From d054183cb64889b0aaa9d355485cb1c428c9cc6c Mon Sep 17 00:00:00 2001
From: Vyacheslav Morov <vyacheslav.morov@gmail.com>
Date: Tue, 22 Oct 2024 21:09:43 +0200
Subject: [PATCH] Fix llm judge example and fix ignore for llm examples.

---
 .github/workflows/examples.yml                        |  2 +-
 example_test.py                                       |  4 ++--
 .../how_to_use_llm_judge_template.ipynb               | 11 +++++------
 3 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/.github/workflows/examples.yml b/.github/workflows/examples.yml
index b36aa7e80e..6f4062502b 100644
--- a/.github/workflows/examples.yml
+++ b/.github/workflows/examples.yml
@@ -42,7 +42,7 @@ jobs:
         if: matrix.minimal
         run: pip install -r requirements.min.txt
       - name: Prepare examples dependencies
-        run: pip install catboost sentence-transformers
+        run: pip install catboost sentence-transformers openai
       - name: Export examples
         run: jupyter nbconvert --to python examples/*/*.ipynb --output-dir example_scripts
       - name: Run examples
diff --git a/example_test.py b/example_test.py
index 9132656429..ae4c71ffe4 100644
--- a/example_test.py
+++ b/example_test.py
@@ -12,8 +12,8 @@
     "comparing_custom_statest_with_classic_distributions.py",
     "how_to_evaluate_llm_with_text_descriptors.py",
     "how_to_run_drift_report_for_text_data.py",  # too slow & torch version conflict?
-    "llm_evaluation_tutorial.ipynb",  # cloud usage
-    "llm_tracing_tutorial.ipynb",  # cloud usage
+    "llm_evaluation_tutorial.py",  # cloud usage
+    "llm_tracing_tutorial.py",  # cloud usage
 ]
 
 
diff --git a/examples/how_to_questions/how_to_use_llm_judge_template.ipynb b/examples/how_to_questions/how_to_use_llm_judge_template.ipynb
index d6f57a6ea5..3623818fa7 100644
--- a/examples/how_to_questions/how_to_use_llm_judge_template.ipynb
+++ b/examples/how_to_questions/how_to_use_llm_judge_template.ipynb
@@ -191,9 +191,7 @@
    "id": "204d90a4-694e-406b-949a-f7ba3b601eac",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "print(ToxicityLLMEval().get_template().get_prompt_template())"
-   ]
+   "source": "print(ToxicityLLMEval().get_template().get_template())"
   },
   {
    "cell_type": "code",
@@ -308,7 +306,7 @@
    "source": [
     "#that's how you can see the prompt\n",
     "\n",
-    "print(ContextQualityLLMEval(question=\"question\").get_template().get_prompt_template())"
+    "print(ContextQualityLLMEval(question=\"question\").get_template().get_template())"
    ]
   },
   {
@@ -414,12 +412,13 @@
     "        pre_messages=[(\"system\", \"You are a judge which evaluates text.\")],\n",
     "        ),\n",
     "    provider = \"openai\",\n",
-    "    model = \"gpt-4o-mini\"\n",
+    "    model = \"gpt-4o-mini\",\n",
+    "    display_name=\"test\"\n",
     ")\n",
     "\n",
     "report = Report(metrics=[\n",
     "    TextEvals(column_name=\"response\", descriptors=[\n",
-    "        custom_judge(display_name=\"test\")\n",
+    "        custom_judge\n",
     "    ])\n",
     "])\n",
     "\n",