From 9511782485d39107c75ac17bd6353581e8313244 Mon Sep 17 00:00:00 2001
From: Sebastian Niehus <sebastian.niehus@ext.aleph-alpha.com>
Date: Fri, 17 May 2024 08:29:14 +0200
Subject: [PATCH] fix: Start adding review comments TASK: IL-394

---
 CHANGELOG.md                           | 6 +++---
 tests/evaluation/test_elo_evaluator.py | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index aedddb08f..918d3ce04 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -3,10 +3,10 @@
 ## Unreleased
 
 ### Breaking Changes
- - Changed the behavior of `IncrementalEvaluator::do_evaluate`  such that it now promotes all output to `do_incremental_evaluate`instead of only the new outputs.
+ - Changed the behavior of `IncrementalEvaluator::do_evaluate` such that it now sends all `SuccessfulExampleOutput`s to `do_incremental_evaluate` instead of only the new `SuccessfulExampleOutput`s.
  -
 ### New Features
- - Add generic `EloEvaluator` class and `EloEvaluationLogic`for implementation of Elo evaluation use cases.
+ - Add generic `EloEvaluator` class and `EloEvaluationLogic` for implementation of Elo evaluation use cases.
  - Add `EloQaEvaluator` and `EloQaEvaluationLogic` for Elo evaluation of QA runs.
  - Add `IncrementalEloQaEvaluator` and `IncrementalEloQaEvaluationLogic` for Elo evaluation of QA runs with later addition of more runs to an existing evaluation.
  - Add `EloAggregationAdapter` class to simplify using the `ComparisonEvaluationAggregationLogic` for different Elo use cases.
@@ -14,7 +14,7 @@
 ### Fixes
 ...
 ### Deprecations
-...lint
+...
 
 ## 1.2.0
 
diff --git a/tests/evaluation/test_elo_evaluator.py b/tests/evaluation/test_elo_evaluator.py
index 51cec543a..8698dbe1c 100644
--- a/tests/evaluation/test_elo_evaluator.py
+++ b/tests/evaluation/test_elo_evaluator.py
@@ -8,10 +8,11 @@
     ControlModel,
     Language,
     LuminousControlModel,
+    NoOpTracer,
     TextChunk,
+    Tracer,
     utc_now,
 )
-from intelligence_layer.core.tracer.tracer import NoOpTracer, Tracer
 from intelligence_layer.evaluation import (
     ComparisonEvaluation,
     EloEvaluationLogic,
@@ -29,8 +30,6 @@
 )
 from intelligence_layer.examples import SingleChunkQaInput, SingleChunkQaOutput
 
-load_dotenv()
-
 
 class DummyEloQaEvalLogic(
     EloEvaluationLogic[SingleChunkQaInput, SingleChunkQaOutput, SingleChunkQaOutput]
@@ -40,6 +39,7 @@ def __init__(
         model: ControlModel,
         tracer: Tracer = NoOpTracer(),
     ):
+        load_dotenv()
         super().__init__()
         self._model = model
         self.tracer = tracer