File size: 2,884 Bytes
8dcfc9b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
import streamlit as st
import openai
import os
import re
import ast

openai.api_key = os.getenv("OPENAI_API_KEY")

SYSTEM_PROMPT = "You are a smart and intelligent Named Entity Recognition (NER) system. I will provide you the definition of the entities you need to extract, the sentence from where your extract the entities and the output format with examples."

USER_PROMPT_1 = "Are you clear about your role?"

ASSISTANT_PROMPT_1 = "Sure, I'm ready to help you with your NER task. Please provide me with the necessary information to get started."
GUIDELINES_PROMPT = (
    "Entity Definition:\n"
    "1. PERSON: Short name or full name of a person from any geographic regions.\n"
    "2. DATE: Any format of dates. Dates can also be in natural language.\n"
    "3. LOC: Name of any geographic location, like cities, countries, continents, districts etc.\n"
    "\n"
    "Output Format:\n"
    "{{'PERSON': [list of entities present], 'DATE': [list of entities present], 'LOC': [list of entities present]}}\n"
    "If no entities are presented in any categories keep it None\n"
    "\n"
    "Examples:\n"
    "\n"
    "1. Sentence: Mr. Jacob lives in Madrid since 12th January 2015.\n"
    "Output: {{'PERSON': ['Mr. Jacob'], 'DATE': ['12th January 2015'], 'LOC': ['Madrid']}}\n"
    "\n"
    "2. Sentence: Mr. Rajeev Mishra and Sunita Roy are friends and they meet each other on 24/03/1998.\n"
    "Output: {{'PERSON': ['Mr. Rajeev Mishra', 'Sunita Roy'], 'DATE': ['24/03/1998'], 'LOC': ['None']}}\n"
    "\n"
    "3. Sentence: {}\n"
    "Output: "
)


COLORED_ENTITY = {"PERSON": "red", "DATE": "blue", "LOC": "green"}


def openai_chat_completion_response(final_prompt):
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=[
            {"role": "system", "content": SYSTEM_PROMPT},
            {"role": "user", "content": USER_PROMPT_1},
            {"role": "assistant", "content": ASSISTANT_PROMPT_1},
            {"role": "user", "content": final_prompt},
        ],
    )

    return response["choices"][0]["message"]["content"].strip(" \n")


my_sentence = st.text_input("Your Sentence")
if st.button("Submit"):
    GUIDELINES_PROMPT = GUIDELINES_PROMPT.format(my_sentence)
    ners = openai_chat_completion_response(GUIDELINES_PROMPT)
    ners_dictionary = ast.literal_eval(ners)
    for entity_type, entity_list in ners_dictionary.items():
        entity_list = list(set(entity_list))
        for ent in entity_list:
            if ent != "None":
                my_sentence = re.sub(
                    ent,
                    ":"
                    + COLORED_ENTITY[entity_type]
                    + "["
                    + ent
                    + "\["
                    + entity_type
                    + "\]"
                    + "]",
                    my_sentence,
                )
    st.markdown(my_sentence)