| ################################################################################ | |
| # Licensed to the Apache Software Foundation (ASF) under one | |
| # or more contributor license agreements. See the NOTICE file | |
| # distributed with this work for additional information | |
| # regarding copyright ownership. The ASF licenses this file | |
| # to you under the Apache License, Version 2.0 (the | |
| # "License"); you may not use this file except in compliance | |
| # with the License. You may obtain a copy of the License at | |
| # | |
| # http://www.apache.org/licenses/LICENSE-2.0 | |
| # | |
| # Unless required by applicable law or agreed to in writing, software | |
| # distributed under the License is distributed on an "AS IS" BASIS, | |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| # See the License for the specific language governing permissions and | |
| # limitations under the License. | |
| ################################################################################ | |
| import unittest | |
| import pyflink.dataframe as pf | |
| from pyflink.common import Row | |
| from pyflink.dataframe import llm | |
| from pyflink.testing.test_case_utils import PyFlinkStreamDataFrameTestCase | |
| class DataFrameLlmITCase(PyFlinkStreamDataFrameTestCase): | |
| def setUp(self): | |
| previous = dict(llm._provider_registry) | |
| self.addCleanup(llm._provider_registry.update, previous) | |
| self.addCleanup(llm._provider_registry.clear) | |
| self.addCleanup(setattr, llm, "_default_provider", llm._default_provider) | |
| llm._provider_registry.clear() | |
| llm._default_provider = None | |
| self.provider = pf.GenericProvider("python-values", {"async": "false", "latency": "0"}) | |
| pf.set_model_provider("values", self.provider) | |
| self.output_type = pf.DataType.struct({ | |
| "x": pf.DataType.string(), | |
| "y": pf.DataType.int32(), | |
| "z": pf.DataType.string(), | |
| }) | |
| def test_sync_prediction_appends_typed_columns(self): | |
| registered_models = self.t_env.list_models() | |
| dataframe = pf.from_records([(1, "first"), (3, "third")], schema=["id", "content"]) | |
| prediction = dataframe.llm.predict( | |
| "id", output_type=self.output_type, config={"async": "false"}, | |
| ) | |
| self.assertEqual(prediction.columns, ["id", "content", "x", "y", "z"]) | |
| self.assertCountEqual(prediction.collect(), [ | |
| Row(1, "first", "x1", 1, "z1"), | |
| Row(3, "third", "x3", 3, "z3"), | |
| ]) | |
| self.assertEqual(self.t_env.list_models(), registered_models) | |
| def test_async_prediction_with_provider_override_and_runtime_config(self): | |
| dataframe = pf.from_records([(2, "second"), (4, "fourth")], schema=["id", "content"]) | |
| prediction = dataframe.llm.predict( | |
| "id", provider="values", output_type=self.output_type, | |
| config={ | |
| "async": "true", | |
| "output-mode": "allow_unordered", | |
| "max-concurrent-operations": "2", | |
| "timeout": "30 s", | |
| }, | |
| **{"async": "true"}, | |
| ) | |
| selected = prediction.select("content", "x", (pf.col("y") + 1).alias("next_id"), "z") | |
| self.assertCountEqual(selected.collect(), [ | |
| Row("second", "x2", 3, "z2"), | |
| Row("fourth", "x4", 5, "z4"), | |
| ]) | |
| self.assertEqual(self.provider.to_options(), {"async": "false", "latency": "0"}) | |
| if __name__ == '__main__': | |
| try: | |
| import xmlrunner | |
| testRunner = xmlrunner.XMLTestRunner(output='target/test-reports') | |
| except ImportError: | |
| testRunner = None | |
| unittest.main(testRunner=testRunner, verbosity=2) |