Update app.py
Browse files
app.py
CHANGED
@@ -40,7 +40,7 @@ description = """
|
|
40 |
|
41 |
article = """Your feedback matters!If you like it, contact us at mgupta70@asu.edu.
|
42 |
\n<b>Limitations:</b> \n 1. Current version of program is built upon a very limited size of data. So, it will not be able to respond to many queries related to construction industry. Also, if the subject of discussion is not present in detail in the training documents, one can expect a brief response.\n
|
43 |
-
2. In case response includes numbers like building codes/year, it is generally recommended to double-check the
|
44 |
|
45 |
"""
|
46 |
|
@@ -51,7 +51,7 @@ gr.Interface(
|
|
51 |
title=title,
|
52 |
description=description,
|
53 |
article=article,
|
54 |
-
examples=[["
|
55 |
).launch()
|
56 |
|
57 |
|
|
|
40 |
|
41 |
article = """Your feedback matters!If you like it, contact us at mgupta70@asu.edu.
|
42 |
\n<b>Limitations:</b> \n 1. Current version of program is built upon a very limited size of data. So, it will not be able to respond to many queries related to construction industry. Also, if the subject of discussion is not present in detail in the training documents, one can expect a brief response.\n
|
43 |
+
2. In case response includes numbers like building codes/year, it is generally recommended to double-check the validity of the response because sometimes the program can give an incorrect 'numerical' output. However, we think that the performance of the model in this regard can easily be improved by increasing the size of database.
|
44 |
|
45 |
"""
|
46 |
|
|
|
51 |
title=title,
|
52 |
description=description,
|
53 |
article=article,
|
54 |
+
examples=[["What codal provisions should be used while planning a pedestrian walkway?"], ["How to determine the exact location of existing underground lines?"], ['What one should do to avoid struck-by hazard incidents?']]
|
55 |
).launch()
|
56 |
|
57 |
|