curo1305
c4f0c7ad49
- Introduce async priority queue service in ai-service; all /chat calls now route through it - Refactor chat router to separate execute_chat (core logic) from the HTTP handler - Add /queue endpoints (status, pause, resume, cancel) for queue management - Update ai-service config to use Pydantic v2 model_config style - Add STATUS.md files for backend, ai-service, doc-service, and frontend - Document STATUS.md workflow in CLAUDE.md - Update doc-service documents router and schemas; frontend DocumentsPage and API client Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
82 lines
2.3 KiB
Python
82 lines
2.3 KiB
Python
"""
|
|
Reads ai_service_config.json from the shared config volume.
|
|
30-second TTL cache + env var overrides (dev credentials stay out of git).
|
|
|
|
Env var overrides (all optional):
|
|
AI_PROVIDER — "lmstudio" | "ollama" | "anthropic"
|
|
LMSTUDIO_BASE_URL, LMSTUDIO_API_KEY, LMSTUDIO_MODEL
|
|
OLLAMA_BASE_URL, OLLAMA_MODEL, OLLAMA_API_KEY
|
|
ANTHROPIC_API_KEY, ANTHROPIC_MODEL
|
|
"""
|
|
import asyncio
|
|
import json
|
|
import os
|
|
import time
|
|
from copy import deepcopy
|
|
from pathlib import Path
|
|
|
|
from app.core.config import settings
|
|
|
|
_DEFAULT_CONFIG: dict = {
|
|
"provider": "lmstudio",
|
|
"timeout_seconds": 60,
|
|
"max_retries": 2,
|
|
"anthropic": {"api_key": "", "model": "claude-haiku-4-5-20251001"},
|
|
"ollama": {"base_url": "http://host.docker.internal:11434/v1", "model": "llama3.2", "api_key": "ollama"},
|
|
"lmstudio": {"base_url": "http://host.docker.internal:1234/v1", "model": "gemma-4-e4b-it", "api_key": "lm-studio"},
|
|
}
|
|
|
|
_cache: dict | None = None
|
|
_cache_at: float = 0.0
|
|
_CACHE_TTL = 30.0
|
|
|
|
|
|
def _read_config_sync() -> dict:
|
|
path = Path(settings.CONFIG_PATH)
|
|
if not path.exists():
|
|
return _apply_env_overrides(deepcopy(_DEFAULT_CONFIG))
|
|
with open(path) as f:
|
|
return _apply_env_overrides(json.load(f))
|
|
|
|
|
|
def _apply_env_overrides(config: dict) -> dict:
|
|
cfg = deepcopy(config)
|
|
|
|
if v := os.environ.get("AI_PROVIDER"):
|
|
cfg["provider"] = v
|
|
|
|
lms = cfg.setdefault("lmstudio", {})
|
|
if v := os.environ.get("LMSTUDIO_BASE_URL"):
|
|
lms["base_url"] = v
|
|
if v := os.environ.get("LMSTUDIO_API_KEY"):
|
|
lms["api_key"] = v
|
|
if v := os.environ.get("LMSTUDIO_MODEL"):
|
|
lms["model"] = v
|
|
|
|
oll = cfg.setdefault("ollama", {})
|
|
if v := os.environ.get("OLLAMA_BASE_URL"):
|
|
oll["base_url"] = v
|
|
if v := os.environ.get("OLLAMA_MODEL"):
|
|
oll["model"] = v
|
|
if v := os.environ.get("OLLAMA_API_KEY"):
|
|
oll["api_key"] = v
|
|
|
|
ant = cfg.setdefault("anthropic", {})
|
|
if v := os.environ.get("ANTHROPIC_API_KEY"):
|
|
ant["api_key"] = v
|
|
if v := os.environ.get("ANTHROPIC_MODEL"):
|
|
ant["model"] = v
|
|
|
|
return cfg
|
|
|
|
|
|
async def load_ai_config() -> dict:
|
|
global _cache, _cache_at
|
|
now = time.monotonic()
|
|
if _cache is not None and (now - _cache_at) < _CACHE_TTL:
|
|
return _cache
|
|
data = await asyncio.to_thread(_read_config_sync)
|
|
_cache = data
|
|
_cache_at = now
|
|
return data
|