more proxy stats

config/config.yml

@@ -8,4 +8,7 @@ concurrent_gens: 3
 
 backend_url: http://172.0.0.2:9104
 
+# Path that is shown to users for them to connect to
+frontend_api_client: /api
+
 database_path: ./proxy-server.db

llm_server/opts.py

@@ -8,3 +8,4 @@ token_limit = 5555
 database_path = './proxy-server.db'
 auth_required = False
 log_prompts = False
+frontend_api_client = ''

llm_server/routes/v1/proxy.py

@@ -1,7 +1,7 @@
 import time
 from datetime import datetime
 
-from flask import jsonify
+from flask import jsonify, request
 
 from llm_server import opts
 from llm_server.routes.v1.generate import concurrent_semaphore
@@ -31,5 +31,7 @@ def get_stats():
         'uptime': int((datetime.now() - stats.start_time).total_seconds()),
         'online': online,
         'mode': opts.mode,
+        'model': get_running_model(),
+        'client': f'https://{request.headers.get("Host")}/{opts.frontend_api_client.strip("/")}',
         'timestamp': int(time.time())
     }), 200

server.py

@@ -22,7 +22,7 @@ if config_path_environ:
 else:
     config_path = Path(script_path, 'config', 'config.yml')
 
-default_vars = {'mode': 'oobabooga', 'log_prompts': False, 'database_path': './proxy-server.db', 'auth_required': False, 'concurrent_gens': 3}
+default_vars = {'mode': 'oobabooga', 'log_prompts': False, 'database_path': './proxy-server.db', 'auth_required': False, 'concurrent_gens': 3, 'frontend_api_client': ''}
 required_vars = []
 config_loader = ConfigLoader(config_path, default_vars, required_vars)
 success, config, msg = config_loader.load_config()
@@ -45,6 +45,7 @@ opts.mode = config['mode']
 opts.auth_required = config['auth_required']
 opts.log_prompts = config['log_prompts']
 opts.concurrent_gens = config['concurrent_gens']
+opts.frontend_api_client = config['frontend_api_client']
 
 app = Flask(__name__)
 cache.init_app(app)