hra commited on
Commit
5d8fcd6
1 Parent(s): 7f8ee62

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +2 -2
app.py CHANGED
@@ -90,7 +90,7 @@ def get_learning_curriculum(openapikey,topic):
90
  with gr.Blocks() as demo:
91
  gr.Markdown("<h1><center>BabyAGI creates Learning Curriculum</center></h1>")
92
  gr.Markdown(
93
- """ This is the first step of an experiment using BabyAGI as a "framework" to construct focused use cases (ex: learning curriculums). The flow uses two AI agents 1) Task creation agent: to create a task list & questions 2) Task execution agent: to execute the tasks & find answers to the questions. Unlike original BabyAGI concept, this is not open-ended. \n\nNote: OpenAI agents (gpt-3.5-turbo) & llama-index are used. The analysis takes roughly 120 secs & may not always be consistent. An error occurs when the OpenAI Api key is not provided/ ChatGPT API is overloaded/ChatGPT is unable to correctly decipher & format the output\n\n Future directions: 1) Make the task creation more open ended or longer. 2) Discover multiple learning paths and make ChatGPT introspect on it before finalizing the optimal one 3)Learn from the answers and change the curriculum![visitors](https://visitor-badge.glitch.me/badge?page_id=hra/Curriculum-BabyAGI)"""
94
  )
95
 
96
  with gr.Row() as row:
@@ -99,7 +99,7 @@ with gr.Blocks() as demo:
99
  with gr.Column():
100
  textboxopenapi = gr.Textbox(placeholder="Enter OpenAPI Key...", lines=1,label='OpenAPI Key')
101
  with gr.Row() as row:
102
- examples = gr.Examples(examples=['Acrylic painting','latest NLP topic models','FIFA mobile game','Telemedicine'],
103
  inputs=[textboxtopic])
104
  with gr.Row() as row:
105
  btn = gr.Button("Generate \nCurriculum")
 
90
  with gr.Blocks() as demo:
91
  gr.Markdown("<h1><center>BabyAGI creates Learning Curriculum</center></h1>")
92
  gr.Markdown(
93
+ """ This is the first step of an experiment using BabyAGI as a "framework" to construct focused use cases (ex: learning curriculums). The flow uses two AI agents 1) Task creation agent: to create a task list & questions 2) Task execution agent: to execute the tasks & find answers to the questions. Unlike the original BabyAGI concept, this is not open-ended. \n\nNote: This is a series of experiments to understand AI agents and hence do check the output for quality. OpenAI agents (gpt-3.5-turbo) & llama-index are used. The analysis takes roughly 120 secs & may not always be consistent. An error occurs when the OpenAI Api key is not provided/ ChatGPT API is overloaded/ChatGPT is unable to correctly decipher & format the output\n\n Future directions: 1) Make the task creation more open-ended or longer. 2) Discover multiple learning paths and make ChatGPT introspect on them before finalizing the optimal one 3)Learn from the answers and change the curriculum![visitors](https://visitor-badge.glitch.me/badge?page_id=hra/Curriculum-BabyAGI)"""
94
  )
95
 
96
  with gr.Row() as row:
 
99
  with gr.Column():
100
  textboxopenapi = gr.Textbox(placeholder="Enter OpenAPI Key...", lines=1,label='OpenAPI Key')
101
  with gr.Row() as row:
102
+ examples = gr.Examples(examples=['Acrylic painting','Generative AI','latest NLP topic models','FIFA mobile game','Telemedicine'],
103
  inputs=[textboxtopic])
104
  with gr.Row() as row:
105
  btn = gr.Button("Generate \nCurriculum")