28c729f1d4
- scripts/llm-server/: start/stop/status fuer llama.cpp-Server (Port 8001, GPU 1, Modell Qwen3.6-35B-A3B-Uncensored, Alias va_llm) - alles per ENV ueberschreibbar - Defaults auf den lokalen Server umgestellt (config.py, .example-Configs, .env.example) - Provider local-openai-compatible sprachoptimiert: Reasoning aus (chat_template_kwargs.enable_thinking=false) + knapper Sprach-System-Prompt, optional max_tokens/temperature - Antwort ~9x schneller, kurze vorlesbare Texte - Makefile-Targets llm-up/llm-down/llm-status - Doku (README, BEDIENUNGSANLEITUNG) auf llama.cpp statt Ollama aktualisiert Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
43 lines
1.1 KiB
Makefile
43 lines
1.1 KiB
Makefile
ifneq (,$(wildcard ./.env))
|
|
include .env
|
|
export
|
|
endif
|
|
|
|
PORT ?= 8080
|
|
HOST ?= 0.0.0.0
|
|
|
|
.PHONY: ensure-env install run test smoke docker-build llm-up llm-down llm-status
|
|
|
|
ensure-env:
|
|
@if [ ! -f .env ] && [ -f .env.example ]; then \
|
|
cp .env.example .env; \
|
|
echo "Created .env from .env.example"; \
|
|
fi
|
|
|
|
install: ensure-env
|
|
python3 -m venv .venv
|
|
. .venv/bin/activate && pip install -U pip && pip install -e .[test]
|
|
|
|
run: ensure-env
|
|
. .venv/bin/activate && uvicorn app.main:app --host $(HOST) --port $(PORT) --reload
|
|
|
|
test: ensure-env
|
|
. .venv/bin/activate && pytest tests/
|
|
|
|
# Echter End-to-End-Test gegen OpenRouter (macht Netz-Aufrufe, kostet wenig).
|
|
smoke: ensure-env
|
|
. .venv/bin/activate && python scripts/smoke_e2e.py
|
|
|
|
docker-build:
|
|
docker build -t voice-assistant-gateway .
|
|
|
|
# --- Lokales LLM (llama.cpp-Server, zentrale unzensierte KI) -----------------
|
|
# Konfig per ENV ueberschreibbar, z. B.: GPU_DEVICE=2 HOST_PORT=8101 make llm-up
|
|
llm-up:
|
|
bash scripts/llm-server/start-llm-server.sh
|
|
|
|
llm-down:
|
|
bash scripts/llm-server/stop-llm-server.sh
|
|
|
|
llm-status:
|
|
bash scripts/llm-server/status-llm-server.sh
|