fixed config issue

.idea/misc.xml

@@ -3,7 +3,7 @@
   <component name="Black">
     <option name="sdkName" value="Python 3.13 (Inference-API)" />
   </component>
-  <component name="ProjectRootManager" version="2" languageLevel="JDK_21" default="true" project-jdk-name="Python 3.12 (Inference-API)" project-jdk-type="Python SDK">
+  <component name="ProjectRootManager" version="2" languageLevel="JDK_21" default="true" project-jdk-name="Python 3.13 (Inference-API) (2)" project-jdk-type="Python SDK">
     <output url="file://$PROJECT_DIR$/out" />
   </component>
 </project>

main/config.yaml

@@ -5,8 +5,8 @@ server:
   max_batch_size: 1
 
 llm_server:
-  host: "teamgenki-llmserver.hf.space"
-  port: 7680  # Will be ignored for hf.space URLs
+  host: "0.0.0.0" # "teamgenki-llmserver.hf.space"
+  port: 8001  # Will be ignored for hf.space URLs
   timeout: 60.0
   api_prefix: "/api/v1"  # This will be used for route prefixing
   endpoints:
@@ -17,4 +17,8 @@ llm_server:
     system_validate: "/system/validate"
     model_initialize: "/model/initialize"
     model_initialize_embedding: "/model/initialize/embedding"
-    model_download: "/model/download"
+    model_download: "/model/download"
+
+model:
+  defaults:
+    model_name: "microsoft/Phi-3.5-mini-instruct"

main/main.py

@@ -57,7 +57,7 @@ def create_app():
     api = InferenceApi(config)
 
     # Initialize router with API instance
-    init_router(api)
+    init_router(api, config)
 
     # Create LitServer instance
     server = ls.LitServer(

main/routes.py

@@ -18,11 +18,13 @@ from .schemas import (
 router = APIRouter()
 logger = logging.getLogger(__name__)
 api = None
+config = None
 
-def init_router(inference_api: InferenceApi):
+def init_router(inference_api: InferenceApi, conf):
     """Initialize router with an already setup API instance"""
-    global api
+    global api, config
     api = inference_api
+    config = conf
     logger.info("Router initialized with Inference API instance")
 
 @router.post("/generate")