diff --git a/examples/frontend_language/usage/openai_parallel_sample.py b/examples/frontend_language/usage/openai_parallel_sample.py deleted file mode 100644 index 753e66c74..000000000 --- a/examples/frontend_language/usage/openai_parallel_sample.py +++ /dev/null @@ -1,153 +0,0 @@ -import openai - -client = openai.Client(base_url="http://127.0.0.1:30000/v1", api_key="EMPTY") - -# Text completion -response = client.completions.create( - model="default", - prompt="I am a robot and I want to study like humans. Now let's tell a story. Once upon a time, there was a little", - n=1, - temperature=0.8, - max_tokens=32, -) -print(response) - - -# Text completion -response = client.completions.create( - model="default", - prompt="I am a robot and I want to study like humans. Now let's tell a story. Once upon a time, there was a little", - n=5, - temperature=0.8, - max_tokens=320, -) -print(response) - - -# Text completion -response = client.completions.create( - model="default", - prompt="I am a robot and I want to study like humans. Now let's tell a story. Once upon a time, there was a little", - n=3, - temperature=0.8, - max_tokens=32, -) -print(response) - - -# Text completion -response = client.completions.create( - model="default", - prompt=["The name of the famous soccer player is"], - n=1, - temperature=0.8, - max_tokens=128, -) -print(response) - - -# Text completion -response = client.completions.create( - model="default", - prompt=["The name of the famous soccer player is ", "The capital of US is"], - n=1, - temperature=0.8, - max_tokens=32, -) -print(response) - - -# Text completion -response = client.completions.create( - model="default", - prompt=["The name of the famous soccer player is ", "The capital of US is"], - n=3, - temperature=0.8, - max_tokens=32, -) -print(response) - - -response = client.completions.create( - model="default", - prompt=[ - "prompt1: I am a robot and I want to learn like humans. Now let's begin a tale. Once upon a time, there was a small", - "prompt2: As a robot, my goal is to understand human learning. Let's start a story. In a faraway land, there lived a tiny", - "prompt3: Being a robot, I aspire to study like people. Let's share a story. Long ago, there was a little", - "prompt4: I am a robot aiming to learn like humans. Let's narrate a story. Once, in a distant kingdom, there was a young", - "prompt5: As a robot, I seek to learn in human ways. Let's tell a story. Once upon a time, in a small village, there was a young", - ], - n=1, - temperature=0.8, - max_tokens=320, -) -print(response) - - -# Text completion -response = client.completions.create( - model="default", - prompt=[ - "The capital of France is", - "The capital of Germany is", - "The capital of US is", - ], - n=3, - temperature=0.8, - max_tokens=32, -) -print(response) - -# Chat completion -response = client.chat.completions.create( - model="default", - messages=[ - {"role": "system", "content": "You are a helpful AI assistant"}, - {"role": "user", "content": "List 3 countries and their capitals."}, - ], - temperature=0.8, - max_tokens=1, - logprobs=True, - top_logprobs=3, -) -print(response) - -# Chat completion -response = client.chat.completions.create( - model="default", - messages=[ - {"role": "system", "content": "You are a helpful AI assistant"}, - {"role": "user", "content": "List 3 countries and their capitals."}, - ], - temperature=0.8, - max_tokens=1, - n=1, -) -print(response) - -# Chat completion -response = client.chat.completions.create( - model="default", - messages=[ - {"role": "system", "content": "You are a helpful AI assistant"}, - {"role": "user", "content": "List 3 countries and their capitals."}, - ], - temperature=0.8, - max_tokens=1, - logprobs=True, - top_logprobs=3, -) -print(response) - -# Chat completion -response = client.chat.completions.create( - model="default", - messages=[ - {"role": "system", "content": "You are a helpful AI assistant"}, - {"role": "user", "content": "List 3 countries and their capitals."}, - ], - temperature=0.8, - max_tokens=1, - n=4, -) -print(response) diff --git a/test/srt/test_openai_server.py b/test/srt/test_openai_server.py index cfc65b7e6..3fc578551 100644 --- a/test/srt/test_openai_server.py +++ b/test/srt/test_openai_server.py @@ -350,11 +350,11 @@ class TestOpenAIServer(unittest.TestCase): completion_window=completion_window, ) - return batch_job, content + return batch_job, content, uploaded_file def run_batch(self, mode): client = openai.Client(api_key=self.api_key, base_url=self.base_url) - batch_job, content = self._create_batch(mode=mode, client=client) + batch_job, content, uploaded_file = self._create_batch(mode=mode, client=client) while batch_job.status not in ["completed", "failed", "cancelled"]: time.sleep(3) @@ -378,10 +378,13 @@ class TestOpenAIServer(unittest.TestCase): if line.strip() != "" ] assert len(results) == len(content) + for delete_fid in [uploaded_file.id, result_file_id]: + del_pesponse = client.files.delete(delete_fid) + assert del_pesponse.deleted def run_cancel_batch(self, mode): client = openai.Client(api_key=self.api_key, base_url=self.base_url) - batch_job, _ = self._create_batch(mode=mode, client=client) + batch_job, _, uploaded_file = self._create_batch(mode=mode, client=client) assert batch_job.status not in ["cancelling", "cancelled"] @@ -396,6 +399,8 @@ class TestOpenAIServer(unittest.TestCase): time.sleep(3) assert batch_job.status == "cancelled" + del_response = client.files.delete(uploaded_file.id) + assert del_response.deleted def test_completion(self): for echo in [False, True]: