File size: 7,976 Bytes
7efeab0
 
 
 
 
 
 
 
fcbeb23
 
39f0b40
fcbeb23
 
7efeab0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9c7b0a3
7efeab0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52ecb98
7efeab0
52ecb98
 
7efeab0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import gradio as gr
import pandas as pd
from functions import process_file_bm25 , process_file_bert , generate_plot , generate

#------------------------------------------------------

# Create the state object
state = gr.State()
state.df_bm25 = pd.DataFrame({"Products": [1, 2, 3], "column2": ["A", "B", "C"]})
state.df_bert = pd.DataFrame({"Products": [1, 2, 3], "column2": ["A", "B", "C"]})

state.df_topics_bert = pd.DataFrame({"Topic": [1, 2, 3], "column2": ["A", "B", "C"]})
state.df_topics_bm25 = pd.DataFrame({"Topic": [1, 2, 3], "column2": ["A", "B", "C"]})



with gr.Blocks() as bm25:
    with gr.Row():
        with gr.Column():
            gr.Markdown(
                """
                # Select a CSV/Excel file with column as 'products'
                """)
            inputfile = gr.File(file_types=['.csv','.xlsx'], label="Upload CSV/Excel file")



            #german = gr.Textbox(label="German Text")
            def confirmation():
                doc='File uploaded! Press Cluster button'
                return doc

            def download_doc(doc):
                return doc

            def download_df():
                df1=state.df
                print(df1)
                return df1

            out = gr.Textbox()
            mode=gr.Radio(["Automated clustering", "Manually choose parameters"], label="Type of algorithm", value="Automated clustering",info="Choose any mode u want")
            inputfile.upload(confirmation,inputs=[],outputs=out)
            with gr.Row():
              with gr.Column():
                min_cluster_size=gr.Slider(1, 100, value=5, step=1,label="min_cluster_size", info="Choose minimum No. of docs in a cluster. Lower the value ,higher the clusters created")
                with gr.Column():
                      top_n_words=gr.Slider(1, 25, value=10, step=1,label="top_n_words", info="Choose no of key words for a cluster")
                      with gr.Column():
                            ngram=gr.Slider(1, 3, value=2, step=1,label="ngram", info="Choose no of n-grams words to be taken for clustering")
               
            cluster_btn = gr.Button(value="Cluster")
            #[  df,topics_info,barchart,topics_plot,heatmap,hierarchy]
            tup=cluster_btn.click(process_file_bm25,    inputs=[inputfile,mode,min_cluster_size,top_n_words,ngram],
            outputs=[
                gr.Dataframe(),
                gr.File(label="Download CSV"),
                gr.Dataframe(),
                #'html',
                gr.Plot(label="Barchart"),
                gr.Plot(label="Topics Plot"),
                gr.Plot(label="Heatmap"),
                gr.Plot(label="Hierarchy")
            ])
            print('Tuple **************************' ,tup)
            #[df1, df2, barchart_plot, topics_plot, heatmap_plot, hierarchy_plot] = tup


            llm_btn = gr.Button(value="AI generation ")
            llm_btn.click(download_df,inputs=[],outputs=gr.Dataframe(label="Output"))


with gr.Blocks() as bert:
    with gr.Row():
        with gr.Column():
            gr.Markdown(
                """
                # Select a CSV/Excel file with column as 'products'
                """)
            inputfile = gr.File(file_types=['.csv','.xlsx'], label="Upload CSV/Excel file")



            #german = gr.Textbox(label="German Text")
            def confirmation():
                doc='File uploaded! Press Cluster button'

                return doc

            out = gr.Textbox()
            mode=gr.Radio(["Automated clustering", "Manually choose parameters"], label="Type of algorithm", value="Automated clustering",info="Choose any mode u want")
            inputfile.upload(confirmation,inputs=[],outputs=out)
            with gr.Row():
              with gr.Column():
                min_cluster_size=gr.Slider(1, 100, value=5, step=1,label="min_cluster_size", info="Choose minimum No. of docs in a cluster. Lower the value ,higher the clusters created")
                with gr.Column():
                      top_n_words=gr.Slider(1, 25, value=10, step=1,label="top_n_words", info="Choose no of key words for a cluster")
                      with gr.Column():
                            ngram=gr.Slider(1, 3, value=2, step=1,label="ngram", info="Choose no of n-grams words to be taken for clustering")
               
            cluster_btn = gr.Button(value="Cluster")

