.deepeval-cache.json

{"test_cases_lookup_map": {"{\"actual_output\": \"Hello! I'm here to help you explore and practice Internal Family Systems (IFS). Do you have any questions about IFS, or would you like to start a session?\", \"context\": null, \"expected_output\": \"Hello! I'm here to help you explore and practice Internal Family Systems (IFS). Do you have any questions about IFS, or would you like to start a session?\", \"hyperparameters\": null, \"input\": \"Hi.\", \"retrieval_context\": null}": {"cached_metrics_data": [{"metric_data": {"name": "Similarity (GEval)", "threshold": 0.5, "success": true, "score": 1.0, "reason": "There are no discrepancies between the actual and expected outputs.", "strictMode": false, "evaluationModel": "gpt-4o", "evaluationCost": 0, "verboseLogs": "Criteria:\nNone \n \nEvaluation Steps:\n[\n    \"Assess if there are any discrepancies in information between the actual and expected outputs.\"\n]"}, "metric_configuration": {"threshold": 0.5, "evaluation_model": "gpt-4o", "strict_mode": false, "include_reason": false, "evaluation_steps": ["Assess if there are any discrepancies in information between the actual and expected outputs."], "evaluation_params": ["actual_output", "expected_output"]}}]}, "{\"actual_output\": \"Thank you for choosing to start a session. Is there a particular feeling, struggle, thought pattern, or part of yourself that you need help with today?\", \"context\": null, \"expected_output\": \"Is there a particular feeling, struggle, thought pattern, or part of yourself that you would like some help with today?\", \"hyperparameters\": null, \"input\": \"Let's start a session.\", \"retrieval_context\": null}": {"cached_metrics_data": [{"metric_data": {"name": "Similarity (GEval)", "threshold": 0.5, "success": true, "score": 0.7717500391596471, "reason": "Minor discrepancy in the opening sentence and wording of the request for help.", "strictMode": false, "evaluationModel": "gpt-4o", "evaluationCost": 0, "verboseLogs": "Criteria:\nNone \n \nEvaluation Steps:\n[\n    \"Assess if there are any discrepancies in information between the actual and expected outputs.\"\n]"}, "metric_configuration": {"threshold": 0.5, "evaluation_model": "gpt-4o", "strict_mode": false, "include_reason": false, "evaluation_steps": ["Assess if there are any discrepancies in information between the actual and expected outputs."], "evaluation_params": ["actual_output", "expected_output"]}}]}, "{\"actual_output\": \"Thank you for sharing that with me. It sounds like there's a part of you that's feeling anxiety, and you're noticing it in the back of your neck. Are you aware of this part, and can you feel it in your body right now?\", \"context\": null, \"expected_output\": \"Thank you for sharing that. It sounds like there's a part of you that's feeling anxiety, and you're noticing it in the back of your neck. How do you feel toward this part? Are you okay with it being there, or do you have other feelings about it?\", \"hyperparameters\": null, \"input\": \"Yes, I feel some anxiety in the back of my neck\", \"retrieval_context\": null}": {"cached_metrics_data": [{"metric_data": {"name": "Similarity (GEval)", "threshold": 0.5, "success": true, "score": 0.545862742277681, "reason": "The actual output misses the questions 'How do you feel toward this part?' and 'Are you okay with it being there, or do you have other feelings about it?' but otherwise captures the essence of acknowledging the anxiety.", "strictMode": false, "evaluationModel": "gpt-4o", "evaluationCost": 0, "verboseLogs": "Criteria:\nNone \n \nEvaluation Steps:\n[\n    \"Assess if there are any discrepancies in information between the actual and expected outputs.\"\n]"}, "metric_configuration": {"threshold": 0.5, "evaluation_model": "gpt-4o", "strict_mode": false, "include_reason": false, "evaluation_steps": ["Assess if there are any discrepancies in information between the actual and expected outputs."], "evaluation_params": ["actual_output", "expected_output"]}}]}, "{\"actual_output\": \"It seems like there's a part of you that wishes this anxiety would go away. Let's see if we can help you unblend from this feeling. Can you try to notice this part of you that wants the anxiety to go away, and see if you can create a little space between you and that feeling?\", \"context\": null, \"expected_output\": \"It sounds like there's a part of you that wishes the anxiety would go away. Would it be possible for that part to take a step back during our session, so we can get to know the anxiety part a little better?\", \"hyperparameters\": null, \"input\": \"Well I wish it would go away\", \"retrieval_context\": null}": {"cached_metrics_data": [{"metric_data": {"name": "Similarity (GEval)", "threshold": 0.5, "success": true, "score": 0.6079504245254902, "reason": "The actual output captures the essence of the expected output but uses different wording. The main discrepancy is that it focuses on creating space between the person and the feeling, rather than asking the part to take a step back.", "strictMode": false, "evaluationModel": "gpt-4o", "evaluationCost": 0, "verboseLogs": "Criteria:\nNone \n \nEvaluation Steps:\n[\n    \"Assess if there are any discrepancies in information between the actual and expected outputs.\"\n]"}, "metric_configuration": {"threshold": 0.5, "evaluation_model": "gpt-4o", "strict_mode": false, "include_reason": false, "evaluation_steps": ["Assess if there are any discrepancies in information between the actual and expected outputs."], "evaluation_params": ["actual_output", "expected_output"]}}]}, "{\"actual_output\": \"Great, thank you for working with that. Now that you've created some space, how do you feel toward the part of you that's experiencing the anxiety in the back of your neck?\", \"context\": null, \"expected_output\": \"Now that the part wishing the anxiety would go away has stepped back, how do you feel toward the anxiety part?\", \"hyperparameters\": null, \"input\": \"Sure, it can do that.\", \"retrieval_context\": null}": {"cached_metrics_data": [{"metric_data": {"name": "Similarity (GEval)", "threshold": 0.5, "success": false, "score": 0.3141131362632225, "reason": "The actual output acknowledges creating space and mentions the anxiety in the back of the neck, but it does not address the part wishing the anxiety would go away.", "strictMode": false, "evaluationModel": "gpt-4o", "evaluationCost": 0, "verboseLogs": "Criteria:\nNone \n \nEvaluation Steps:\n[\n    \"Assess if there are any discrepancies in information between the actual and expected outputs.\"\n]"}, "metric_configuration": {"threshold": 0.5, "evaluation_model": "gpt-4o", "strict_mode": false, "include_reason": false, "evaluation_steps": ["Assess if there are any discrepancies in information between the actual and expected outputs."], "evaluation_params": ["actual_output", "expected_output"]}}]}}}