|
import openai |
|
import ast |
|
from langchain.prompts import PromptTemplate |
|
|
|
|
|
def MasterLLM(Role, FewShotExamples, UserPrompt): |
|
Role = [{"role": "system", "content": Role}] |
|
UserPrompt = [{"role": "user", "content": UserPrompt}] |
|
message = [*Role, *FewShotExamples, *UserPrompt] |
|
response = openai.ChatCompletion.create( |
|
engine="GPT4_32k", |
|
messages= message, |
|
temperature=0, |
|
) |
|
return response['choices'][0]['message']['content'] |
|
|
|
def intent_recognition(UserPrompt): |
|
|
|
IntentRole = "You are an expert intent classifier. Your job is to understand user input and classify into either of the following 'Describe', 'Compare', 'Others' and 'Transfer' as per the given examples.Do not explain" |
|
|
|
IntentExamples = [ |
|
{"role": "user", "content": "What is the difference between step X and step y for a opening a XYZ?"}, |
|
{"role": "assistant", "content": "Compare"}, |
|
{"role": "user", "content": "Compare differences between the following services"}, |
|
{"role": "assistant", "content": "Compare"}, |
|
{"role": "user", "content": "Differentiate the following services on the basis of price"}, |
|
{"role": "assistant", "content": "Compare"}, |
|
{"role": "user", "content": "Which of the follwing is better"}, |
|
{"role": "assistant", "content": "Compare"}, |
|
{"role": "user", "content": "Explain the difference between pricing of service A and B"}, |
|
{"role": "assistant", "content": "Compare"}, |
|
{"role": "user", "content": "Why should I choose service A over service B"}, |
|
{"role": "assistant", "content": "Compare"}, |
|
{"role": "user", "content": "Weigh the following services on their requirements"}, |
|
{"role": "assistant", "content": "Compare"}, |
|
{"role": "user", "content": "Service A vs Service B"}, |
|
{"role": "assistant", "content": "Compare"}, |
|
{"role": "user", "content": "Describe requirements for the following service"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "Tell me about A"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "Tell me about wholesale of software and retail sale of software"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "How can I appply for the following service"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "What are the conditions for A"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "How much is the price to apply for the following service"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "Explain the requirements of service A"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "Define the important characteristics of the following service"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "Difference between the following services"}, |
|
{"role": "assistant", "content": "Compare"}, |
|
{"role": "user", "content": "How to do service A"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "How much time to get A for License B"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "Can you help me with XYZVS"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "Please help me with XYZVS"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "How to enquire service XYZVS"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "How to access the service XYZVS"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "How to get information on service XYZVS"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "How to find about service XYZVS"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "Provide info on something"}, |
|
{"role": "assistant", "content": "Describe"}, |
|
{"role": "user", "content": "Can you send this to me"}, |
|
{"role": "assistant", "content": "Transfer"}, |
|
{"role": "user", "content": "Send it to my number"}, |
|
{"role": "assistant", "content": "Transfer"}, |
|
{"role": "user", "content": "This is my number XXXXXXXXX Send it to me"}, |
|
{"role": "assistant", "content": "Transfer"}, |
|
{"role": "user", "content": "Transfer it to my nummber"}, |
|
{"role": "assistant", "content": "Transfer"}, |
|
{"role": "user", "content": "Send this to me on Whatsapp"}, |
|
{"role": "assistant", "content": "Transfer"}, |
|
{"role": "user", "content": "I want to see this on my phone"}, |
|
{"role": "assistant", "content": "Transfer"}, |
|
{"role": "user", "content": "Whatsapp it to me"}, |
|
{"role": "assistant", "content": "Transfer"}, |
|
{"role": "user", "content": "WhatsApp it to me please"}, |
|
{"role": "assistant", "content": "Transfer"} |
|
] |
|
|
|
intent = MasterLLM(IntentRole, IntentExamples, UserPrompt) |
|
|
|
return intent |
|
|
|
def entity_recognition_main(UserPrompt, LicenseName): |
|
entity = [] |
|
|
|
try: |
|
EntityRole = f"You are a Named Entity Recognition expert. You can find relevant entities from a list based on the mentioned user prompt. Following is a list of license names: {LicenseName}. Extract relevant entities from the list of license names based on User Prompt.Extract exact license names from the list matching the extracted entities. Make sure the extracted entities are present in the given list of license names. Strictly make sure that output includes the entity from the given list of license name and not the entity from User Prompt. Answer should only be in a python list format. Make sure to match entities on synonyms as well. Remove duplicate entities from the response. If there is no match, print blank list. Again, strictly make sure the entity returned must be an exact match of license names in the provided list" |
|
EntityExamples = [] |
|
entity = ast.literal_eval(MasterLLM(EntityRole, EntityExamples, UserPrompt)) |
|
|
|
