[pre-commit.ci] pre-commit suggestions (#353)

* [pre-commit.ci] pre-commit suggestions updates: - [github.com/pre-commit/pre-commit-hooks: v4.6.0 → v5.0.0](pre-commit/pre-commit-hooks@v4.6.0...v5.0.0) - [github.com/pre-commit/mirrors-prettier: v3.0.3 → v4.0.0-alpha.8](pre-commit/mirrors-prettier@v3.0.3...v4.0.0-alpha.8) - [github.com/PyCQA/docformatter: 06907d0267368b49b9180eed423fae5697c1e909 → v1.7.5](PyCQA/docformatter@06907d0...v1.7.5) - [github.com/astral-sh/ruff-pre-commit: v0.6.3 → v0.7.2](astral-sh/ruff-pre-commit@v0.6.3...v0.7.2) * Apply suggestions from code review * Apply suggestions from code review * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Jirka Borovec <[email protected]>
Lightning-AI · Nov 7, 2024 · 6dbb793 · 6dbb793
1 parent 23ba5e2
commit 6dbb793
Show file tree

Hide file tree

Showing 10 changed files with 70 additions and 73 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -9,7 +9,7 @@ ci:
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v5.0.0
     hooks:
       - id: end-of-file-fixer
       - id: trailing-whitespace
@@ -30,7 +30,7 @@ repos:
         #args: ["--write-changes"]
 
   - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: v3.0.3
+    rev: v3.1.0
     hooks:
       - id: prettier
         files: \.(json|yml|yaml|toml)
@@ -45,7 +45,7 @@ repos:
         args: ["--in-place"]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.6.3
+    rev: v0.7.2
     hooks:
       - id: ruff-format
         args: ["--preview"]

diff --git a/src/litserve/server.py b/src/litserve/server.py
@@ -473,7 +473,7 @@ def run(
 
         if sys.platform == "win32":
             warnings.warn(
-                "Windows does not support forking. Using threads" " api_server_worker_type will be set to 'thread'"
+                "Windows does not support forking. Using threads api_server_worker_type will be set to 'thread'"
             )
             api_server_worker_type = "thread"
         elif api_server_worker_type is None:

diff --git a/src/litserve/test_examples/openai_spec_example.py b/src/litserve/test_examples/openai_spec_example.py
@@ -66,7 +66,7 @@ def predict(self, inputs, context):
         for ctx in context:
             ctx["temperature"] = 1.0
         output = (
-            "Hi! It's nice to meet you. Is there something I can help you with " "or would you like to chat?"
+            "Hi! It's nice to meet you. Is there something I can help you with or would you like to chat?"
         ).split()
         for out in output:
             time.sleep(0.01)  # fake delay

diff --git a/tests/e2e/test_e2e.py b/tests/e2e/test_e2e.py
@@ -64,9 +64,9 @@ def test_run_with_port():
         client_code = f.read()
         assert ":8080" in client_code, "Could not find 8080 in client.py"
     output = subprocess.run("python client.py", shell=True, capture_output=True, text=True).stdout
-    assert (
-        '{"output":16.0}' in output
-    ), f"tests/simple_server_server_diff_port.py didn't return expected output, got {output}"
+    assert '{"output":16.0}' in output, (
+        f"tests/simple_server_server_diff_port.py didn't return expected output, got {output}"
+    )
     os.remove("client.py")
 
 
@@ -121,7 +121,7 @@ def test_openai_parity():
         ],
     )
     assert response.choices[0].message.content == "This is a generated output", (
-        f"Server didn't return expected output" f"\nOpenAI client output: {response}"
+        f"Server didn't return expected output\nOpenAI client output: {response}"
     )
 
     response = client.chat.completions.create(
@@ -136,7 +136,7 @@ def test_openai_parity():
     expected_outputs = ["This is a generated output", None]
     for r, expected_out in zip(response, expected_outputs):
         assert r.choices[0].delta.content == expected_out, (
-            f"Server didn't return expected output.\n" f"OpenAI client output: {r}"
+            f"Server didn't return expected output.\nOpenAI client output: {r}"
         )
 
