Update djezzy.py

djezzy.py

@@ -143,7 +143,7 @@ def pip(question,docs_text, docs_embeddings,mots_a_verifier,vector_db):
      else:
         context="\n---------------------\n".join([doc for doc,_ in similar_docs[:4]]if len(similar_docs) >=3 else [doc for doc, _ in similar_docs[:1]])
         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]"
+        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  ###context:{context}\n  ###question: {query_text} "
         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 the answer in french and write theme ,don't mention that you translate the answer \n   ###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
@@ -157,9 +157,9 @@ def pip(question,docs_text, docs_embeddings,mots_a_verifier,vector_db):
     else:
      context = "\n---------------------\n".join([doc for doc, _ in similar_docs2[:2]] if len(similar_docs2) >= 2 else [doc for doc, _ in similar_docs2[:1]])
      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]"
+     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} "
      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 the answer in french and write theme ,don't mention that you translate the answer\n   ###context:{context}<</SYS>>\n\n  ###question: {query_text} [/INST]" 
+             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}" 
         
      #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)
@@ -173,9 +173,9 @@ def pip(question,docs_text, docs_embeddings,mots_a_verifier,vector_db):
    else:
     context="\n---------------------\n".join([doc for doc,_ in similar_docs1[:1]])
     system_message=" "
-    prompt = f"[INST] <<SYS>>\n As Djezzy's chatbot\nread 3 times  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 differentiates between each price and gives the correct answer and does not distinguish between the offers of each price\n ###context:{context}<</SYS>>\n\n {query_text}[/INST]"
+    prompt = f"As Djezzy's chatbot\nread 3 times  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 differentiates between each price and gives the correct answer and does not distinguish between the offers of each price\n ###context:{context}\n {query_text}"
     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\n   ###context:{context}<</SYS>>\n\n  ###question: {query_text} [/INST]" 
+             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 and give me the answer in french ,don't mention that you translate the answer\n   ###context:{context}\n  ###question: {query_text} " 
            
     #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)
@@ -200,7 +200,7 @@ def pip(question,docs_text, docs_embeddings,mots_a_verifier,vector_db):
      system_message=" "
      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} "
      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 \n ###context:{context}<</SYS>>\n\n  ###question: {query_text} [/INST]" 
+             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 and give me the answer in french ,don't mention that you translate the answer \n ###context:{context}\n  ###question: {query_text}" 
          
      #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)