mgupta70 commited on
Commit
5849748
1 Parent(s): 072e932

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +0 -19
app.py CHANGED
@@ -25,12 +25,6 @@ def get_model_reply_no_prev_context(question):
25
  final_response = response.response[1:]
26
  return final_response
27
 
28
-
29
- # def get_model_reply_no_prev_context(question):
30
- # final_response = question
31
- # return final_response
32
-
33
-
34
  title = """
35
  <center>
36
  Knowledge Center at Penta Building Group
@@ -38,25 +32,12 @@ Knowledge Center at Penta Building Group
38
  </center>
39
  """
40
 
41
- # description = """
42
- # <p><b>The idea of this project is to build an ‘AI’ program which by reading through documentation of a company’s projects of the last 10-30 years would consolidate its learning in one place. This ‘intelligent’ program can now assist a PE/PM/anyone in taking decisions which is reflective of the company’s previous experiences and its possible benefits and repercussions. </b><p>\n\n
43
- # This program is designed to answer questions based on the documentation of 'Lessons Learned' at <h3 <a href= "https://www.pentabldggroup.com/" The Penta Building Group </a></h3>, USA. Lessons Learned captures significant events that happened during a project or an initiative. It includes assessment of what worked well and what did not. This helps an organization to avoid repeating mistakes and improve their decision-making process using their own data. The current documentation of Lessons Learned used for this program includes some experiences of Penta in <b> walkway construction, demolition activities, ADA compliance, Fireproofing</b>, etc.
44
- # """
45
- # description = """
46
- # <p><b>The idea of this project is to build an ‘AI’ program which by reading through documentation of a company’s projects of the last 10-30 years would consolidate its learning in one place. This ‘intelligent’ program can now assist a PE/PM/anyone in taking decisions which is reflective of the company’s previous experiences and its possible benefits and repercussions. </b><p>\n\n
47
- # This program is designed to answer questions based on the documentation of 'Lessons Learned' at <h3><a href="https://www.pentabldggroup.com/">The Penta Building Group</a></h3>, USA. Lessons Learned captures significant events that happened during a project or an initiative. It includes assessment of what worked well and what did not. This helps an organization to avoid repeating mistakes and improve their decision-making process using their own data. The current documentation of Lessons Learned used for this program includes some experiences of Penta in <b> walkway construction, demolition activities, ADA compliance, Fireproofing</b>, etc.
48
- # """
49
-
50
-
51
  description = """
52
  <p><b>The idea of this project is to build an ‘AI’ program which by reading through documentation of a company’s projects of the last 10-30 years would consolidate its learning in one place. This ‘intelligent’ program can now assist a PE/PM/anyone in taking decisions which is reflective of the company’s previous experiences and its possible benefits and repercussions. </b></p>
53
 
54
  <p>This program is designed to answer questions based on the documentation of 'Lessons Learned' at <a href="https://www.pentabldggroup.com/">The Penta Building Group</a>, USA. Lessons Learned captures significant events that happened during a project or an initiative. It includes assessment of what worked well and what did not. This helps an organization to avoid repeating mistakes and improve their decision-making process using their own data. The current documentation of Lessons Learned used for this program includes some experiences of Penta in <b> walkway construction, demolition activities, ADA compliance, Fireproofing</b>, etc.</p>
55
  """
56
 
57
-
58
-
59
-
60
  article = """Your feedback matters!If you like it, contact us at mgupta70@asu.edu.
61
  \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
62
  2. In case response includes numbers like building codes/year, it is generally recommended to double-check the sanity of building code or any number provided by our program. However, we think that the performance of the model in this regard can easily be improved by increasing the size of database.
 
25
  final_response = response.response[1:]
26
  return final_response
27
 
 
 
 
 
 
 
28
  title = """
29
  <center>
30
  Knowledge Center at Penta Building Group
 
32
  </center>
33
  """
34
 
 
 
 
 
 
 
 
 
 
 
35
  description = """
36
  <p><b>The idea of this project is to build an ‘AI’ program which by reading through documentation of a company’s projects of the last 10-30 years would consolidate its learning in one place. This ‘intelligent’ program can now assist a PE/PM/anyone in taking decisions which is reflective of the company’s previous experiences and its possible benefits and repercussions. </b></p>
37
 
38
  <p>This program is designed to answer questions based on the documentation of 'Lessons Learned' at <a href="https://www.pentabldggroup.com/">The Penta Building Group</a>, USA. Lessons Learned captures significant events that happened during a project or an initiative. It includes assessment of what worked well and what did not. This helps an organization to avoid repeating mistakes and improve their decision-making process using their own data. The current documentation of Lessons Learned used for this program includes some experiences of Penta in <b> walkway construction, demolition activities, ADA compliance, Fireproofing</b>, etc.</p>
39
  """
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 sanity of building code or any number provided by our program. However, we think that the performance of the model in this regard can easily be improved by increasing the size of database.