File size: 7,903 Bytes
b30ed6a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
# Import required libraries
import streamlit as st
import youtube
import confluence
import modJira
import time
import similarity
import ingest

# global transcript_result
# transcript_result = ""

# Set page configuration and title for Streamlit
st.set_page_config(page_title="AI-Seeker", page_icon="📼", layout="wide")

# Add header with title and description
st.markdown(
    '<p style="display:inline-block;font-size:40px;font-weight:bold;">AI-Seeker</p> <p style="display:inline-block;font-size:16px;">AI-Seeker is a web-app tool that utilizes APIs to extract text content from YouTube, Confluence and Jira. It incorporates Llama-2-7B-Chat-GGML model with Langchain to provide users with a summary and query-based smart response depending on the content of the media source.<br><br></p>',
    unsafe_allow_html=True
)

txtInputBox = "YouTube"


with st.sidebar.title("Configuration"):
    usecase = st.sidebar.selectbox("Select Media Type:",("YouTube", "Confluence", "Jira"))
    if usecase == "YouTube":
        txtInputBox = "Enter ID of YouTube Video"
        default_value = "Y8Tko2YC5hA"
    elif usecase == "Confluence":
        txtInputBox = "Enter ID of your Confluence Page"
        default_value = "393217"
    elif usecase == "Jira":
        txtInputBox = "Enter the name of your JIRA Project"
        default_value = "jira_test"

    video_id = st.sidebar.text_input(txtInputBox,value=default_value)

    strTranscript = ""
    training_status = "yet_to_start"
    btnTranscript = st.sidebar.button("Transcript")
    btnSummary = st.sidebar.button("Summary")
    btnTrain = st.sidebar.button("Train")
    if btnTrain:
        with st.spinner("Training in Progress..."):
            ingest.main()

    query = st.sidebar.text_input('Enter your question below:', value="What is Python?")
    btnAsk = st.sidebar.button("Query")

    btnClear = st.sidebar.button("Clear Data")
    if btnClear:
        st.session_state.clear()

def fnJira():
    st.info("Transcription")

    if btnTranscript:

        if 'transcript_result' not in st.session_state:
            st.session_state['transcript_result'] = modJira.get_details(video_id)
            transcript_result = st.session_state['transcript_result']
            st.dataframe(transcript_result)
    else:
        if 'transcript_result' in st.session_state:
            transcript_result = st.session_state['transcript_result']
            st.dataframe(transcript_result)

    st.info("Query")
        
    if btnAsk:
        with st.spinner(text="Retrieving..."):
            if 'transcript_answer' not in st.session_state:
                answer = modJira.ask_question(query)
                st.session_state['transcript_answer'] = answer
                #st.success(answer)
            if 'transcript_answer' in st.session_state:
                answer = st.session_state['transcript_answer']

            st.success(answer)

    else:
        if 'transcript_answer' in st.session_state:
            answer = st.session_state['transcript_answer']

            st.success(answer)


def fnConfluence():
    st.info("Transcription")

    if btnTranscript:

        if 'transcript_result' not in st.session_state:
            st.session_state['transcript_result'] = confluence.transcript(video_id)
        transcript_result = st.session_state['transcript_result']
        st.markdown(f"<div style='height: 100px; overflow-y: scroll;'>{transcript_result}</div>", unsafe_allow_html=True)
    else:
        if 'transcript_result' in st.session_state:
            transcript_result = st.session_state['transcript_result']
            st.markdown(f"<div style='height: 100px; overflow-y: scroll;'>{transcript_result}</div>", unsafe_allow_html=True)

    col1, col2 = st.columns([1, 1])

    with col1:
        # with col12:
        st.info("Summary")
        if btnSummary:
            if 'transcript_summary' not in st.session_state:
                with st.spinner(text="Retrieving..."):
                    st.session_state['transcript_summary'] = confluence.summarize()
                    summary = st.session_state['transcript_summary'] 
                    st.success(summary)
        else:
            if 'transcript_summary' in st.session_state:
                summary = st.session_state['transcript_summary']
                st.success(summary)

    with col2:
        st.info("Query")
        
        if btnAsk:
            with st.spinner(text="Retrieving..."):
                if 'transcript_answer' not in st.session_state:
                    answer = confluence.ask_question(query)
                    st.session_state['transcript_answer'] = answer
                    #st.success(answer)
                if 'transcript_answer' in st.session_state:
                    answer = st.session_state['transcript_answer']

                st.success(answer)

        else:
            if 'transcript_answer' in st.session_state:
                answer = st.session_state['transcript_answer']

                st.success(answer)

def fnYoutube():
    st.info("Transcription")

    if btnTranscript:

        if 'transcript_result' not in st.session_state:
            st.session_state['transcript_result'] = youtube.audio_to_transcript(video_id)
        transcript_result = st.session_state['transcript_result']
        st.markdown(f"<div style='height: 100px; overflow-y: scroll;'>{transcript_result}</div>", unsafe_allow_html=True)
    else:
        if 'transcript_result' in st.session_state:
            transcript_result = st.session_state['transcript_result']
            st.markdown(f"<div style='height: 100px; overflow-y: scroll;'>{transcript_result}</div>", unsafe_allow_html=True)

    col1, col2 = st.columns([1, 1])

    with col1:
        # with col12:
        st.info("Summary")
        if btnSummary:
            if 'transcript_summary' not in st.session_state:
                with st.spinner(text="Retrieving..."):
                    st.session_state['transcript_summary'] = youtube.summarize()
                    summary = st.session_state['transcript_summary'] 
                    st.success(summary)
        else:
            if 'transcript_summary' in st.session_state:
                summary = st.session_state['transcript_summary']
                st.success(summary)

    with col2:
        st.info("Query")
        
        if btnAsk:
            with st.spinner(text="Retrieving..."):
                if 'transcript_answer' not in st.session_state:
                    answer = youtube.ask_question(query)
                    st.session_state['transcript_answer'] = answer
                    #st.success(answer)
                if 'transcript_answer' in st.session_state:
                    answer = st.session_state['transcript_answer']

                st.success(answer)

                transcript_start_time, transcript_end_time = similarity.similarity(strQuery=answer)

                st.video(f"https://www.youtube.com/embed/{video_id}", format="video/mp4", start_time=int(transcript_start_time))

        else:
            if 'transcript_answer' in st.session_state:
                answer = st.session_state['transcript_answer']

                st.success(answer)

                transcript_start_time, transcript_end_time = similarity.similarity(strQuery=answer)

                st.video(f"https://www.youtube.com/embed/{video_id}", format="video/mp4", start_time=int(transcript_start_time))

if usecase == "YouTube":
    fnYoutube()
elif usecase == "Confluence":
    fnConfluence()
elif usecase == "Jira":
    fnJira()

# Hide Streamlit header, footer, and menu
hide_st_style = """
    <style>
    #MainMenu {visibility: hidden;}
    footer {visibility: hidden;}
    header {visibility: hidden;}
    </style>
"""
#"""footer {visibility: hidden;}
#    header {visibility: hidden;}"""

# Apply CSS code to hide header, footer, and menu
st.markdown(hide_st_style, unsafe_allow_html=True)