Deploy public LiteLLM on US DC1 with preserved HK routes
This commit is contained in:
Codex
@@ -0,0 +1,175 @@
|
||||
"""Render only credential-ready routes; credentials remain environment references."""
|
||||
import os
|
||||
import json
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
import yaml
|
||||
|
||||
|
||||
def oauth_ready(path):
|
||||
try:
|
||||
record = json.loads(path.read_text())
|
||||
return isinstance(record, dict) and bool(record.get('access_token'))
|
||||
except (OSError, ValueError):
|
||||
return False
|
||||
|
||||
|
||||
def namespace_config(config):
|
||||
"""Add explicit provider names without removing existing client aliases."""
|
||||
routes = config['model_list']
|
||||
existing = {r['model_name']: r for r in routes}
|
||||
fallbacks = config['router_settings']['fallbacks']
|
||||
automatic = {name for group in fallbacks for name in group}
|
||||
renamed = {}
|
||||
|
||||
def clone(route, alias):
|
||||
if alias in existing:
|
||||
if existing[alias]['litellm_params'] != route['litellm_params']:
|
||||
raise ValueError('Conflicting namespace alias: ' + alias)
|
||||
return
|
||||
new = deepcopy(route)
|
||||
new['model_name'] = alias
|
||||
existing[alias] = new
|
||||
routes.append(new)
|
||||
|
||||
for route in list(routes):
|
||||
alias = route['model_name']
|
||||
model = route['litellm_params']['model']
|
||||
if alias in {'gemini-3.6-flash', 'gemini-3.5-flash-lite',
|
||||
'google/gemini-embedding-2', 'google/gemini-3.8-flash'}:
|
||||
continue
|
||||
if alias.endswith('-openrouter'):
|
||||
new = 'openrouter/' + alias.removesuffix('-openrouter')
|
||||
elif alias in automatic:
|
||||
new = 'auto/' + alias
|
||||
clone(route, 'zenmux/' + alias)
|
||||
elif model.startswith('anthropic/'):
|
||||
new = ('zenmux-payg/' + alias.removesuffix('-payg')
|
||||
if alias.endswith('-payg') else 'zenmux/' + alias)
|
||||
elif model.startswith('openai/'):
|
||||
name = model.removeprefix('openai/').split('/', 1)[-1]
|
||||
new = 'zenmux/' + (name if alias.startswith('asr-') else
|
||||
alias.replace('-zenmux', '-latest'))
|
||||
elif model.startswith('openrouter/'):
|
||||
new = 'openrouter/' + alias
|
||||
elif model.startswith('gemini/'):
|
||||
new = 'aistudio/' + alias.removesuffix('-studio')
|
||||
elif model.startswith('vertex_ai/'):
|
||||
name = {'google-rerank-default': 'rerank-default-latest',
|
||||
'google-rerank-fast': 'rerank-fast-latest'}.get(alias,
|
||||
alias.replace('-vertex', '-latest'))
|
||||
new = 'vertex/' + name
|
||||
elif model.startswith('chatgpt/'):
|
||||
name = model.split('/', 1)[1] if alias in {'gpt-work-sol', 'gpt-review-5.5'} else alias
|
||||
new = 'codex/' + name
|
||||
elif model.startswith('xai/'):
|
||||
new = 'xai/' + alias
|
||||
else:
|
||||
raise ValueError('Unrecognized namespace provider: ' + alias)
|
||||
clone(route, new)
|
||||
renamed[alias] = new
|
||||
for group in list(fallbacks):
|
||||
for source, targets in group.items():
|
||||
fallbacks.append({renamed[source]: [renamed[target] for target in targets]})
|
||||
return config
|
||||
|
||||
|
||||
def add_bailian_routes(config, env, vocabulary_path):
|
||||
if env.get('BAILIAN_CN_API_KEY'):
|
||||
base = env.get('BAILIAN_CN_API_BASE')
|
||||
if not base:
|
||||
raise ValueError('BAILIAN_CN_API_BASE required for Beijing Bailian')
|
||||
for personal in [False, True]:
|
||||
params = {'model': 'dashscope/qwen-audio-3.1-asr-flash',
|
||||
'api_base': base, 'api_key': 'os.environ/BAILIAN_CN_API_KEY',
|
||||
'max_retries': 0}
|
||||
if personal:
|
||||
params['bailian_vocabulary_path'] = vocabulary_path
|
||||
config['model_list'].append({'model_name': 'bailian-cn/qwen-audio-3.1-asr-flash' +
|
||||
('-personal' if personal else ''), 'litellm_params': params})
|
||||
return config
|
||||
|
||||
|
||||
def build_config(catalog, env, exists, namespaced=True):
|
||||
routes = []
|
||||
fallbacks = []
|
||||
|
||||
def add(alias, model, key=None, **params):
|
||||
if key:
|
||||
params['api_key'] = 'os.environ/' + key
|
||||
routes.append({'model_name': alias, 'litellm_params': {'model': model, **params}})
|
||||
|
||||
for key, suffix in [('ZENMUX_SUBSCRIPTION_API_KEY', ''), ('ZENMUX_PAYG_API_KEY', '-payg')]:
|
||||
if env.get(key):
|
||||
for alias, model in catalog['zenmux'].items():
