From 1f014c1d61e93eaf217d080291a095cb3fa0eacd Mon Sep 17 00:00:00 2001
From: Brandon Hancock <brandon@brandonhancock.io>
Date: Tue, 28 Jan 2025 13:17:48 -0500
Subject: [PATCH] make sure to raise an error when missing training data

---
 .../utilities/evaluators/task_evaluator.py    | 33 +++++++++++++++----
 1 file changed, 27 insertions(+), 6 deletions(-)

diff --git a/src/crewai/utilities/evaluators/task_evaluator.py b/src/crewai/utilities/evaluators/task_evaluator.py
index 5ee99e85d..0b7b8cca7 100644
--- a/src/crewai/utilities/evaluators/task_evaluator.py
+++ b/src/crewai/utilities/evaluators/task_evaluator.py
@@ -90,16 +90,37 @@ class TaskEvaluator:
             - training_data (dict): The training data to be evaluated.
             - agent_id (str): The ID of the agent.
         """
-        print("Training data: ", training_data)
 
         output_training_data = training_data[agent_id]
-
         final_aggregated_data = ""
-        for _, data in output_training_data.items():
+
+        for iteration, data in output_training_data.items():
+            improved_output = data.get("improved_output")
+            initial_output = data.get("initial_output")
+            human_feedback = data.get("human_feedback")
+
+            if not all([improved_output, initial_output, human_feedback]):
+                missing_fields = [
+                    field
+                    for field in ["improved_output", "initial_output", "human_feedback"]
+                    if not data.get(field)
+                ]
+                error_msg = (
+                    f"Critical training data error: Missing fields ({', '.join(missing_fields)}) "
+                    f"for agent {agent_id} in iteration {iteration}.\n"
+                    "This indicates a broken training process. "
+                    "Cannot proceed with evaluation.\n"
+                    "Please check your training implementation."
+                )
+                self._logger.log("critical", error_msg, color="red")
+                raise ValueError(error_msg)
+
             final_aggregated_data += (
-                f"Initial Output:\n{data.get('initial_output')}\n\n"
-                f"Human Feedback:\n{data.get('human_feedback')}\n\n"
-                f"Improved Output:\n{data.get('improved_output')}\n\n"
+                f"Iteration: {iteration}\n"
+                f"Initial Output:\n{initial_output}\n\n"
+                f"Human Feedback:\n{human_feedback}\n\n"
+                f"Improved Output:\n{improved_output}\n\n"
+                "------------------------------------------------\n\n"
             )
 
         evaluation_query = (