Consolidated local ollama model logic
This commit is contained in:
Executable
+41
@@ -0,0 +1,41 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
ROOT_OVERRIDE="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
export ROOT_OVERRIDE
|
||||
# shellcheck disable=SC1091
|
||||
source "${ROOT_OVERRIDE}/scripts/common.sh"
|
||||
|
||||
init_log bootstrap-native
|
||||
acquire_lock jr-sql-ai-native-model.lock
|
||||
print_header "bootstrap-native: START"
|
||||
|
||||
need_cmd curl
|
||||
need_cmd python
|
||||
load_env
|
||||
need_cmd "$OLLAMA_BIN"
|
||||
check_for_legacy_docker_ollama
|
||||
[[ -n "$BASE_MODEL" ]] || fail "BASE_MODEL is empty" 50
|
||||
|
||||
log "bootstrap-native: ensuring local Ollama runtime is ready at ${OLLAMA_URL}"
|
||||
ensure_ollama_ready "$OLLAMA_API_MAX_WAIT" "$OLLAMA_API_START_WAIT" || fail "Ollama API not reachable at ${OLLAMA_URL}" 51
|
||||
ok "bootstrap-native: Ollama API reachable"
|
||||
|
||||
if fetch_version >/dev/null 2>&1; then
|
||||
ok "bootstrap-native: Ollama version endpoint reachable"
|
||||
fi
|
||||
|
||||
pull_configured_models
|
||||
|
||||
tmp="$(mktemp)"
|
||||
trap 'rm -f "$tmp"' EXIT
|
||||
render_modelfile "$tmp"
|
||||
|
||||
log "bootstrap-native: building expert model ${EXPERT_MODEL}"
|
||||
ollama_cmd create "${EXPERT_MODEL}" -f "$tmp"
|
||||
|
||||
verify_models_available
|
||||
ok "bootstrap-native: base and expert models are available"
|
||||
|
||||
warmup_sqlai
|
||||
print_footer "bootstrap-native: END status=OK log=${LOG_FILE}"
|
||||
Executable
+51
@@ -0,0 +1,51 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
LOG_DIR="${ROOT}/logs"
|
||||
mkdir -p "$LOG_DIR"
|
||||
LOG_FILE="${LOG_DIR}/cleanup-docker-ollama-$(date -Iseconds).log"
|
||||
exec > >(tee -a "$LOG_FILE") 2>&1
|
||||
|
||||
ts(){ date -Is; }
|
||||
log(){ echo "[$(ts)] $*"; }
|
||||
|
||||
log "cleanup-docker-ollama: START ROOT=${ROOT}"
|
||||
|
||||
if ! command -v docker >/dev/null 2>&1; then
|
||||
log "cleanup-docker-ollama: docker not installed; nothing to do"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if [[ -f "${ROOT}/docker-compose.yml" ]] && docker compose version >/dev/null 2>&1; then
|
||||
log "cleanup-docker-ollama: docker compose down --remove-orphans"
|
||||
docker compose -f "${ROOT}/docker-compose.yml" down --remove-orphans || true
|
||||
fi
|
||||
|
||||
if docker ps -a --format '{{.Names}}' | grep -qx 'ollama'; then
|
||||
log "cleanup-docker-ollama: removing container ollama"
|
||||
docker rm -f ollama || true
|
||||
else
|
||||
log "cleanup-docker-ollama: container ollama not present"
|
||||
fi
|
||||
|
||||
if docker images --format '{{.Repository}}:{{.Tag}}' | grep -qx 'ollama/ollama:latest'; then
|
||||
log "cleanup-docker-ollama: removing image ollama/ollama:latest"
|
||||
docker image rm -f ollama/ollama:latest || true
