File size: 2,697 Bytes
d5b718d 1bb301c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
#@title Utility Functions
def get_history_from_prompt(prompt:str):
if "Here are previous chats for your reference (only use this if you need further information to infer the intent):" in prompt:
history = prompt.split("Here are previous chats for your reference (only use this if you need further information to infer the intent):")
else:
history = prompt.split("Here are previous chats or summary conversation for your reference (only use this if you need further information to infer the intent):")
return history[1].replace("""The Intent:""", '')
def get_latest_user_input_from_prompt(prompt:str):
input = prompt.split("Here is the message you are to classify:")
if "Here are previous chats for your reference (only use this if you need further information to infer the intent):" in prompt:
input = input[1].split("Here are previous chats for your reference (only use this if you need further information to infer the intent):")
else:
input = input[1].split("Here are previous chats or summary conversation for your reference (only use this if you need further information to infer the intent)")
return input[0]
# Get the top 5 intents with the highest values
def get_top_intents(intent_list:list, similarity, n=5, threshold=0.3, flow=None) -> str:
result = dict()
for i in range(len(intent_list)):
if flow:
if intent_list[i] in flow:
# print("intent {} is ignored, because it's not in the possible intent".format(intent_list[i]))
if similarity[0][i].item() > threshold:
result[intent_list[i]] = similarity[0][i].item()
else:
if similarity[0][i].item() > threshold:
result[intent_list[i]] = similarity[0][i].item()
top_intents = sorted(result.items(), key=lambda item: item[1], reverse=True)[:n]
if not top_intents:
top_intents.append(('unknown', 1.0))
return top_intents
def create_embedding(intents:dict, model_en):
intents_description_en = []
for k,v in intents.items():
intents_description_en.append(v)
intents_embedding = model_en.encode(intents_description_en)
return intents_embedding
# def get_embedding(text, model="text-embedding-ada-002"):
# text = text.replace("\n", " ")
# return client.embeddings.create(input = [text], model=model).data[0].embedding
# from openai import OpenAI
# import numpy as np
# client = OpenAI()
# def create_embedding_openai(intents:dict):
# intents_description_en = []
# for k,v in intents.items():
# intents_description_en.append(v)
# embeddings = np.zeros((len(intents_description_en), 1536))
# for i, text in enumerate(intents_description_en):
# embeddings[i,:] = get_embedding(text)
# return embeddings
|