zinoubm commited on
Commit
9bb4c09
·
1 Parent(s): f3f50da

adding final touches

Browse files
__pycache__/openai_manager.cpython-310.pyc CHANGED
Binary files a/__pycache__/openai_manager.cpython-310.pyc and b/__pycache__/openai_manager.cpython-310.pyc differ
 
app.py CHANGED
@@ -2,6 +2,19 @@ import gradio as gr
2
  from qdrant import qdrant_manager
3
  from openai_manager import openai_manager
4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
 
6
  def generate(keywords):
7
  try:
@@ -22,18 +35,7 @@ iface = gr.Interface(
22
  fn=generate,
23
  inputs="text",
24
  outputs="text",
25
- description="""
26
- In this project, Im using Few-Shot Learning as an alternative to Fine-Tuning and Prompt
27
- Engineering methods. While Prompt Engineering offers a cost-effective and swift approach
28
- for development, it falls short in providing a comprehensive level of instruction
29
- definition. For instance, crafting instructions that simulate a specific writing style proves to be exceptionally challenging.
30
- On the other hand, Fine-Tuning excels in terms of instruction integration as it
31
- comprehends and learns instructions rather than merely receiving them. However, it
32
- comes with challenges such as complexity, high costs, and time-intensive processes.
33
- Few-Shot Learning elegantly positions itself between these two approaches, offering the
34
- best of both worlds. It provides an enticing balance that you might want to explore.
35
- Why not give it a try?
36
- """,
37
  title="Sales Role Play Generator - Few Shots Learning",
 
38
  )
39
  iface.launch()
 
2
  from qdrant import qdrant_manager
3
  from openai_manager import openai_manager
4
 
5
+ description = """
6
+ In this project, Im using Few-Shot Learning as an alternative to Fine-Tuning and Prompt
7
+ Engineering methods. While Prompt Engineering offers a cost-effective and swift approach
8
+ for development, it falls short in providing a comprehensive level of instruction
9
+ definition. For instance, crafting instructions that simulate a specific writing style proves to be exceptionally challenging.
10
+ On the other hand, Fine-Tuning excels in terms of instruction integration as it
11
+ comprehends and learns instructions rather than merely receiving them. However, it
12
+ comes with challenges such as complexity, high costs, and time-intensive processes.
13
+ Few-Shot Learning elegantly positions itself between these two approaches, offering the
14
+ best of both worlds. It provides an enticing balance that you might want to explore.
15
+ Why not give it a try?
16
+ """
17
+
18
 
19
  def generate(keywords):
20
  try:
 
35
  fn=generate,
36
  inputs="text",
37
  outputs="text",
 
 
 
 
 
 
 
 
 
 
 
 
38
  title="Sales Role Play Generator - Few Shots Learning",
39
+ description=description,
40
  )
41
  iface.launch()