|
||||
else
|
||||
log "cleanup-docker-ollama: image ollama/ollama:latest not present"
|
||||
fi
|
||||
|
||||
if [[ "${PURGE_OLLAMA_DOCKER_VOLUMES:-0}" == "1" ]]; then
|
||||
mapfile -t volumes < <(docker volume ls --format '{{.Name}}' | grep -E 'ollama' || true)
|
||||
if (( ${#volumes[@]} > 0 )); then
|
||||
log "cleanup-docker-ollama: removing volumes: ${volumes[*]}"
|
||||
docker volume rm "${volumes[@]}" || true
|
||||
else
|
||||
log "cleanup-docker-ollama: no ollama volumes found"
|
||||
fi
|
||||
else
|
||||
log "cleanup-docker-ollama: keeping volumes (set PURGE_OLLAMA_DOCKER_VOLUMES=1 to remove them)"
|
||||
fi
|
||||
|
||||
log "cleanup-docker-ollama: END log=${LOG_FILE}"
|
||||
Executable
+287
@@ -0,0 +1,287 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
ROOT="${ROOT_OVERRIDE:-$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)}"
|
||||
ENV_FILE="${ENV_FILE:-${ROOT}/.env}"
|
||||
MODFILE="${MODFILE:-${ROOT}/Modelfile}"
|
||||
SQLAI_BIN="${SQLAI_BIN:-${ROOT}/bin/sqlai}"
|
||||
OLLAMA_BIN="${OLLAMA_BIN:-ollama}"
|
||||
LOG_FILE=""
|
||||
LOCK_FD=""
|
||||
|
||||
_ts_prefix(){ date -Is; }
|
||||
ts(){ _ts_prefix; }
|
||||
|
||||
log(){ echo "[$(ts)] $*"; }
|
||||
ok(){ log "OK $*"; }
|
||||
warn(){ log "WARN $*"; }
|
||||
fail(){
|
||||
local msg="$1"
|
||||
local code="${2:-1}"
|
||||
log "FAIL $msg"
|
||||
exit "$code"
|
||||
}
|
||||
|
||||
need_cmd(){
|
||||
command -v "$1" >/dev/null 2>&1 || fail "missing command: $1" 10
|
||||
}
|
||||
|
||||
init_log(){
|
||||
local name="$1"
|
||||
local log_dir="${ROOT}/logs"
|
||||
mkdir -p "$log_dir"
|
||||
LOG_FILE="${log_dir}/${name}-$(date -Iseconds).log"
|
||||
export LOG_FILE
|
||||
exec > >(tee -a "$LOG_FILE") 2>&1
|
||||
}
|
||||
|
||||
acquire_lock(){
|
||||
local name="${1:-jr-sql-ai-native.lock}"
|
||||
local wait_seconds="${LOCK_WAIT_SECONDS:-600}"
|
||||
local lock_dir="${ROOT}/.locks"
|
||||
mkdir -p "$lock_dir"
|
||||
local lock_path="${lock_dir}/${name}"
|
||||
|
||||
if command -v flock >/dev/null 2>&1; then
|
||||
exec 8>"$lock_path"
|
||||
flock -w "$wait_seconds" 8 || fail "could not acquire lock ${lock_path}" 11
|
||||
LOCK_FD="8"
|
||||
return 0
|
||||
fi
|
||||
|
||||
local i
|
||||
for ((i=0; i<wait_seconds; i++)); do
|
||||
if mkdir "$lock_path.lock" 2>/dev/null; then
|
||||
trap 'rmdir "'$lock_path'.lock" >/dev/null 2>&1 || true' EXIT
|
||||
return 0
|
||||
fi
|
||||
sleep 1
|
||||
done
|
||||
fail "could not acquire lock ${lock_path}.lock" 11
|
||||
}
|
||||
|
||||
load_env(){
|
||||
if [[ ! -f "$ENV_FILE" && -f "${ROOT}/.env.example" ]]; then
|
||||
cp -n "${ROOT}/.env.example" "$ENV_FILE" || true
|
||||
fi
|
||||
|
||||
if [[ -f "$ENV_FILE" ]]; then
|
||||
set -a
|
||||
# shellcheck disable=SC1090
|
||||
source "$ENV_FILE"
|
||||
set +a
|
||||
fi
|
||||
|
||||
: "${OLLAMA_URL:=http://127.0.0.1:11434}"