except: |
|
entity = [] |
|
|
|
entity = list(set(entity)) |
|
|
|
return entity |
|
|
|
|
|
def describe(entity, final_json, UserPrompt): |
|
|
|
prompt = f"Describe in strictly not more than 4 lines - {entity} on the following data: {final_json} as per the following question: {UserPrompt}. " |
|
|
|
prompt_template = PromptTemplate( |
|
input_variables = ['context'], |
|
template = """You are an online assistant for Saudi Business Centre. |
|
You will provide concise and to the point answers to the user questions. |
|
Answer must be well-structured, short and must include all essential points in strictly not more than 4 lines. |
|
Strictly make sure to give the answer human-like feel. |
|
Strictly make sure to not give extra information more than asked by the user |
|
Provide answer to the following: {context}""") |
|
|
|
|
|
return prompt,prompt_template |
|
|
|
def compare(entity,final_json, UserPrompt): |
|
prompt = f"Compare the following {entity} on their following data {final_json} and frame in strictly not more than 4 lines as per the following question {UserPrompt}" |
|
|
|
prompt_template = PromptTemplate( |
|
input_variables = ['context'], |
|
template = "You are an online assistant for Saudi Business Centre. You will provide concise and to the point answers to the user questions. Answer must be well-structured, short and must include all essential points in strictly not more than 4 lines. Do not assume anything while providing output. Make sure the tone is formal and friendly. Strictly make sure to give the answer human-like feel. Make sure at the end of the comparison, you give a innovative insight from the answer about the comparison. Provide answer to the following: {context}") |
|
|
|
return prompt,prompt_template |
|
|
|
def RAG(UserPrompt,entity): |
|
|
|
context = """You are an online assistant for Saudi Business Centre. You will provide concise and to the point answers to the user questions according to the context provided. Ensure the answers are in bullets only. Do not assume anything while providing output. Make sure the tone is formal and friendly.Make sure you're able to answer generic questions from the provided data. Answer the question given the information in those contexts. Apart from questions related to licenses and services, you can also use information from data to answer user queries about businesses, investments and how SBC can help them achieve the same, these you've to figure out from the context provided. If you cannot find the answer to the question, give a 2 line explanation of why you don't know the answer. Answer must be well-structured, short and must include all essential points in strictly not more than 4 lines but make sure the short answer must cover the crux of all entities in the given context as per user prompt. User Prompt:""" |
|
if len(entity) != 0: |
|
listToStr = ', '.join([str(elem) for i, elem in enumerate(entity)]) |
|
prompt = f"{UserPrompt}"+f"answer using the following licenses if available: {listToStr}" |
|
else: |
|
prompt = f"{UserPrompt}" |
|
|
|
|
|
|
|
|
|
|
|
return context+":"+prompt |
|
|
|
def sentiment(UserPrompt, PrevEntity): |
|
|
|
MemoryRole = "You are a sentiment analysis assistant. You analyze users prompt and decide whether it requires a conversational context or not. If the user prompt requires memory addition, you will answer as 'Memory' else you will answer as 'Direct'. Make sure to focus on finding pronouns like That, Those, Them, Their, it, this" |
|
|
|
MemoryExamples=[ |
|
{"role": "user", "content": "Can you share more details about the above license?"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "Is the above better than license AAAAA"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "Share details for all of the above"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "Do above licenses require anything"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "Can you Tell me more about this"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "Can you tell me about their prices/fees"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "Tell me more about it in detail"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "How is it better than service BB?"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "What is the price for it"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "How can I get that license"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "Are there any alternatives to this ?"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "Is there anything additional I should know"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "Can you explain to me further ?"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "What are the key differences between those?"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "Do I XXXXXX for this?"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "Can you elaborate more"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "How long does it take"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
{"role": "user", "content": "How much time will it take?"}, |
|
{"role": "assistant", "content": "Memory"}, |
|
] |
|
|
|
if_memory = MasterLLM(MemoryRole, MemoryExamples, UserPrompt) |
|
print(if_memory) |
|
print() |
|
|
|
listToStr = ', '.join([str(elem) for i, elem in enumerate(PrevEntity)]) |
|
|
|
if if_memory in 'Direct' or len(PrevEntity) == 0: |
|
FullPrompt = UserPrompt |
|
PrevEntity = [] |
|
else: |
|
FullPrompt = f"{UserPrompt}, where previous conversation had been about {listToStr}" |
|
|
|
|
|
return FullPrompt, PrevEntity |
|
|
