fix

src/engine.py

@@ -134,7 +134,7 @@ async def request_chat_completions(self, model="default", messages=None, max_tok
                 async for line in response.content.iter_any():
                     yield line.decode()
             else:
-                return await response.json()
+                yield await response.json()
 
     async def request_completions(self, model="default", prompt="The capital of France is", max_tokens=100, stream=False, frequency_penalty=0.0, n=1, stop=None, temperature=1.0, top_p=1.0):
         data = {
@@ -154,8 +154,8 @@ async def request_completions(self, model="default", prompt="The capital of Fran
                 async for line in response.content.iter_any():
                     yield line.decode()
             else:
-                return await response.json()
+                yield await response.json()
 
     async def get_models(self):
         async with self.session.get(f"{self.base_url}/models") as response:
-            return await response.json()
+            yield await response.json()

src/handler.py

@@ -26,8 +26,8 @@ async def async_handler(job):
                 async for chunk in openai_request.request_completions(**openai_input):
                     yield chunk
             elif openai_route == "/v1/models":
-                models = await openai_request.get_models()
-                yield models
+                async for models in openai_request.get_models():
+                    yield models
         else:
             generate_url = f"{engine.base_url}/generate"
             headers = {"Content-Type": "application/json"}