|
||||
: "${EXPERT_MODEL:=jr-sql-expert}"
|
||||
: "${BASE_MODEL:=}"
|
||||
: "${EXTRA_MODELS:=}"
|
||||
: "${OLLAMA_BIN:=ollama}"
|
||||
: "${OLLAMA_AUTOSTART:=1}"
|
||||
: "${OLLAMA_SERVE_FALLBACK:=1}"
|
||||
: "${OLLAMA_SYSTEMD_SERVICE:=ollama.service}"
|
||||
: "${OLLAMA_SYSTEMD_SCOPE:=auto}"
|
||||
: "${OLLAMA_API_MAX_WAIT:=120}"
|
||||
: "${OLLAMA_API_START_WAIT:=45}"
|
||||
export OLLAMA_URL EXPERT_MODEL BASE_MODEL EXTRA_MODELS OLLAMA_BIN OLLAMA_AUTOSTART OLLAMA_SERVE_FALLBACK OLLAMA_SYSTEMD_SERVICE OLLAMA_SYSTEMD_SCOPE OLLAMA_API_MAX_WAIT OLLAMA_API_START_WAIT
|
||||
|
||||
export OLLAMA_HOST="$OLLAMA_URL"
|
||||
}
|
||||
|
||||
is_json(){
|
||||
python -c 'import json,sys; json.load(sys.stdin)' >/dev/null 2>&1
|
||||
}
|
||||
|
||||
http_get(){
|
||||
local path="$1"
|
||||
curl -fsS --connect-timeout 3 --max-time 20 "${OLLAMA_URL}${path}"
|
||||
}
|
||||
|
||||
wait_for_ollama_api(){
|
||||
local max_wait="${1:-120}"
|
||||
local i
|
||||
for ((i=1; i<=max_wait; i++)); do
|
||||
if http_get "/api/tags" >/dev/null 2>&1; then
|
||||
return 0
|
||||
fi
|
||||
sleep 1
|
||||
done
|
||||
return 1
|
||||
}
|
||||
|
||||
fetch_tags(){
|
||||
http_get "/api/tags"
|
||||
}
|
||||
|
||||
fetch_version(){
|
||||
http_get "/api/version"
|
||||
}
|
||||
|
||||
model_in_tags(){
|
||||
local model="$1"
|
||||
local tags="$2"
|
||||
TAGS_JSON="$tags" python - "$model" <<'PY'
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
m = sys.argv[1]
|
||||
obj = json.loads(os.environ['TAGS_JSON'])
|
||||
names = {it.get('name') for it in obj.get('models', []) if it.get('name')}
|
||||
ok = (
|
||||
m in names or
|
||||
f"{m}:latest" in names or
|
||||
(m.endswith(':latest') and m[:-7] in names)
|
||||
)
|
||||
sys.exit(0 if ok else 1)
|
||||
PY
|
||||
}
|
||||
|
||||
render_modelfile(){
|
||||
local out_file="$1"
|
||||
[[ -f "$MODFILE" ]] || fail "Modelfile not found at $MODFILE" 20
|
||||
[[ -n "$BASE_MODEL" ]] || fail "BASE_MODEL is empty" 21
|
||||
|
||||
python - "$MODFILE" "$out_file" "$BASE_MODEL" <<'PY'
|
||||
from pathlib import Path
|
||||
import sys
|
||||
src = Path(sys.argv[1]).read_text(encoding='utf-8')
|
||||
out = src.replace('${BASE_MODEL}', sys.argv[3])
|
||||
Path(sys.argv[2]).write_text(out, encoding='utf-8')
|
||||
PY
|
||||
}
|
||||
|
||||
ollama_cmd(){
|
||||
OLLAMA_HOST="$OLLAMA_URL" "$OLLAMA_BIN" "$@"
|
||||
}
|
||||
|
||||
ollama_service_exists(){
|
||||
local scope="$1"
|
||||
if [[ "$scope" == "user" ]]; then
|
||||
systemctl --user cat "$OLLAMA_SYSTEMD_SERVICE" >/dev/null 2>&1
|
||||
else
|
||||
systemctl cat "$OLLAMA_SYSTEMD_SERVICE" >/dev/null 2>&1
|
||||
fi
|
||||
}
|
||||
|
||||
start_ollama_via_systemd(){
|
||||
command -v systemctl >/dev/null 2>&1 || return 1
|
||||
|
||||
if [[ "$OLLAMA_SYSTEMD_SCOPE" == "auto" || "$OLLAMA_SYSTEMD_SCOPE" == "user" ]]; then