 
@@ -167,7 +167,7 @@ def test_openai_parity_with_image_input():
         messages=messages,
     )
     assert response.choices[0].message.content == "This is a generated output", (
-        f"Server didn't return expected output" f"\nOpenAI client output: {response}"
+        f"Server didn't return expected output\nOpenAI client output: {response}"
     )
 
     response = client.chat.completions.create(
@@ -179,7 +179,7 @@ def test_openai_parity_with_image_input():
     expected_outputs = ["This is a generated output", None]
     for r, expected_out in zip(response, expected_outputs):
         assert r.choices[0].delta.content == expected_out, (
-            f"Server didn't return expected output.\n" f"OpenAI client output: {r}"
+            f"Server didn't return expected output.\nOpenAI client output: {r}"
         )
 
 
@@ -218,10 +218,10 @@ def test_openai_parity_with_tools():
         tools=tools,
     )
     assert response.choices[0].message.content == "", (
-        f"Server didn't return expected output" f"\nOpenAI client output: {response}"
+        f"Server didn't return expected output\nOpenAI client output: {response}"
     )
     assert response.choices[0].message.tool_calls[0].function.name == "get_current_weather", (
-        f"Server didn't return expected output" f"\nOpenAI client output: {response}"
+        f"Server didn't return expected output\nOpenAI client output: {response}"
     )
 
     response = client.chat.completions.create(
@@ -233,11 +233,11 @@ def test_openai_parity_with_tools():
     expected_outputs = ["", None]
     for r, expected_out in zip(response, expected_outputs):
         assert r.choices[0].delta.content == expected_out, (
-            f"Server didn't return expected output.\n" f"OpenAI client output: {r}"
+            f"Server didn't return expected output.\nOpenAI client output: {r}"
         )
         if r.choices[0].delta.tool_calls:
             assert r.choices[0].delta.tool_calls[0].function.name == "get_current_weather", (
-                f"Server didn't return expected output.\n" f"OpenAI client output: {r}"
+                f"Server didn't return expected output.\nOpenAI client output: {r}"
             )
 
 
@@ -255,7 +255,7 @@ def test_e2e_openai_with_batching(openai_request_data):
         ],
     )
     assert response.choices[0].message.content == (
-        "Hi! It's nice to meet you. Is there something I can " "help you with or would you like to chat? "
+        "Hi! It's nice to meet you. Is there something I can help you with or would you like to chat? "
     ), f"Server didn't return expected output OpenAI client output: {response}"
 
 
@@ -293,7 +293,7 @@ def test_openai_parity_with_response_format():
         response_format=response_format,
     )
     assert response.choices[0].message.content == output, (
-        f"Server didn't return expected output" f"\nOpenAI client output: {response}"
+        f"Server didn't return expected output\nOpenAI client output: {response}"
     )
 
     response = client.chat.completions.create(
@@ -306,7 +306,7 @@ def test_openai_parity_with_response_format():
     expected_outputs = [output, None]
     for r, expected_out in zip(response, expected_outputs):
         assert r.choices[0].delta.content == expected_out, (
-            f"Server didn't return expected output.\n" f"OpenAI client output: {r}"
+            f"Server didn't return expected output.\nOpenAI client output: {r}"
         )
 
 

diff --git a/tests/test_connector.py b/tests/test_connector.py
@@ -92,13 +92,13 @@ def test_check_cuda_with_nvidia_smi_mock_gpu(mock_subprocess):
 def test_connector(input_accelerator, expected_accelerator, expected_devices):
     check_cuda_with_nvidia_smi.cache_clear()
     connector = _Connector(accelerator=input_accelerator)
-    assert (
-        connector.accelerator == expected_accelerator
-    ), f"accelerator mismatch - expected: {expected_accelerator}, actual: {connector.accelerator}"
+    assert connector.accelerator == expected_accelerator, (
+        f"accelerator mismatch - expected: {expected_accelerator}, actual: {connector.accelerator}"
+    )
 
