Added documentation

LLMPipelineTest documentation

Carrot-Assistant/evaluation/eval_tests.py

@@ -1,3 +1,4 @@
+from typing import Dict
 from evaluation.evaltypes import (
     SingleResultPipelineTest,
     SingleResultMetric,
@@ -6,16 +7,60 @@
 
 
 class LLMPipelineTest(SingleResultPipelineTest):
+    """
+    This class provides a pipeline test for LLM pipelines that return a single result
+    """
+
     def __init__(
         self,
         name: str,
         pipeline: LLMPipeline,
         metrics: list[SingleResultMetric],
     ):
+        """
+        Initialises the LLMPipelineTest class
+
+        Parameters
+        ----------
+        name: str
+            Name given to the test
+        pipeline: LLMPipeline
+            The pipeline used to generate output
+        metrics: list[SingleResultMetric]
+            A list of metrics used to compare the pipeline output with the expected output
+        """
         super().__init__(name, pipeline, metrics)
 
-    def run_pipeline(self, input_data):
+    def run_pipeline(self, input_data) -> str:
+        """
+        Runs the provided pipeline on the input_data
+
+        Parameters
+        ----------
+        input_data
+            The data used for input to the pipeline
+
+        Returns
+        -------
+        str
+            The reply from the pipeline
+        """
         return super().run_pipeline(input_data)
 
-    def evaluate(self, input_data, expected_output):
+    def evaluate(self, input_data, expected_output) -> Dict:
+        """
+        Evaluates the attached pipeline's output against the expected output using the metrics
+
+        Parameters
+        ----------
+        input_data
+            The data used for input to the pipeline
+        expected_output
+            The expected result of running the input data through the pipeline
+
+        Returns
+        -------
+        Dict
+            A dictionary of results from evaluating the pipeline.
+        """
         return super().evaluate(input_data, expected_output)

Carrot-Assistant/tests/test_evals.py

@@ -104,6 +104,7 @@ def test_pipeline_called_from_eval_returns_string(self, llm_pipeline_test):
 
     def test_llm_pipelinetest_evaluates(self, llm_pipeline_test):
         model_eval = llm_pipeline_test.evaluate(
+            name="Testing the parrot pipeline",
             input_data={"input_sentence": "Polly wants a cracker"},
             expected_output="Polly wants a cracker",
         )