diff --git a/dist/litellm-0.1.644-py3-none-any.whl b/dist/litellm-0.1.644-py3-none-any.whl
new file mode 100644
index 000000000..4979a2db4
Binary files /dev/null and b/dist/litellm-0.1.644-py3-none-any.whl differ
diff --git a/dist/litellm-0.1.644.tar.gz b/dist/litellm-0.1.644.tar.gz
new file mode 100644
index 000000000..3e9d956bb
Binary files /dev/null and b/dist/litellm-0.1.644.tar.gz differ
diff --git a/litellm/__pycache__/__init__.cpython-311.pyc b/litellm/__pycache__/__init__.cpython-311.pyc
index 58688f27f..4dd38f2b1 100644
Binary files a/litellm/__pycache__/__init__.cpython-311.pyc and b/litellm/__pycache__/__init__.cpython-311.pyc differ
diff --git a/litellm/__pycache__/main.cpython-311.pyc b/litellm/__pycache__/main.cpython-311.pyc
index fcec8b4e6..48f542741 100644
Binary files a/litellm/__pycache__/main.cpython-311.pyc and b/litellm/__pycache__/main.cpython-311.pyc differ
diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
index 189cf63d1..8ffdbc4ea 100644
Binary files a/litellm/__pycache__/utils.cpython-311.pyc and b/litellm/__pycache__/utils.cpython-311.pyc differ
diff --git a/litellm/tests/test_streaming.py b/litellm/tests/test_streaming.py
index 0ec8563ab..1423ff2a6 100644
--- a/litellm/tests/test_streaming.py
+++ b/litellm/tests/test_streaming.py
@@ -121,13 +121,14 @@ def test_openai_chat_completion_call():
             print(chunk)
             if "content" in chunk["choices"][0]["delta"]:
                 complete_response += chunk["choices"][0]["delta"]["content"]
-        if complete_response == "": 
+            print(f'complete_chunk: {complete_response}')
+        if complete_response.strip() == "": 
             raise Exception("Empty response received")
     except:
         print(f"error occurred: {traceback.format_exc()}")
         pass
 
-# test_openai_chat_completion_call()
+test_openai_chat_completion_call()
 async def completion_call():
     try:
         response = completion(
diff --git a/litellm/utils.py b/litellm/utils.py
index 4c31c774a..b9d636506 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -2451,7 +2451,11 @@ class CustomStreamWrapper:
 
     def __next__(self):
         try:
+<<<<<<< HEAD
             completion_obj = {"content": "", "role": ""} # default to role being assistant
+=======
+            completion_obj = {"content": ""} # default to role being assistant
+>>>>>>> 31d771b (fix streaming error)
             if self.model in litellm.anthropic_models:
                 chunk = next(self.completion_stream)
                 completion_obj["content"] = self.handle_anthropic_chunk(chunk)
@@ -2496,15 +2500,12 @@ class CustomStreamWrapper:
             else: # openai chat/azure models
                 chunk = next(self.completion_stream)
                 completion_obj["content"] = chunk["choices"][0]["delta"]["content"]
-                completion_obj["role"] = chunk["choices"][0]["delta"]["role"]
-                # return chunk # open ai returns finish_reason, we should just return the openai chunk
-            
-                #completion_obj["content"] = self.handle_openai_chat_completion_chunk(chunk)
+
             # LOGGING
             threading.Thread(target=self.logging_obj.success_handler, args=(completion_obj,)).start()
             # return this for all models
             model_response = ModelResponse(stream=True)
-            model_response.choices[0].delta = completion_obj
+            model_response.choices[0].delta.content = completion_obj["content"]
             return model_response
         except StopIteration:
             raise StopIteration
diff --git a/pyproject.toml b/pyproject.toml
index d2f571150..10039fe8e 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.644"
+version = "0.1.645"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"