Wajahat698 commited on
Commit
d4d6745
·
verified ·
1 Parent(s): 0594768

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -3
app.py CHANGED
@@ -282,14 +282,14 @@ tools = [knowledge_base_tool, google_search_tool]
282
  prompt_message = f"""
283
  **ROLE:** Act as expert content writer .
284
 
285
- **TASK:** Generate meaningful content for user based upon user query: [message] .
286
 
287
 
288
  **TONE:** Write in an active and enthusiastic tone.
289
  **Restrictions:** Strictly do not mention "Conclusion" in your response .
290
 
291
 
292
- First classify this query : " [message]" as general or trust based query for your convenience. Do not explicity mention in response .
293
 
294
  **Classification Criteria :**
295
  General Query: If the user asks for general information (e.g., blogs, posts, articles, reports etc) for any organization , classify it as a general query.
@@ -299,7 +299,7 @@ prompt_message = f"""
299
  * It should properly follow format of blogs , reports and articles for any organization. No need to literally follow the knowledge base here .
300
  * Do not mention name of trust bucket [ stability, development , relationship , competence , benefit , vision] in your response .
301
  If query is related to trust builders or proof points , refer to knowledge base :[{knowledge_base}] and follow the instructions :
302
- * Generate a compelling copy between 1000-2000 words based upon guidlines & objective of specific trust bucket mentioned in [message].
303
  * Strictly Do not mention "Trust" , "Stability" , "Development" , "Relationship" , "Competence" , "benefit" , "vision" words in your response .
304
  * If [message] contains more than one trust bucket then Do not make seperate sections/headings for both the buckets .
305
  * Proof Points: Use guiding principles or objectives from the knowledge base to support your points . Add sub-points everytime
 
282
  prompt_message = f"""
283
  **ROLE:** Act as expert content writer .
284
 
285
+ **TASK:** Generate meaningful content for user based upon user query: [{input}] .
286
 
287
 
288
  **TONE:** Write in an active and enthusiastic tone.
289
  **Restrictions:** Strictly do not mention "Conclusion" in your response .
290
 
291
 
292
+ First classify this query : " [{input}]" as general or trust based query for your convenience. Do not explicity mention in response .
293
 
294
  **Classification Criteria :**
295
  General Query: If the user asks for general information (e.g., blogs, posts, articles, reports etc) for any organization , classify it as a general query.
 
299
  * It should properly follow format of blogs , reports and articles for any organization. No need to literally follow the knowledge base here .
300
  * Do not mention name of trust bucket [ stability, development , relationship , competence , benefit , vision] in your response .
301
  If query is related to trust builders or proof points , refer to knowledge base :[{knowledge_base}] and follow the instructions :
302
+ * Generate a compelling copy between 1000-2000 words based upon guidlines & objective of specific trust bucket mentioned in [{input}].
303
  * Strictly Do not mention "Trust" , "Stability" , "Development" , "Relationship" , "Competence" , "benefit" , "vision" words in your response .
304
  * If [message] contains more than one trust bucket then Do not make seperate sections/headings for both the buckets .
305
  * Proof Points: Use guiding principles or objectives from the knowledge base to support your points . Add sub-points everytime