File size: 5,100 Bytes
dd124ec
55d03cf
dd124ec
 
55d03cf
 
dd124ec
 
 
 
 
 
 
 
 
 
 
 
2a53bc3
dd124ec
 
f75d001
 
ef1d02b
a087ad0
f75d001
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dd124ec
 
 
 
 
 
121a5b7
dd124ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0bb6ca7
 
 
dd124ec
 
 
0bb6ca7
a087ad0
 
f75d001
dd124ec
 
f75d001
 
 
dd124ec
 
 
f75d001
 
 
 
 
 
 
 
dd124ec
 
 
f75d001
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dd124ec
 
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
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
# set path
import glob, os, sys; sys.path.append('../scripts')

#import helper
import scripts.process as pre
import scripts.clean as clean

#import needed libraries
import seaborn as sns
from pandas import DataFrame
import matplotlib.pyplot as plt
import numpy as np
import streamlit as st
import pandas as pd 
from sklearn.feature_extraction import _stop_words
import string
from tqdm.autonotebook import tqdm
import numpy as np
import tempfile


#Haystack Components
@st.cache(hash_funcs={"builtins.SwigPyObject": lambda _: None},allow_output_mutation=True)

def start_haystack(documents_processed):
    document_store = InMemoryDocumentStore()
    document_store.write_documents(documents_processed)
    retriever = TfidfRetriever(document_store=document_store)
    reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2-distilled", use_gpu=True)
    pipeline = ExtractiveQAPipeline(reader, retriever)
    return pipeline

def ask_question(question):
    prediction = pipeline.run(query=question, params={"Retriever": {"top_k": 10}, "Reader": {"top_k": 5}})
    results = []
    for answer in prediction["answers"]:
        answer = answer.to_dict()
        if answer["answer"]:
            results.append(
                {
                    "context": "..." + answer["context"] + "...",
                    "answer": answer["answer"],
                    "relevance": round(answer["score"] * 100, 2),
                    "offset_start_in_doc": answer["offsets_in_document"][0]["start"],
                }
            )
        else:
            results.append(
                {
                    "context": None,
                    "answer": None,
                    "relevance": round(answer["score"] * 100, 2),
                }
            )
    return results

def app():
    with st.container():
        st.markdown("<h1 style='text-align: center; color: black;'> Keyword Search</h1>", unsafe_allow_html=True)
        st.write(' ')
        st.write(' ')

    with st.expander("ℹ️ - About this app", expanded=False):

        st.write(
            """     
            The *Keyword Search* app is an easy-to-use interface built in Streamlit for doing keyword search in policy document - developed by GIZ Data and the Sustainable Development Solution Network.
            """
        )

        st.markdown("")
    st.markdown("")
    st.markdown("##  📌 Step One: Upload document ")
    
    with st.container():
        file = st.file_uploader('Upload PDF File', type=['pdf', 'docx', 'txt'])
        if file is not None:
            with tempfile.NamedTemporaryFile(mode="wb") as temp:
                bytes_data = file.getvalue()
                temp.write(bytes_data)
                file_name = file.name
                file_path = temp.name
                
                st.write("Filename: ", file.name)
                
                # load document
                documents = pre.load_document(temp.name,file_name)
                documents_processed = pre.preprocessing(documents)
                pipeline = start_haystack(documents_processed)
                #docs = pre.load_document(temp.name, file)

                # preprocess document
                #haystackDoc, dataframeDoc, textData, paraList = clean.preprocessing(docs)

                question = st.text_input("Please enter your question here, we will look for the answer in the document.",
                                         value="floods",)
                                         
                
                if st.button("Find them."):
                     with st.spinner("👑 Performing semantic search on"):#+file.name+"..."):
                        try:
                            msg = 'Asked ' + question
                            logging.info(msg)
                            st.session_state.results = ask_question(question)    
                        except Exception as e:
                            logging.exception(e)
                    
                
                
                if st.session_state.results:
                    st.write('## Top Results')
                    for count, result in enumerate(st.session_state.results):
                        if result["answer"]:
                            answer, context = result["answer"], result["context"]
                            start_idx = context.find(answer)
                            end_idx = start_idx + len(answer)
                            st.write(
                                markdown(context[:start_idx] + str(annotation(body=answer, label="ANSWER", background="#964448", color='#ffffff')) + context[end_idx:]),
                                unsafe_allow_html=True,
                            )
                            st.markdown(f"**Relevance:** {result['relevance']}")
                        else:
                            st.info(
                                "🤔 &nbsp;&nbsp; Haystack is unsure whether any of the documents contain an answer to your question. Try to reformulate it!"
                            )