diff --git a/evals/deepeval_metrics.py b/evals/deepeval_metrics.py
new file mode 100644
index 000000000..03f9f6dba
--- /dev/null
+++ b/evals/deepeval_metrics.py
@@ -0,0 +1,14 @@
+from deepeval.metrics import GEval
+from deepeval.test_case import LLMTestCaseParams
+
+correctness_metric = GEval(
+        name="Correctness",
+        model="gpt-4o-mini",
+        evaluation_params=[
+            LLMTestCaseParams.ACTUAL_OUTPUT,
+            LLMTestCaseParams.EXPECTED_OUTPUT
+        ],
+        evaluation_steps=[
+           "Determine whether the actual output is factually correct based on the expected output."    
+        ]
+    )