Update app.py

app.py

@@ -81,7 +81,6 @@ models = [
     {"id": "cognitivecomputations/dolphin-2.9.1-llama-3-70b", "object": "model", "created": 1686935002, "owned_by": "cognitivecomputations"},
     {"id": "nvidia/Nemotron-4-340B-Instruct", "object": "model", "created": 1686935002, "owned_by": "nvidia"},
     {"id": "Qwen/Qwen2-72B-Instruct", "object": "model", "created": 1686935002, "owned_by": "qwen"},
-    {"id": "microsoft/Phi-3-medium-4k-instruct", "object": "model", "created": 1686935002, "owned_by": "microsoft"},
     {"id": "google/gemma-2-9b-it", "object": "model", "created": 1686935002, "owned_by": "ConsiousAI"},
     {"id": "openchat/openchat-3.6-8b", "object": "model", "created": 1686935002, "owned_by": "unknown"},
     {"id": "mistralai/Mistral-7B-Instruct-v0.3", "object": "model", "created": 1686935002, "owned_by": "mistral"},
@@ -93,7 +92,7 @@ models = [
 
 ]
 
-@app.post("/v1/chat/completions/")
+@app.post("/v1/chat/completions")
 def handle_completions(completion_request: CompletionRequest):
     system_prompt = next((message.content for message in completion_request.messages if message.role == 'system'), None)
     user_query = next((message.content for message in completion_request.messages if message.role == 'user'), None)
@@ -110,11 +109,11 @@ def handle_completions(completion_request: CompletionRequest):
     )
     return response
 
-@app.get("/v1/models/")
+@app.get("/v1/models")
 def get_models():
     return {"object": "list", "data": models}
 
-@app.post("/v1/completions/")
+@app.post("/v1/completions")
 def create_completion(prompt: str, model: str, best_of: int = 1, echo: bool = False, frequency_penalty: float = 0.0):
     response_text = generative(prompt, "you are an helpful assistant", model)