Update app.py to include markdown text

app.py

@@ -29,5 +29,48 @@ def predict(text):
     return '\n'.join(results)
 
 
-iface = gr.Interface(fn=predict, inputs="text", outputs="text")
-iface.launch()
+
+markdown_text = '''
+<br>
+<br>
+This space provides a gradio demo and an easy-to-run wrapper of the pre-trained model for structured sentiment analysis in Norwegian language, pre-trained on the [NoReC dataset](https://huggingface.co/datasets/norec).
+This model is an implementation of the paper "Direct parsing to sentiment graphs" (Samuel _et al._, ACL 2022). The main repository that also contains the scripts for training the model, can be found on the project [github](https://github.com/jerbarnes/direct_parsing_to_sent_graph). 
+
+The current model uses the 'labeled-edge' graph encoding, and achieves the following results on the NoReC dataset:
+
+| Unlabeled sentiment tuple F1 | Target F1  | Relative polarity precision |
+|:----------------------------:|:----------:|:---------------------------:|
+|     0.393                    |  0.468     |        0.939                |
+
+
+The model can be easily used for predicting sentiment tuples as follows: 
+
+```python
+>>> import model_wrapper
+>>> model = model_wrapper.PredictionModel()
+>>> model.predict(['vi liker svart kaffe'])
+[{'sent_id': '0',
+  'text': 'vi liker svart kaffe',
+  'opinions': [{'Source': [['vi'], ['0:2']],
+    'Target': [['svart', 'kaffe'], ['9:14', '15:20']],
+    'Polar_expression': [['liker'], ['3:8']],
+    'Polarity': 'Positive'}]}]
+```
+'''
+
+
+
+with gr.Blocks() as demo:
+    with gr.Row(equal_height=False) as row:
+        text_input = gr.Textbox(label="input")
+        text_output = gr.Textbox(label="output")
+    with gr.Row(scale=4) as row:
+        text_button = gr.Button("submit").style(full_width=True)
+
+    text_button.click(fn=predict, inputs=text_input, outputs=text_output)
+
+    gr.Markdown(markdown_text)
+
+
+
+demo.launch()