|
||||
if ollama_service_exists user; then
|
||||
log "starting Ollama via systemd user service ${OLLAMA_SYSTEMD_SERVICE}"
|
||||
systemctl --user start "$OLLAMA_SYSTEMD_SERVICE"
|
||||
return 0
|
||||
fi
|
||||
fi
|
||||
|
||||
if [[ "$OLLAMA_SYSTEMD_SCOPE" == "auto" || "$OLLAMA_SYSTEMD_SCOPE" == "system" ]]; then
|
||||
if ollama_service_exists system; then
|
||||
log "starting Ollama via systemd system service ${OLLAMA_SYSTEMD_SERVICE}"
|
||||
systemctl start "$OLLAMA_SYSTEMD_SERVICE"
|
||||
return 0
|
||||
fi
|
||||
fi
|
||||
|
||||
return 1
|
||||
}
|
||||
|
||||
start_ollama_fallback(){
|
||||
[[ "$OLLAMA_SERVE_FALLBACK" == "1" ]] || return 1
|
||||
|
||||
if pgrep -fa '(^|/)ollama( |$).*serve' >/dev/null 2>&1; then
|
||||
warn "ollama serve process already exists but API is not reachable yet"
|
||||
return 0
|
||||
fi
|
||||
|
||||
local serve_log="${ROOT}/logs/ollama-serve-fallback.log"
|
||||
mkdir -p "${ROOT}/logs"
|
||||
log "starting Ollama via detached fallback process (${OLLAMA_BIN} serve)"
|
||||
nohup env OLLAMA_HOST="$OLLAMA_URL" "$OLLAMA_BIN" serve >>"$serve_log" 2>&1 &
|
||||
return 0
|
||||
}
|
||||
|
||||
ensure_ollama_ready(){
|
||||
local max_wait="${1:-$OLLAMA_API_MAX_WAIT}"
|
||||
local start_wait="${2:-$OLLAMA_API_START_WAIT}"
|
||||
|
||||
if wait_for_ollama_api 3; then
|
||||
return 0
|
||||
fi
|
||||
|
||||
[[ "$OLLAMA_AUTOSTART" == "1" ]] || return 1
|
||||
|
||||
if start_ollama_via_systemd; then
|
||||
wait_for_ollama_api "$start_wait" && return 0
|
||||
warn "Ollama service start issued, but API is still not reachable"
|
||||
fi
|
||||
|
||||
if start_ollama_fallback; then
|
||||
wait_for_ollama_api "$max_wait" && return 0
|
||||
fi
|
||||
|
||||
return 1
|
||||
}
|
||||
|
||||
iter_models(){
|
||||
if [[ -n "$BASE_MODEL" ]]; then
|
||||
printf '%s\n' "$BASE_MODEL"
|
||||
fi
|
||||
if [[ -n "$EXTRA_MODELS" ]]; then
|
||||
printf '%s\n' "$EXTRA_MODELS" | tr ' ' '\n' | sed '/^$/d'
|
||||
fi
|
||||
}
|
||||
|
||||
pull_configured_models(){
|
||||
local model
|
||||
while IFS= read -r model; do
|
||||
[[ -n "$model" ]] || continue
|
||||
log "pulling model ${model}"
|
||||
ollama_cmd pull "$model"
|
||||
done < <(iter_models)
|
||||
}
|
||||
|
||||
check_for_legacy_docker_ollama(){
|
||||
if ! command -v docker >/dev/null 2>&1; then
|
||||
return 0
|
||||
fi
|
||||
|
||||
if docker ps --format '{{.Names}}' | grep -qx 'ollama'; then
|
||||
fail "legacy docker container 'ollama' is still running; run cleanup-docker-ollama.sh first" 30
|
||||
fi
|
||||
|
||||
if docker ps -a --format '{{.Names}}' | grep -qx 'ollama'; then
|
||||
warn "legacy docker container 'ollama' still exists in stopped state; cleanup recommended"
|
||||
fi
|
||||
|
||||
if docker images --format '{{.Repository}}:{{.Tag}}' | grep -qx 'ollama/ollama:latest'; then
|
||||
