP_FILE"
FROM $base_model
TEMPLATE \"\"\"{{- if .System }}
TEMPLATE """{{- if .System }}
[SYSTEM_PROMPT]
{{ .System }}
[/SYSTEM_PROMPT]
{{- end }}
{{- range .Messages }}
{{- if eq .Role \"user\" }}
{{- if eq .Role "user" }}
[INST]
{{ .Content }}
[/INST]
{{- else if eq .Role \"assistant\" }}
{{- else if eq .Role "assistant" }}
{{ .Content }}
{{- end }}
{{- end }}\"\"\"
{{- end }}"""
PARAMETER num_ctx 131072
PARAMETER num_predict 4096
PARAMETER num_keep 1024
PARAMETER repeat_penalty 1.1
PARAMETER top_k 40
PARAMETER stop \"[INST]\"
PARAMETER stop \"[/INST]\"
PARAMETER stop \"</s>\"
EOF"
${pkgs.docker}/bin/docker exec ollama ollama create "$model_name" -f "/root/.ollama/$model_name.modelfile"
${pkgs.docker}/bin/docker exec ollama rm "/root/.ollama/$model_name.modelfile"
else
echo "$model_name already exists, skipping."
fi
}
PARAMETER stop "[INST]"
PARAMETER stop "[/INST]"
PARAMETER stop "</s>"
EOF
# Create Nemotron
create_model_if_missing "nemotron-3-nano:30b-128k" "nemotron-3-nano:30b"
# Create Devstral
create_model_if_missing "devstral-small-2:24b-128k" "devstral-small-2:24b"
# create_model_if_missing "qwen2.5-coder:32b-128k" "qwen2.5-coder:32b"
# create_model_if_missing "mistral-large-planner:123b" "mistral-large:123b-instruct-v2407-q4_K_S"
# Copie et création dans le conteneur
${pkgs.docker}/bin/docker cp "$TMP_FILE" ollama:/tmp/model.modelfile
${pkgs.docker}/bin/docker exec ollama ollama create "$model_name" -f /tmp/model.modelfile
${pkgs.docker}/bin/docker exec ollama rm /tmp/model.modelfile
rm -f "$TMP_FILE"
else
echo "$model_name already exists, skipping."
fi
}
# Create Nemotron
create_model_if_missing "nemotron-3-nano:30b-128k" "nemotron-3-nano:30b"
# Create Devstral
create_model_if_missing "devstral-small-2:24b-128k" "devstral-small-2:24b"
) &
'';
serviceConfig = {
Type = "oneshot";
RemainAfterExit = true;
Type = "forking"; # Permet à systemd de savoir que le script passe en arrière-plan via '&'
User = "root";
};
};
}