-    assert (
-        connector.devices == expected_devices
-    ), f"devices mismatch - expected {expected_devices}, actual: {connector.devices}"
+    assert connector.devices == expected_devices, (
+        f"devices mismatch - expected {expected_devices}, actual: {connector.devices}"
+    )
 
     with pytest.raises(ValueError, match="accelerator must be one of 'auto', 'cpu', 'mps', 'cuda', or 'gpu'"):
         _Connector(accelerator="SUPER_CHIP")

diff --git a/tests/test_lit_server.py b/tests/test_lit_server.py
@@ -65,13 +65,13 @@ async def test_stream(simple_stream_api):
             resp2 = ac.post("/predict", json={"prompt": "World"}, timeout=10)
             resp1, resp2 = await asyncio.gather(resp1, resp2)
             assert resp1.status_code == 200, "Check if server is running and the request format is valid."
-            assert (
-                resp1.text == expected_output1
-            ), "Server returns input prompt and generated output which didn't match."
+            assert resp1.text == expected_output1, (
+                "Server returns input prompt and generated output which didn't match."
+            )
             assert resp2.status_code == 200, "Check if server is running and the request format is valid."
-            assert (
-                resp2.text == expected_output2
-            ), "Server returns input prompt and generated output which didn't match."
+            assert resp2.text == expected_output2, (
+                "Server returns input prompt and generated output which didn't match."
+            )
 
 
 @pytest.mark.asyncio
@@ -87,12 +87,12 @@ async def test_batched_stream_server(simple_batched_stream_api):
             resp1, resp2 = await asyncio.gather(resp1, resp2)
             assert resp1.status_code == 200, "Check if server is running and the request format is valid."
             assert resp2.status_code == 200, "Check if server is running and the request format is valid."
-            assert (
-                resp1.text == expected_output1
-            ), "Server returns input prompt and generated output which didn't match."
-            assert (
-                resp2.text == expected_output2
-            ), "Server returns input prompt and generated output which didn't match."
+            assert resp1.text == expected_output1, (
+                "Server returns input prompt and generated output which didn't match."
+            )
+            assert resp2.text == expected_output2, (
+                "Server returns input prompt and generated output which didn't match."
+            )
 
 
 def test_litapi_with_stream(simple_litapi):

diff --git a/tests/test_loops.py b/tests/test_loops.py
@@ -120,13 +120,13 @@ def put(self, item):
             raise StopIteration("interrupt iteration")
         if status == LitAPIStatus.ERROR and isinstance(response, StopIteration):
             assert self.count // 2 == self.num_streamed_outputs, (
-                f"Loop count must have incremented for " f"{self.num_streamed_outputs} times."
+                f"Loop count must have incremented for {self.num_streamed_outputs} times."
             )
             raise StopIteration("finish streaming")
 
-        assert (
-            response == f"{self.count // 2}"
-        ), f"streaming loop generates number from 0 to 9 which is sent via Queue. {args}, count:{self.count}"
+        assert response == f"{self.count // 2}", (
+            f"streaming loop generates number from 0 to 9 which is sent via Queue. {args}, count:{self.count}"
+        )
         self.count += 1
 
 

diff --git a/tests/test_readme.py b/tests/test_readme.py
@@ -115,13 +115,10 @@ def test_readme(tmp_path, killall):
         returncode, stdout, stderr = run_script_with_timeout(file, timeout=5, extra_time=extra_time, killall=killall)
 
         if "server.run" in code:
-            assert uvicorn_msg in stderr, (
-                f"Expected to run uvicorn server.\n" f"Code:\n {code}\n\nCode output: {stderr}"
-            )
+            assert uvicorn_msg in stderr, f"Expected to run uvicorn server.\nCode:\n {code}\n\nCode output: {stderr}"
         elif "requests.post" in code:
             assert "ConnectionError" in stderr, (
-                f"Client examples should fail with a ConnectionError because there is no server running."
-                f"\nCode:\n{code}"
+                f"Client examples should fail with a ConnectionError because there is no server running.\nCode:\n{code}"
             )
         else:
             assert returncode == 0, (

diff --git a/tests/test_simple.py b/tests/test_simple.py
@@ -136,12 +136,12 @@ async def test_timeout():
             await asyncio.sleep(0.0001)
             response2 = asyncio.create_task(ac.post("/predict", json={"input": 5.0}))
             responses = await asyncio.gather(response1, response2, return_exceptions=True)
-            assert (
-                responses[0].status_code == 200
-            ), "First request should complete since it's popped from the request queue."
-            assert (
-                responses[1].status_code == 504
-            ), "Server takes longer than specified timeout and request should timeout"
+            assert responses[0].status_code == 200, (
+                "First request should complete since it's popped from the request queue."
+            )
+            assert responses[1].status_code == 504, (
+                "Server takes longer than specified timeout and request should timeout"
+            )
 
