tarekfer8 commited on
Commit
e8e36b6
·
verified ·
1 Parent(s): 1a63093

Update djezzy.py

Browse files
Files changed (1) hide show
  1. djezzy.py +1 -1
djezzy.py CHANGED
@@ -201,7 +201,7 @@ def pip(question,docs_text, docs_embeddings,mots_a_verifier,vector_db):
201
  system_message=" "
202
  prompt = f" As Djezzy's chatbot\nread each paraphrase in the context and Answer the question .\ndo not take into consideration the paragraphs which have no relation to the question\n if there is not a paragraph that is related to the question, respond that for this question it's best to reach out to our customer service team . They'll be able to assist you with your needs\n just give me the answer I don't want any other details \n ###context:{context}\n ###question: {query_text} "
203
  if lang=='fr':
204
- prompt=f" As Djezzy's chatbot\nread each paraphrase in the context and Answer the question .\ndo not take into consideration the paragraphs which have no relation to the question\n if there is not a paragraph that is related to the question, respond that for this question it's best to reach out to our customer service team . They'll be able to assist you with your needs\n just give me the answer I don't want any other details \n dont' mention that you used the provided context\n translate the answer in french ,don't mention that you translate the answer \n ###context:{context}\n ###question: {query_text}"
205
 
206
  #prompt = f" <bos><start_of_turn>user \n read each paraphrase in the context and Answer the question .\ndo not take into consideration the paragraphs which have no relation to the question\n if there is not a paragraph that is related to the question, respond that for this question it's best to reach out to our customer service team . They'll be able to assist you with your needs\n just give me the answer I don't want any other details \n###context:\n{contexts[0]}\n ###question:\nWhat are the benefits of opting for the Djezzy Legend 100 DA package? \n###answer:\n{reponses[0]}<eos>\nuser \n read each paraphrase in the context and Answer the question .\ndo not take into consideration the paragraphs which have no relation to the question\n if there is not a paragraph that is related to the question, respond that for this question it's best to reach out to our customer service team . They'll be able to assist you with your needs\n just give me the answer I don't want any other details \n###context:\n{contexts[1]}\n ###question:\nWhat are the benefits of opting for the Djezzy Legend 100 DA package? \n###answer:\n{reponses[1]}<eos>\nuser read each paraphrase in the context and Answer the question .\ndo not take into consideration the paragraphs which have no relation to the question\n if there is not a paragraph that is related to the question, respond that for this question it's best to reach out to our customer service team . They'll be able to assist you with your needs\n just give me the answer I don't want any other details \n###context:\n{context}\n###question:\n{query_text}\n###answer:\n<end_of_turn>\n <start_of_turn>model" # replace the command here with something relevant to your task
207
  #pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer,temperature=0.1,top_p=0.9, max_length=4000)
 
201
  system_message=" "
202
  prompt = f" As Djezzy's chatbot\nread each paraphrase in the context and Answer the question .\ndo not take into consideration the paragraphs which have no relation to the question\n if there is not a paragraph that is related to the question, respond that for this question it's best to reach out to our customer service team . They'll be able to assist you with your needs\n just give me the answer I don't want any other details \n ###context:{context}\n ###question: {query_text} "
203
  if lang=='fr':
204
+ prompt=f" As Djezzy's chatbot\nread each paraphrase in the context and Answer the question .\ndo not take into consideration the paragraphs which have no relation to the question\n if there is not a paragraph that is related to the question, respond that for this question it's best to reach out to our customer service team . They'll be able to assist you with your needs\n just give me the answer I don't want any other details \n dont' mention that you used the provided context\n translate the answer in french and write theme ,don't mention that you translate the answer \n ###context:{context}\n ###question: {query_text}"
205
 
206
  #prompt = f" <bos><start_of_turn>user \n read each paraphrase in the context and Answer the question .\ndo not take into consideration the paragraphs which have no relation to the question\n if there is not a paragraph that is related to the question, respond that for this question it's best to reach out to our customer service team . They'll be able to assist you with your needs\n just give me the answer I don't want any other details \n###context:\n{contexts[0]}\n ###question:\nWhat are the benefits of opting for the Djezzy Legend 100 DA package? \n###answer:\n{reponses[0]}<eos>\nuser \n read each paraphrase in the context and Answer the question .\ndo not take into consideration the paragraphs which have no relation to the question\n if there is not a paragraph that is related to the question, respond that for this question it's best to reach out to our customer service team . They'll be able to assist you with your needs\n just give me the answer I don't want any other details \n###context:\n{contexts[1]}\n ###question:\nWhat are the benefits of opting for the Djezzy Legend 100 DA package? \n###answer:\n{reponses[1]}<eos>\nuser read each paraphrase in the context and Answer the question .\ndo not take into consideration the paragraphs which have no relation to the question\n if there is not a paragraph that is related to the question, respond that for this question it's best to reach out to our customer service team . They'll be able to assist you with your needs\n just give me the answer I don't want any other details \n###context:\n{context}\n###question:\n{query_text}\n###answer:\n<end_of_turn>\n <start_of_turn>model" # replace the command here with something relevant to your task
207
  #pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer,temperature=0.1,top_p=0.9, max_length=4000)