|
||||
# Strip only the LiteLLM provider prefix, retaining ZenMux's vendor prefix.
|
||||
add(alias + suffix, 'anthropic/' + model, key,
|
||||
api_base='https://zenmux.ai/api/anthropic')
|
||||
if env.get('ZENMUX_SUBSCRIPTION_API_KEY'):
|
||||
for alias, model in catalog.get('zenmux_chat', {}).items():
|
||||
add(alias, 'openai/' + model, 'ZENMUX_SUBSCRIPTION_API_KEY',
|
||||
api_base='https://zenmux.ai/api/v1')
|
||||
if env.get('OPENROUTER_API_KEY'):
|
||||
for alias, model in catalog['openrouter'].items():
|
||||
primary = catalog.get('zenmux_open_models', {}).get(alias)
|
||||
if primary and env.get('ZENMUX_SUBSCRIPTION_API_KEY'):
|
||||
if primary != model:
|
||||
raise ValueError('Cross-provider model mismatch: ' + alias)
|
||||
add(alias, 'openai/' + primary, 'ZENMUX_SUBSCRIPTION_API_KEY',
|
||||
api_base='https://zenmux.ai/api/v1', max_retries=0)
|
||||
routes[-1]['model_info'] = {'cooldown_time': 60,
|
||||
'allowed_fails_policy': {'RateLimitErrorAllowedFails': 0,
|
||||
'AuthenticationErrorAllowedFails': 0,
|
||||
'InternalServerErrorAllowedFails': 0,
|
||||
'ServiceUnavailableErrorAllowedFails': 0,
|
||||
'TimeoutErrorAllowedFails': 0}}
|
||||
add(alias + '-openrouter', 'openrouter/' + model, 'OPENROUTER_API_KEY')
|
||||
fallbacks.append({alias: [alias + '-openrouter']})
|
||||
else:
|
||||
add(alias, 'openrouter/' + model, 'OPENROUTER_API_KEY')
|
||||
elif env.get('ZENMUX_SUBSCRIPTION_API_KEY'):
|
||||
for alias, model in catalog.get('zenmux_open_models', {}).items():
|
||||
add(alias, 'openai/' + model, 'ZENMUX_SUBSCRIPTION_API_KEY',
|
||||
api_base='https://zenmux.ai/api/v1', max_retries=0)
|
||||
if env.get('GOOGLE_AI_STUDIO_API_KEY'):
|
||||
add('gemini-transcribe-personal', 'gemini/gemini-3.5-transcribe',
|
||||
'GOOGLE_AI_STUDIO_API_KEY', personal_vocabulary=True)
|
||||
for alias, model in catalog['google_ai_studio'].items():
|
||||
add(alias, 'gemini/' + model, 'GOOGLE_AI_STUDIO_API_KEY')
|
||||
if env.get('VERTEXAI_ENABLED', '').lower() == 'true' and env.get('VERTEXAI_PROJECT'):
|
||||
for alias, model in catalog.get('google_vertex', {}).items():
|
||||
add(alias, 'vertex_ai/' + model,
|
||||
vertex_project='os.environ/VERTEXAI_PROJECT',
|
||||
vertex_location='os.environ/VERTEXAI_LOCATION')
|
||||
for provider, token_var, default_dir in [
|
||||
('chatgpt', 'CHATGPT_TOKEN_DIR', '/tokens/chatgpt'),
|
||||
('xai', 'XAI_OAUTH_TOKEN_DIR', '/tokens/xai'),
|
||||
]:
|
||||
if exists(Path(env.get(token_var, default_dir)) / 'auth.json'):
|
||||
for alias, model in catalog[provider].items():
|
||||
extra = {'use_xai_oauth': True} if provider == 'xai' else {}
|
||||
add(alias, provider + '/' + model, **extra)
|
||||
config = {
|
||||
'model_list': routes,
|
||||
'general_settings': {
|
||||
'master_key': 'os.environ/LITELLM_MASTER_KEY',
|
||||
'database_url': 'os.environ/DATABASE_URL',
|
||||
'store_model_in_db': False,
|
||||
'disable_env_credential_login': True,
|
||||
},
|
||||
'litellm_settings': {'drop_params': False, 'set_verbose': False},
|
||||
# Only explicitly approved open-model routes have cross-provider fallbacks.
|
||||
'router_settings': {'num_retries': 1, 'timeout': 180, 'fallbacks': fallbacks},
|
||||
}
|
||||
return add_bailian_routes(namespace_config(config), env,
|
||||
'/etc/litellm/personal-vocabulary.json') if namespaced else config
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
catalog = yaml.safe_load(Path('/etc/litellm/models.yaml').read_text())
|
||||
config = build_config(catalog, os.environ, oauth_ready)
|
||||
output = Path('/tmp/litellm.yaml')
|
||||
output.write_text(yaml.safe_dump(config, allow_unicode=True, sort_keys=False))
|
||||
output.chmod(0o600)
|
||||
print('Configured routes:', ', '.join(route['model_name'] for route in config['model_list']))
|
||||
Reference in New Issue
Block a user