 
 @pytest.mark.asyncio
@@ -169,12 +169,12 @@ async def test_batch_timeout():
             await asyncio.sleep(0.0001)
             response3 = asyncio.create_task(ac.post("/predict", json={"input": 6.0}))
             responses = await asyncio.gather(response1, response2, response3, return_exceptions=True)
-            assert (
-                responses[0].status_code == 200
-            ), "Batch: First request should complete since it's popped from the request queue."
-            assert (
-                responses[1].status_code == 200
-            ), "Batch: Second request should complete since it's popped from the request queue."
+            assert responses[0].status_code == 200, (
+                "Batch: First request should complete since it's popped from the request queue."
+            )
+            assert responses[1].status_code == 200, (
+                "Batch: Second request should complete since it's popped from the request queue."
+            )
             assert responses[2].status_code == 504, "Batch: Third request was delayed and should fail"
 
     server1 = LitServer(SlowLitAPI(), accelerator="cpu", devices=1, timeout=-1)

diff --git a/tests/test_specs.py b/tests/test_specs.py
@@ -40,9 +40,9 @@ async def test_openai_spec(openai_request_data):
             resp = await ac.post("/v1/chat/completions", json=openai_request_data, timeout=10)
             assert resp.status_code == 200, "Status code should be 200"
 
-            assert (
-                resp.json()["choices"][0]["message"]["content"] == "This is a generated output"
-            ), "LitAPI predict response should match with the generated output"
+            assert resp.json()["choices"][0]["message"]["content"] == "This is a generated output", (
+                "LitAPI predict response should match with the generated output"
+            )
 
 
 # OpenAIWithUsage
@@ -81,9 +81,9 @@ async def test_openai_spec_with_image(openai_request_data_with_image):
             resp = await ac.post("/v1/chat/completions", json=openai_request_data_with_image, timeout=10)
             assert resp.status_code == 200, "Status code should be 200"
 
-            assert (
-                resp.json()["choices"][0]["message"]["content"] == "This is a generated output"
-            ), "LitAPI predict response should match with the generated output"
+            assert resp.json()["choices"][0]["message"]["content"] == "This is a generated output", (
+                "LitAPI predict response should match with the generated output"
+            )
 
 
 @pytest.mark.asyncio
@@ -94,9 +94,9 @@ async def test_override_encode(openai_request_data):
             resp = await ac.post("/v1/chat/completions", json=openai_request_data, timeout=10)
             assert resp.status_code == 200, "Status code should be 200"
 
-            assert (
-                resp.json()["choices"][0]["message"]["content"] == "This is a custom encoded output"
-            ), "LitAPI predict response should match with the generated output"
+            assert resp.json()["choices"][0]["message"]["content"] == "This is a custom encoded output", (
+                "LitAPI predict response should match with the generated output"
+            )
 
 
 @pytest.mark.asyncio
@@ -107,9 +107,9 @@ async def test_openai_spec_with_tools(openai_request_data_with_tools):
         async with LifespanManager(server.app) as manager, AsyncClient(app=manager.app, base_url="http://test") as ac:
             resp = await ac.post("/v1/chat/completions", json=openai_request_data_with_tools, timeout=10)
             assert resp.status_code == 200, "Status code should be 200"
-            assert (
-                resp.json()["choices"][0]["message"]["content"] == ""
-            ), "LitAPI predict response should match with the generated output"
+            assert resp.json()["choices"][0]["message"]["content"] == "", (
+                "LitAPI predict response should match with the generated output"
+            )
             assert resp.json()["choices"][0]["message"]["tool_calls"] == [
                 {
                     "id": "call_1",
@@ -182,9 +182,9 @@ async def test_oai_prepopulated_context(openai_request_data):
     with wrap_litserve_start(server) as server:
         async with LifespanManager(server.app) as manager, AsyncClient(app=manager.app, base_url="http://test") as ac:
             resp = await ac.post("/v1/chat/completions", json=openai_request_data, timeout=10)
-            assert (
-                resp.json()["choices"][0]["message"]["content"] == "This is a"
-            ), "OpenAISpec must return only 3 tokens as specified using `max_tokens` parameter"
+            assert resp.json()["choices"][0]["message"]["content"] == "This is a", (
+                "OpenAISpec must return only 3 tokens as specified using `max_tokens` parameter"
+            )
 
 
 class WrongLitAPI(ls.LitAPI):