Fix semantic similarity in LLM eval tutorial

[elenasamuylova]

Fix the example notebook, section "Semantic similarity":
https://github.com/evidentlyai/evidently/blob/main/examples/sample_notebooks/llm_evaluation_tutorial.ipynb

For new API:

text_evals_report = Report(metrics=[
    TextEvals(column_name="response", descriptors=[
        SemanticSimilarity(with_column="question", 
                           display_name="Response-Question Similarity"),
    ])
])

text_evals_report.run(reference_data=None,
                      current_data=assistant_logs[:100],
                      column_mapping=column_mapping)
text_evals_report