warn "legacy docker image ollama/ollama:latest still exists; cleanup recommended"
|
||||
fi
|
||||
}
|
||||
|
||||
warmup_sqlai(){
|
||||
if [[ -x "$SQLAI_BIN" ]]; then
|
||||
log "warmup via ${SQLAI_BIN}"
|
||||
"$SQLAI_BIN" ask --text "Warmup: reply with exactly 'OK'." --no-metrics || warn "warmup failed"
|
||||
else
|
||||
warn "${SQLAI_BIN} not executable; skipping warmup"
|
||||
fi
|
||||
}
|
||||
|
||||
verify_models_available(){
|
||||
local tags
|
||||
tags="$(fetch_tags)"
|
||||
printf '%s' "$tags" | is_json || fail "/api/tags did not return valid JSON" 40
|
||||
|
||||
[[ -z "$BASE_MODEL" ]] || model_in_tags "$BASE_MODEL" "$tags" || fail "base model missing: ${BASE_MODEL}" 41
|
||||
model_in_tags "$EXPERT_MODEL" "$tags" || fail "expert model missing: ${EXPERT_MODEL}" 42
|
||||
}
|
||||
|
||||
print_header(){
|
||||
echo "================================================================================"
|
||||
log "$1 ROOT=$ROOT"
|
||||
}
|
||||
|
||||
print_footer(){
|
||||
log "$1"
|
||||
echo "================================================================================"
|
||||
}
|
||||
Executable
+54
@@ -0,0 +1,54 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
ROOT_OVERRIDE="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
export ROOT_OVERRIDE
|
||||
# shellcheck disable=SC1091
|
||||
source "${ROOT_OVERRIDE}/scripts/common.sh"
|
||||
|
||||
init_log selftest-native
|
||||
acquire_lock jr-sql-ai-native-model.lock
|
||||
print_header "selftest-native: START"
|
||||
|
||||
load_env
|
||||
need_cmd curl
|
||||
need_cmd python
|
||||
need_cmd "$OLLAMA_BIN"
|
||||
need_cmd grep
|
||||
check_for_legacy_docker_ollama
|
||||
[[ -x "$SQLAI_BIN" ]] || fail "bin/sqlai missing or not executable at ${SQLAI_BIN}" 70
|
||||
|
||||
log "selftest-native: ensuring local Ollama runtime is ready at ${OLLAMA_URL}"
|
||||
ensure_ollama_ready "$OLLAMA_API_MAX_WAIT" "$OLLAMA_API_START_WAIT" || fail "Ollama API not reachable at ${OLLAMA_URL}" 71
|
||||
ok "selftest-native: Ollama API reachable"
|
||||
|
||||
tags="$(fetch_tags)"
|
||||
[[ -n "$tags" ]] || fail "/api/tags returned empty body" 72
|
||||
printf '%s' "$tags" | is_json || fail "/api/tags did not return valid JSON" 73
|
||||
ok "selftest-native: /api/tags returned valid JSON"
|
||||
|
||||
model_in_tags "$EXPERT_MODEL" "$tags" || fail "expert model missing: ${EXPERT_MODEL}" 74
|
||||
ok "selftest-native: expert model present: ${EXPERT_MODEL}"
|
||||
|
||||
if [[ -n "$BASE_MODEL" ]]; then
|
||||
model_in_tags "$BASE_MODEL" "$tags" || fail "base model missing: ${BASE_MODEL}" 75
|
||||
ok "selftest-native: base model present: ${BASE_MODEL}"
|
||||
fi
|
||||
|
||||
log "selftest-native: warmup request via sqlai"
|
||||
set +e
|
||||
"$SQLAI_BIN" ask --text "Warmup: reply with exactly 'OK'." --no-metrics >/dev/null 2>&1
|
||||
rc=$?