            #[  df,topics_info,barchart,topics_plot,heatmap,hierarchy]
            tup=cluster_btn.click(process_file_bert,    inputs=[inputfile,mode,min_cluster_size],
            outputs=[
            gr.Dataframe(),
            gr.Dataframe(),
            gr.Plot(label="Barchart"),
            gr.Plot(label="Topics Plot"),
            gr.Plot(label="Heatmap"),
            gr.Plot(label="Hierarchy")
            ])
         
#___________________________________________
additional_inputs=[
gr.Textbox(
    label="System Prompt",
    max_lines=1,
    interactive=True,
),
gr.Slider(
    label="Temperature",
    value=0.9,
    minimum=0.0,
    maximum=1.0,
    step=0.05,
    interactive=True,
    info="Higher values produce more diverse outputs",
),
gr.Slider(
    label="Max new tokens",
    value=256,
    minimum=0,
    maximum=4096,
    step=64,
    interactive=True,
    info="The maximum numbers of new tokens",
),
gr.Slider(
    label="Top-p (nucleus sampling)",
    value=0.90,
    minimum=0.0,
    maximum=1,
    step=0.05,
    interactive=True,
    info="Higher values sample more low-probability tokens",
),
gr.Slider(
    label="Repetition penalty",
    value=1.2,
    minimum=1.0,
    maximum=2.0,
    step=0.05,
    interactive=True,
    info="Penalize repeated tokens",
)
]

examples=[["I'm planning a vacation to Japan. Can you suggest a one-week itinerary including must-visit places and local cuisines to try?", None, None, None, None, None, ],
          ["Can you write a short story about a time-traveling detective who solves historical mysteries?", None, None, None, None, None,],
          ["I'm trying to learn French. Can you provide some common phrases that would be useful for a beginner, along with their pronunciations?", None, None, None, None, None,],
          ["I have chicken, rice, and bell peppers in my kitchen. Can you suggest an easy recipe I can make with these ingredients?", None, None, None, None, None,],
          ["Can you explain how the QuickSort algorithm works and provide a Python implementation?", None, None, None, None, None,],
          ["What are some unique features of Rust that make it stand out compared to other systems programming languages like C++?", None, None, None, None, None,],
        ]

chat_interface=gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
    additional_inputs=additional_inputs,
    title="Mixtral 46.7B",
    examples=examples,
    concurrency_limit=20,
)

#______________________________________________________
# Create a Gradio interface
df=pd.DataFrame(columns=['Topic'])
df=state.df_topics_bm25
print(df)

excel_analysis_bm25 = gr.Interface(
    fn=generate_plot,  # Placeholder function, will be defined later
    inputs=[
        gr.Dropdown(df['Topic'].unique().tolist(), label="Select Topic Number", type="index"),
        gr.Dropdown(list(df.columns[~df.columns.isin(['Topic'])]), label="Select X Axis", type="index"),
        gr.Dropdown(list(df.columns[~df.columns.isin(['Topic'])]), label="Select Y Axis", type="index"),
        gr.Radio(["scatter", "bar", "line", "box", "wordcloud", "pie"], label="Select Chart Type"),
        gr.Dropdown(["count", "count_distinct", "sum", "average"], label="Select Aggregation Function")
    ],
    outputs=gr.Plot(label="Visualization")
)
demo = gr.TabbedInterface([bm25,chat_interface,excel_analysis_bm25,
     bert], ["TFIDF-BM25 Clustering", "TFIDF-BM25-Topics AI","TFIDF-BM25-Topic analysis","keyBERT"])


demo.launch(share=True,debug=True)