Update app.py
Browse files
app.py
CHANGED
@@ -1,68 +1,63 @@
|
|
1 |
-
import streamlit as st
|
2 |
-
from FlagEmbedding import BGEM3FlagModel
|
3 |
-
from FlagEmbedding import FlagReranker
|
4 |
-
import pandas as pd
|
5 |
-
import numpy as np
|
6 |
-
|
7 |
-
@st.cache_resource
|
8 |
-
def load_model():
|
9 |
-
return BGEM3FlagModel('BAAI/bge-m3',
|
10 |
-
use_fp16=True)
|
11 |
-
@st.cache_resource
|
12 |
-
def load_reranker():
|
13 |
-
return FlagReranker('BAAI/bge-reranker-v2-m3', use_fp16=True)
|
14 |
-
|
15 |
-
@st.cache_data
|
16 |
-
def
|
17 |
-
|
18 |
-
return
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
st.
|
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 |
-
pred_book
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
finalpred = []
|
65 |
-
pred_book.reverse()
|
66 |
-
st.write("Here is your prediction")
|
67 |
-
for n, pred in enumerate(pred_book):
|
68 |
st.write(f"{n+1}: {pred}")
|
|
|
1 |
+
import streamlit as st
|
2 |
+
from FlagEmbedding import BGEM3FlagModel
|
3 |
+
from FlagEmbedding import FlagReranker
|
4 |
+
import pandas as pd
|
5 |
+
import numpy as np
|
6 |
+
|
7 |
+
@st.cache_resource
|
8 |
+
def load_model():
|
9 |
+
return BGEM3FlagModel('BAAI/bge-m3',
|
10 |
+
use_fp16=True)
|
11 |
+
@st.cache_resource
|
12 |
+
def load_reranker():
|
13 |
+
return FlagReranker('BAAI/bge-reranker-v2-m3', use_fp16=True)
|
14 |
+
|
15 |
+
@st.cache_data
|
16 |
+
def load_df(path):
|
17 |
+
df = pd.read_csv(path)
|
18 |
+
return df
|
19 |
+
@st.cache_data
|
20 |
+
def load_embed(path):
|
21 |
+
embeddings_2 = np.load(path)
|
22 |
+
return embeddings_2
|
23 |
+
|
24 |
+
model = load_model()
|
25 |
+
reranker = load_reranker()
|
26 |
+
|
27 |
+
df = load_df('D:/AI_Builder/BookDataFrame.csv')
|
28 |
+
embeddings_2 = load_embed('D:/AI_Builder/BGE_embeddings_2.npy')
|
29 |
+
|
30 |
+
st.header(":books: Book Identifier")
|
31 |
+
|
32 |
+
k = 10
|
33 |
+
with st.form(key='my_form'):
|
34 |
+
sen1 = st.text_area("Book description:")
|
35 |
+
submit_button = st.form_submit_button(label='Submit')
|
36 |
+
|
37 |
+
if submit_button:
|
38 |
+
embeddings_1 = model.encode(sen1,
|
39 |
+
batch_size=12,
|
40 |
+
max_length=8192,
|
41 |
+
)['dense_vecs']
|
42 |
+
similarity = embeddings_1 @ embeddings_2.T
|
43 |
+
|
44 |
+
top_k_qs = []
|
45 |
+
topk = np.argsort(similarity)[-k:]
|
46 |
+
|
47 |
+
for t in topk:
|
48 |
+
pred_sum = df['Summary'].iloc[t]
|
49 |
+
pred_ques = sen1
|
50 |
+
pred = [pred_ques, pred_sum]
|
51 |
+
top_k_qs.append(pred)
|
52 |
+
rrscore = reranker.compute_score(top_k_qs, normalize=True)
|
53 |
+
rrscore_index = np.argsort(rrscore)
|
54 |
+
|
55 |
+
pred_book = []
|
56 |
+
for rr in rrscore_index:
|
57 |
+
pred_book.append(f"{df['Book Name'][topk[rr]]} by {df['Book Author'][topk[rr]]}")
|
58 |
+
|
59 |
+
finalpred = []
|
60 |
+
pred_book.reverse()
|
61 |
+
st.write("Here is your prediction")
|
62 |
+
for n, pred in enumerate(pred_book):
|
|
|
|
|
|
|
|
|
|
|
63 |
st.write(f"{n+1}: {pred}")
|