refactor: Remove unused code in large_language_model.py (#5433)

api/core/model_runtime/model_providers/__base/large_language_model.py

@@ -489,37 +489,6 @@ if you are not sure about the structure.
         """Cut off the text as soon as any stop words occur."""
         return re.split("|".join(stop), text, maxsplit=1)[0]
 
-    def _llm_result_to_stream(self, result: LLMResult) -> Generator:
-        """
-from typing_extensions import deprecated
-        Transform llm result to stream
-
-        :param result: llm result
-        :return: stream
-        """
-        index = 0
-
-        tool_calls = result.message.tool_calls
-
-        for word in result.message.content:
-            assistant_prompt_message = AssistantPromptMessage(
-                content=word,
-                tool_calls=tool_calls if index == (len(result.message.content) - 1) else []
-            )
-
-            yield LLMResultChunk(
-                model=result.model,
-                prompt_messages=result.prompt_messages,
-                system_fingerprint=result.system_fingerprint,
-                delta=LLMResultChunkDelta(
-                    index=index,
-                    message=assistant_prompt_message,
-                )
-            )
-
-            index += 1
-            time.sleep(0.01)
-
     def get_parameter_rules(self, model: str, credentials: dict) -> list[ParameterRule]:
         """
         Get parameter rules

api/tests/integration_tests/model_runtime/azure_openai/test_llm.py

@@ -156,11 +156,6 @@ def test_invoke_chat_model(setup_openai_mock):
     assert isinstance(result, LLMResult)
     assert len(result.message.content) > 0
 
-    for chunk in model._llm_result_to_stream(result):
-        assert isinstance(chunk, LLMResultChunk)
-        assert isinstance(chunk.delta, LLMResultChunkDelta)
-        assert isinstance(chunk.delta.message, AssistantPromptMessage)
-        assert len(chunk.delta.message.content) > 0 if chunk.delta.finish_reason is None else True
 
 @pytest.mark.parametrize('setup_openai_mock', [['chat']], indirect=True)
 def test_invoke_stream_chat_model(setup_openai_mock):

api/tests/integration_tests/model_runtime/cohere/test_llm.py

@@ -136,12 +136,6 @@ def test_invoke_chat_model():
     assert isinstance(result, LLMResult)
     assert len(result.message.content) > 0
 
-    for chunk in model._llm_result_to_stream(result):
-        assert isinstance(chunk, LLMResultChunk)
-        assert isinstance(chunk.delta, LLMResultChunkDelta)
-        assert isinstance(chunk.delta.message, AssistantPromptMessage)
-        assert len(chunk.delta.message.content) > 0 if chunk.delta.finish_reason is None else True
-
 
 def test_invoke_stream_chat_model():
     model = CohereLargeLanguageModel()

api/tests/integration_tests/model_runtime/openai/test_llm.py

@@ -156,12 +156,6 @@ def test_invoke_chat_model(setup_openai_mock):
     assert isinstance(result, LLMResult)
     assert len(result.message.content) > 0
 
-    for chunk in model._llm_result_to_stream(result):
-        assert isinstance(chunk, LLMResultChunk)
-        assert isinstance(chunk.delta, LLMResultChunkDelta)
-        assert isinstance(chunk.delta.message, AssistantPromptMessage)
-        assert len(chunk.delta.message.content) > 0 if chunk.delta.finish_reason is None else True
-
 @pytest.mark.parametrize('setup_openai_mock', [['chat']], indirect=True)
 def test_invoke_chat_model_with_vision(setup_openai_mock):
     model = OpenAILargeLanguageModel()