Merge pull request #2924 from BerriAI/litellm_text_completion_response

fix(main.py): handle translating text completion openai to chat completion for async requests

litellm/main.py

@@ -317,6 +317,14 @@ async def acompletion(
                 response = await init_response
             else:
                 response = init_response  # type: ignore
+
+            if custom_llm_provider == "text-completion-openai" and isinstance(
+                response, TextCompletionResponse
+            ):
+                response = litellm.OpenAITextCompletionConfig().convert_to_chat_model_response_object(
+                    response_object=response,
+                    model_response_object=litellm.ModelResponse(),
+                )
         else:
             # Call the synchronous function using run_in_executor
             response = await loop.run_in_executor(None, func_with_context)  # type: ignore

litellm/tests/test_completion.py

@@ -975,6 +975,19 @@ def test_completion_text_openai():
         pytest.fail(f"Error occurred: {e}")
 
 
+@pytest.mark.asyncio
+async def test_completion_text_openai_async():
+    try:
+        # litellm.set_verbose =True
+        response = await litellm.acompletion(
+            model="gpt-3.5-turbo-instruct", messages=messages
+        )
+        print(response["choices"][0]["message"]["content"])
+    except Exception as e:
+        print(e)
+        pytest.fail(f"Error occurred: {e}")
+
+
 def custom_callback(
     kwargs,  # kwargs to completion
     completion_response,  # response from completion