Update djezzy.py

djezzy.py

@@ -132,12 +132,12 @@ def pip(question,docs_text, docs_embeddings,mots_a_verifier,vector_db):
          print("As a chatbot for Djezzy, I can provide information exclusively about our affiliated companies. Unfortunately, I'm unable to respond to inquiries outside of that scope.")
          prompt=" for this question write this answer and don't add anything  :As a chatbot for Djezzy, I can provide information exclusively about our affiliated companies. Unfortunately, I'm unable to respond to inquiries outside of that scope."
          if lang=='fr':
-             prompt="for this question translate this answer in frensh  and write theme , don't add anything :As a chatbot for Djezzy, I can provide information exclusively about our affiliated companies. Unfortunately, I'm unable to respond to inquiries outside of that scope."
+             prompt="for this question translate this answer in frensh  and write theme , don't add anything and don't mention that you translate the answer :As a chatbot for Djezzy, I can provide information exclusively about our affiliated companies. Unfortunately, I'm unable to respond to inquiries outside of that scope."
        else:
         print("I apologize, I don't fully understand your question. You can contact our customer service for answers to your needs, or if you can provide more details, I would be happy to help.")
         prompt="for this question write this answer and don't add anything: I apologize, I don't fully understand your question. You can contact our customer service for answers to your needs, or if you can provide more details, I would be happy to help."
         if lang=='fr':
-             prompt="for this question translate this answer in frensh  and write theme,don't add anything :As a chatbot for Djezzy, I can provide information exclusively about our affiliated companies. Unfortunately, I'm unable to respond to inquiries outside of that scope."
+             prompt="for this question translate this answer in frensh  and write theme,don't add anything and don't mention that you translate the answer :As a chatbot for Djezzy, I can provide information exclusively about our affiliated companies. Unfortunately, I'm unable to respond to inquiries outside of that scope."
 
         
      else:
@@ -145,7 +145,7 @@ def pip(question,docs_text, docs_embeddings,mots_a_verifier,vector_db):
         system_message=" "
         prompt = f"[INST] <<SYS>>\n 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  ###context:{context}<</SYS>>\n\n  ###question: {query_text} [/INST]"
         if lang=='fr':
-             prompt=f"[INST] <<SYS>>\n 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 and give me the answer in french ,don't mention that you translate the answer   ###context:{context}<</SYS>>\n\n  ###question: {query_text} [/INST]" 
+             prompt=f"[INST] <<SYS>>\n 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   ###context:{context}<</SYS>>\n\n  ###question: {query_text} [/INST]" 
         #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
         #pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer,temperature=0.1,top_p=0.9, max_length=4000)
         #result = pipe(prompt)
@@ -159,7 +159,7 @@ def pip(question,docs_text, docs_embeddings,mots_a_verifier,vector_db):
      system_message=" "
      prompt = f"[INST] <<SYS>>\n  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}<</SYS>>\n\n  ###question: {query_text} [/INST]"
      if lang=='fr':
-             prompt=f"[INST] <<SYS>>\n 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 and give me the answer in french ,don't mention that you translate the answer   ###context:{context}<</SYS>>\n\n  ###question: {query_text} [/INST]" 
+             prompt=f"[INST] <<SYS>>\n 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   ###context:{context}<</SYS>>\n\n  ###question: {query_text} [/INST]" 
         
      #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
      #pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer,temperature=0.1,top_p=0.9, max_length=4000)