added the app.py file

app.py

@@ -1,8 +1,25 @@
 import gradio as gr
 
+from src.TextSummarizer.pipeline.prediction import PredictionPipeline
 
-def greet(name):
-    return "Hello " + name + "!!"
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+def predict(document):
+    """
+    Method will take the document and summarize it.
+    """
+
+    # predict the summary using my own pre-trained model.
+    summary = PredictionPipeline().predict(document)
+    return summary
+
+
+# Create the frontend.
+input_interfaces: list = []
+
+with gr.Blocks(theme=gr.theme.Soft()) as app:
+    with gr.Row():
+        title = "Text Summarizer..."
+
+
+
+app.launch()

requirements.txt

@@ -13,7 +13,7 @@ transformers
 # notebook
 # boto3
 # mypy-boto3-s3
-# python-box==6.0.2
+python-box==6.0.2
 # ensure==1.0.2
 # fastapi==0.78.0
 # uvicorn==0.18.3

src/TextSummarizer/pipeline/prediction.py

@@ -7,12 +7,13 @@ class PredictionPipeline:
     def __init__(self):
         self.config = ConfigManager().get_model_evaluation_config()
 
-    def predict(self,text):
+    def predict(self, text):
         """
         Predict the tex summarization for the given text.
         """
         gen_kwargs = {"length_penalty": 0.8, "num_beams":8, "max_length": 128}
 
+        # Call our own pretrained model from hugging face.
         summarizer = pipeline("summarization", model=self.config.hub_model_name)
 
         print("document:")