Timothy-Vinzent commited on
Commit
df2b29c
·
verified ·
1 Parent(s): 5771b1d

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +8 -6
app.py CHANGED
@@ -224,18 +224,20 @@ def build_interface():
224
  Constructs the Gradio interface with a submission button and single-submission mechanism.
225
  """
226
  with gr.Blocks() as demo:
227
- gr.Markdown("# System Prompt Applicant Task")
228
  gr.Markdown("## Document and Clause Level Classification")
229
  # General description
230
  gr.Markdown("""
231
- Applicants must create a system prompt for a language model that classifies user queries about legal documents into two specific categories:
232
  1. **Document Level**: Determines whether the query refers to a single document or multiple documents.
233
  2. **Clause Level**: Identifies whether the query is focused on:
234
  - A single clause,
235
  - Multiple clauses, or
236
- - General information not constrained to any specific clause.
 
 
237
 
238
- The model must return a valid JSON object with the following structure:
239
 
240
  ```
241
  {
@@ -248,7 +250,7 @@ def build_interface():
248
  """)
249
 
250
  # Example Inputs and Outputs in an Accordion
251
- with gr.Accordion("**Example Inputs and Expected Outputs**", open=False):
252
  gr.Markdown("""
253
  1. **User Message Example 1:**
254
  - *"Please provide the contract for the lease agreement."*
@@ -301,7 +303,7 @@ def build_interface():
301
  """)
302
 
303
  # Challenge instructions in another Accordion
304
- with gr.Accordion("**Challenge Instructions**", open=False):
305
  gr.Markdown("""
306
  - Design a system prompt that ensures gpt4o-mini generates outputs like those above when given similar user messages.
307
 
 
224
  Constructs the Gradio interface with a submission button and single-submission mechanism.
225
  """
226
  with gr.Blocks() as demo:
227
+ gr.Markdown("# Applicant Task: Writing a System Prompt")
228
  gr.Markdown("## Document and Clause Level Classification")
229
  # General description
230
  gr.Markdown("""
231
+ Applicants must create a system prompt for a language model that classifies user requests about finding information into two specific categories:
232
  1. **Document Level**: Determines whether the query refers to a single document or multiple documents.
233
  2. **Clause Level**: Identifies whether the query is focused on:
234
  - A single clause,
235
  - Multiple clauses, or
236
+ - General information not constrained to any specific clause.
237
+
238
+ Imagine the user is a legal professional who is trying to find information related to their work. We need this classification to guide our downstream approach on how to retrieve this information.
239
 
240
+ That's why the model must return a valid JSON object with the following structure:
241
 
242
  ```
243
  {
 
250
  """)
251
 
252
  # Example Inputs and Outputs in an Accordion
253
+ with gr.Accordion("Example Inputs and Expected Outputs", open=False):
254
  gr.Markdown("""
255
  1. **User Message Example 1:**
256
  - *"Please provide the contract for the lease agreement."*
 
303
  """)
304
 
305
  # Challenge instructions in another Accordion
306
+ with gr.Accordion("Task Instructions", open=False):
307
  gr.Markdown("""
308
  - Design a system prompt that ensures gpt4o-mini generates outputs like those above when given similar user messages.
309