resolved: errors in sycophancy-test, factuality-test and augmentation.

demo/tutorials/misc/Loading_Data_with_Custom_Columns.ipynb

@@ -11,7 +11,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/custom_column_csv.ipynb)"
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/Loading_Data_with_Custom_Columns.ipynb)"
    ]
   },
   {

docs/pages/tutorials/tutorials.md

@@ -56,7 +56,7 @@ The following table gives an overview of the different tutorial notebooks. We ha
 | LogiQA                              | OpenAI                            | Question-Answering                | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/llm_notebooks/dataset-notebooks/LogiQA_dataset.ipynb)                       |
 | ASDiv                               | OpenAI                            | Question-Answering                | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/llm_notebooks/dataset-notebooks/ASDiv_dataset.ipynb)                        |
 | BigBench                            | OpenAI                            | Question-Answering                | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/llm_notebooks/dataset-notebooks/Bigbench_dataset.ipynb)                     |
-| HuggingFaceDataset-Support          | Hugging Face/OpenAI               | Text-Classification/Summarization | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/HuggingFace_Dataset_Notebook.ipynb)                                    |
+| HuggingFaceDataset-Support          | Hugging Face/Spacy/OpenAI               | NER/Text-Classification/Question-Answering/Summarization | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/HuggingFace_Dataset_Notebook.ipynb)                                    |
 | Augmentation-Control                | John Snow Labs                    | NER                               | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/Augmentation_Control_Notebook.ipynb)                                   |
 | Comparing Models                    | Hugging Face/John Snow Labs/Spacy | NER/Text-Classification           | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/Comparing_Models_Notebook.ipynb)                                       |
 | Runtime Test                        | Hugging Face/John Snow Labs/Spacy | NER                               | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/RuntimeTest_Notebook.ipynb)                                            |
@@ -84,7 +84,7 @@ The following table gives an overview of the different tutorial notebooks. We ha
 | Evaluation Metrics                         | OpenAI                      | Question-Answering                       | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/Evaluation_Metrics.ipynb)     |
 | Fiqa                         | OpenAI                     | Question-Answering                       | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/llm_notebooks/dataset-notebooks/Fiqa_dataset.ipynb)  |
 | Customized Model                         | Custom                     | Text-Classification                       | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/Custom_Hub_Notebook.ipynb)  |
-
+| Loading Data with Custom Columns                         | Hugging Face/OpenAI                     | NER/Text-Classification/Question-Answering/Summarization                       | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/langtest/blob/main/demo/tutorials/misc/Loading_Data_with_Custom_Columns.ipynb)  |
 
 <style>
   .heading {

langtest/modelhandler/jsl_modelhandler.py

@@ -174,18 +174,20 @@ def load_model(cls, path) -> "NLUPipeline":
         Args:
             path (str): Path to pretrained local or NLP Models Hub SparkNLP model
         """
-        if os.path.exists(path):
-            if try_import_lib("johnsnowlabs"):
-                loaded_model = nlp.load(path=path)
+        if isinstance(path, str):
+            if os.path.exists(path):
+                if try_import_lib("johnsnowlabs"):
+                    loaded_model = nlp.load(path=path)
+                else:
+                    loaded_model = PipelineModel.load(path)
             else:
-                loaded_model = PipelineModel.load(path)
-        else:
-            if try_import_lib("johnsnowlabs"):
-                loaded_model = nlp.load(path)
-            else:
-                raise ValueError(Errors.E039)
+                if try_import_lib("johnsnowlabs"):
+                    loaded_model = nlp.load(path)
+                else:
+                    raise ValueError(Errors.E039)
 
-        return cls(loaded_model)
+            return cls(loaded_model)
+        return cls(path)
 
     @abstractmethod
     def predict(self, text: str, *args, **kwargs) -> Any:

langtest/tasks/task.py

@@ -595,7 +595,7 @@ def create_sample(
 class FactualityTest(BaseTask):
     """Factuality task."""
 
-    _name = "factuality"
+    _name = "factualitytest"
     _default_col = {
         "article_sent": ["article_sent"],
         "correct_sent": ["correct_sent"],

langtest/utils/custom_types/sample.py

@@ -2338,9 +2338,7 @@ def prompt_eval(self):
                 answer_key="answer",
                 prediction_key="text",
             )
-            if (graded_outputs1[0]["text"].strip() == "CORRECT") and (
-                graded_outputs2[0]["text"].strip() == "CORRECT"
-            ):
+            if self.output(graded_outputs1) and self.output(graded_outputs2):
                 return True
             else:
                 return False
@@ -2365,7 +2363,7 @@ def prompt_eval(self):
                 answer_key="answer",
                 prediction_key="text",
             )
-            return graded_outputs[0]["text"].strip() == "CORRECT"
+            return self.output(graded_outputs)
 
     def is_pass_with_ground_truth(self) -> bool:
         """
@@ -2460,6 +2458,12 @@ def run(self, model, **kwargs):
 
         return True
 
+    def output(self, graded_outputs):
+        """
+        Check if the output is correct.
+        """
+        return list(graded_outputs[0].values())[0].replace("\n", "").strip() == "CORRECT"
+
 
 Sample = TypeVar(
     "Sample",