Deploy public LiteLLM on US DC1 with preserved HK routes

2026-10-28 19:12:03 -07:00
parent 81c475464e
commit df391cd41f
12 changed files with 741 additions and 0 deletions
@@ -0,0 +1,68 @@
+"""HK-compatible public routes on DC1, with separately named official OpenAI API."""
+import os
+from pathlib import Path
+
+import yaml
+
+from provider_routes import build_config, namespace_config, add_bailian_routes
+
+
+def build_hk_config(catalog, env):
+    config = build_config(catalog, env, lambda path: False, namespaced=False)
+    config['general_settings'] = {'master_key': 'os.environ/LITELLM_MASTER_KEY'}
+    routes = config['model_list']
+    routes[:] = [route for route in routes if route['model_name'] != 'gemini-transcribe-personal']
+    if env.get('ZENMUX_SUBSCRIPTION_API_KEY'):
+        asr_models = {
+            'asr-gpt': 'openai/gpt-transcribe',
+            'asr-qwen': 'qwen/qwen-audio-3.1-asr-flash',
+            'asr-doubao': 'bytedance/doubao-seed-asr-2.0',
+            'asr-mimo': 'xiaomi/mimo-v2.5-asr',
+        }
+        for alias, model in asr_models.items():
+            routes.append({'model_name': alias, 'litellm_params': {
+                'model': 'openai/' + model,
+                'api_key': 'os.environ/ZENMUX_SUBSCRIPTION_API_KEY',
+                'api_base': 'https://zenmux.ai/api/v1',
+                'max_retries': 0}})
+    if env.get('GOOGLE_AI_STUDIO_API_KEY'):
+        routes.append({'model_name': 'gemini-transcribe', 'litellm_params': {
+            'model': 'gemini/gemini-3.5-transcribe',
+            'api_key': 'os.environ/GOOGLE_AI_STUDIO_API_KEY'}})
+    if env.get('VERTEXAI_ENABLED', '').lower() == 'true' and env.get('VERTEXAI_PROJECT'):
+        routes.append({'model_name': 'gemini-transcribe-personal', 'litellm_params': {
+            'model': 'vertex_ai/gemini-3.5-transcribe',
+            'vertex_project': 'os.environ/VERTEXAI_PROJECT',
+            'vertex_location': 'global',
+            'personal_dictation': True}})
+        # Keep old client aliases; the old 3.6 alias now follows the verified Flash map.
+        legacy = {
+            'gemini-3.6-flash': catalog['google_vertex']['gemini-flash-vertex'],
+            'gemini-3.5-flash-lite': catalog['google_vertex']['gemini-flash-lite-vertex'],
+            'google/gemini-embedding-2': 'gemini-embedding-2',
+            'google/gemini-3.8-flash': catalog['google_vertex']['gemini-flash-vertex'],
+        }
+        for alias, model in legacy.items():
+            routes.append({'model_name': alias, 'litellm_params': {
+                'model': 'vertex_ai/' + model,
+                'vertex_project': 'os.environ/VERTEXAI_PROJECT',
+                'vertex_location': 'os.environ/VERTEXAI_LOCATION'}})
+    config = add_bailian_routes(namespace_config(config), env, '/credentials/personal-vocabulary.json')
+    if env.get('OPENAI_API_KEY'):
+        models = dict(catalog.get('openai', {}))
+        for alias, model in catalog.get('chatgpt', {}).items():
+            models[alias if alias.endswith('-latest') else model] = model
+        for alias, model in models.items():
+            config['model_list'].append({'model_name': 'openai/' + alias, 'litellm_params': {
+                'model': 'openai/' + model, 'api_base': 'https://api.openai.com/v1',
+                'api_key': 'os.environ/OPENAI_API_KEY', 'max_retries': 0}})
+    return config
+
+
+if __name__ == '__main__':
+    catalog = yaml.safe_load(Path('/etc/litellm/models.yaml').read_text())
+    config = build_hk_config(catalog, os.environ)
+    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']))