:sparkles: add file upload widget

app.py

@@ -29,14 +29,20 @@ def proc_submission(
     max_input_length: int = 768,
 ):
     """
-    proc_submission - a helper function for the gradio module
-    Parameters
-    ----------
-    input_text : str, required, the text to be processed
-    max_input_length : int, optional, the maximum length of the input text, default=512
-    Returns
-    -------
-    str of HTML, the interactive HTML form for the model
+    proc_submission - a helper function for the gradio module to process submissions
+
+    Args:
+        input_text (str): the input text to summarize
+        model_size (str): the size of the model to use
+        num_beams (int): the number of beams to use
+        token_batch_length (int): the length of the token batches to use
+        length_penalty (float): the length penalty to use
+        repetition_penalty (float): the repetition penalty to use
+        no_repeat_ngram_size (int): the no repeat ngram size to use
+        max_input_length (int, optional): the maximum input length to use. Defaults to 768.
+
+    Returns:
+        str in HTML format, string of the summary, str of score
     """
 
     settings = {
@@ -110,6 +116,27 @@ def load_single_example_text(
         text = clean(raw_text, lower=False)
     return text
 
+def load_uploaded_file(file_obj):
+    """
+    load_uploaded_file - process an uploaded file
+
+    Args:
+        file_obj (_type_): Gradio file object
+
+    Returns:
+        str, the uploaded file contents
+    """
+
+    file_path = Path(file_obj[0].name)
+
+    try:
+        with open(file_path, "r", encoding='utf-8', errors='ignore') as f:
+            raw_text = f.read()
+        text = clean(raw_text, lower=False)
+        return text
+    except Exception as e:
+        logging.info(f"Trying to load file with path {file_path}, error: {e}")
+        return "Error: Could not read file. Ensure that it is a valid text file with encoding UTF-8."
 
 if __name__ == "__main__":
 
@@ -130,21 +157,21 @@ if __name__ == "__main__":
 
             gr.Markdown("## Load Inputs & Select Parameters")
             gr.Markdown(
-                "Enter your text below or choose an example, and select the model size and parameters. Press the button to load examples."
+                "Enter text below in the text area. The text will be summarized using the selected parameters. Optionally load an example from the list below or upload a file."
             )
 
-            model_size = gr.inputs.Radio(
-                choices=["base", "large"], label="model size", default="large"
+            model_size = gr.Radio(
+                choices=["base", "large"], label="model size", value="large"
             )
-            num_beams = gr.inputs.Slider(
-                minimum=2, maximum=4, label="num_beams", default=2, step=1
+            num_beams = gr.Radio(
+                choices=[2, 3, 4],
+                label="num beams",
+                value=2,
             )
-            token_batch_length = gr.inputs.Slider(
-                minimum=512,
-                maximum=1024,
-                label="token_batch_length",
-                default=512,
-                step=256,
+            token_batch_length = gr.Radio(
+                choices=[512, 768, 1024],
+                label="token batch length",
+                value=512,
             )
             length_penalty = gr.inputs.Slider(
                 minimum=0.5, maximum=1.0, label="length penalty", default=0.7, step=0.05
@@ -156,12 +183,14 @@ if __name__ == "__main__":
                 default=3.5,
                 step=0.1,
             )
-            no_repeat_ngram_size = gr.inputs.Slider(
-                minimum=2, maximum=4, label="no repeat ngram size", default=3, step=1
+            no_repeat_ngram_size = gr.Radio(
+                choices=[2, 3, 4],
+                label="no repeat ngram size",
+                value=3,
             )
             example_name = gr.Dropdown(
                 list(name_to_path.keys()),
-                label="Load Example",
+                label="Choose an Example",
             )
             load_examples_button = gr.Button(
                 "Load Example",
@@ -171,10 +200,21 @@ if __name__ == "__main__":
                 label="input text",
                 placeholder="Enter text to summarize, the text will be cleaned and truncated on Spaces. Narrative, academic (both papers and lecture transcription), and article text work well. May take a bit to generate depending on the input text :)",
             )
+            gr.Markdown("Upload your own file:")
+            uploaded_file = gr.File(
+                label="Upload a text file",
+                file_count=1,
+                type="file",
+            )
+            load_file_button = gr.Button(
+                "Load Uploaded File"
+            )
 
         with gr.Column():
             gr.Markdown("## Generate Summary")
-            gr.Markdown("Summary generation should take approximately 1-2 minutes for most settings.")
+            gr.Markdown(
+                "Summary generation should take approximately 1-2 minutes for most settings."
+            )
             summarize_button = gr.Button("Summarize!")
 
             output_text = gr.HTML("<p><em>Output will appear below:</em></p>")
@@ -202,6 +242,10 @@ if __name__ == "__main__":
             fn=load_single_example_text, inputs=[example_name], outputs=[input_text]
         )
 
+        load_file_button.click(
+            fn=load_uploaded_file, inputs=[uploaded_file], outputs=[input_text]
+        )
+
         summarize_button.click(
             fn=proc_submission,
             inputs=[