|
||||
set -e
|
||||
[[ "$rc" -eq 0 ]] || warn "warmup failed rc=${rc}"
|
||||
|
||||
log "selftest-native: real query via sqlai"
|
||||
set +e
|
||||
out="$("$SQLAI_BIN" ask --text "Give a concise checklist to troubleshoot parameter sniffing in SQL Server 2022. Keep it technical." --no-metrics 2>&1)"
|
||||
rc=$?
|
||||
set -e
|
||||
[[ "$rc" -eq 0 ]] || fail "real query failed rc=${rc}" 76
|
||||
[[ -n "${out//[[:space:]]/}" ]] || fail "real query returned empty output" 77
|
||||
ok "selftest-native: real query returned non-empty output"
|
||||
|
||||
print_footer "selftest-native: END status=OK log=${LOG_FILE}"
|
||||
+1
-1
@@ -8,7 +8,7 @@ export QT_QPA_PLATFORM="${QT_QPA_PLATFORM:-wayland}"
|
||||
|
||||
# Optional: Wenn du einen venv nutzt
|
||||
if [[ -x "$APP_DIR/.venv/bin/python" ]]; then
|
||||
exec "$APP_DIR/.venv/bin/python" "$APP_DIR/sql_ai_gui.py"
|
||||
exec "$APP_DIR/.venv/bin/python" "$APP_DIR/sql_ai_gui_local_ollama.py"
|
||||
else
|
||||
exec python "$APP_DIR/sql_ai_gui.py"
|
||||
fi
|
||||
|
||||
Executable
+37
@@ -0,0 +1,37 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
ROOT_OVERRIDE="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
export ROOT_OVERRIDE
|
||||
# shellcheck disable=SC1091
|
||||
source "${ROOT_OVERRIDE}/scripts/common.sh"
|
||||
|
||||
init_log update-native
|
||||
acquire_lock jr-sql-ai-native-model.lock
|
||||
print_header "update-native: START"
|
||||
|
||||
load_env
|
||||
need_cmd curl
|
||||
need_cmd python
|
||||
need_cmd "$OLLAMA_BIN"
|
||||
check_for_legacy_docker_ollama
|
||||
[[ -n "$BASE_MODEL" ]] || fail "BASE_MODEL is empty" 60
|
||||
|
||||
log "update-native: ensuring local Ollama runtime is ready at ${OLLAMA_URL}"
|
||||
ensure_ollama_ready "$OLLAMA_API_MAX_WAIT" "$OLLAMA_API_START_WAIT" || fail "Ollama API not reachable at ${OLLAMA_URL}" 61
|
||||
ok "update-native: Ollama API reachable"
|
||||
|
||||
pull_configured_models
|
||||
|
||||
tmp="$(mktemp)"
|
||||
trap 'rm -f "$tmp"' EXIT
|
||||
render_modelfile "$tmp"
|
||||
|
||||
log "update-native: rebuilding expert model ${EXPERT_MODEL}"
|
||||
ollama_cmd create "${EXPERT_MODEL}" -f "$tmp"
|
||||
|
||||
verify_models_available
|
||||
ok "update-native: base and expert models are available"
|
||||
|
||||
warmup_sqlai
|
||||
print_footer "update-native: END status=OK log=${LOG_FILE}"
|
||||
Reference in New Issue
Block a user