Spaces:
Runtime error
Runtime error
Update appStore/keyword_search.py
Browse files
appStore/keyword_search.py
CHANGED
@@ -8,24 +8,19 @@ import scripts.clean as clean
|
|
8 |
#import needed libraries
|
9 |
import seaborn as sns
|
10 |
from pandas import DataFrame
|
11 |
-
from sentence_transformers import SentenceTransformer, CrossEncoder, util
|
12 |
-
# from keybert import KeyBERT
|
13 |
-
from transformers import pipeline
|
14 |
import matplotlib.pyplot as plt
|
15 |
import numpy as np
|
16 |
import streamlit as st
|
17 |
import pandas as pd
|
18 |
-
from rank_bm25 import BM25Okapi
|
19 |
from sklearn.feature_extraction import _stop_words
|
20 |
import string
|
21 |
from tqdm.autonotebook import tqdm
|
22 |
import numpy as np
|
23 |
|
24 |
-
import tempfile
|
25 |
-
import sqlite3
|
26 |
|
27 |
#Haystack Components
|
28 |
@st.cache(hash_funcs={"builtins.SwigPyObject": lambda _: None},allow_output_mutation=True)
|
|
|
29 |
def start_haystack(temp.name, file):
|
30 |
document_store = InMemoryDocumentStore()
|
31 |
documents = pre.load_document(temp.name, file)
|
@@ -36,7 +31,6 @@ def start_haystack(temp.name, file):
|
|
36 |
pipeline = ExtractiveQAPipeline(reader, retriever)
|
37 |
return pipeline
|
38 |
|
39 |
-
|
40 |
def ask_question(question):
|
41 |
prediction = pipeline.run(query=question, params={"Retriever": {"top_k": 10}, "Reader": {"top_k": 5}})
|
42 |
results = []
|
|
|
8 |
#import needed libraries
|
9 |
import seaborn as sns
|
10 |
from pandas import DataFrame
|
|
|
|
|
|
|
11 |
import matplotlib.pyplot as plt
|
12 |
import numpy as np
|
13 |
import streamlit as st
|
14 |
import pandas as pd
|
|
|
15 |
from sklearn.feature_extraction import _stop_words
|
16 |
import string
|
17 |
from tqdm.autonotebook import tqdm
|
18 |
import numpy as np
|
19 |
|
|
|
|
|
20 |
|
21 |
#Haystack Components
|
22 |
@st.cache(hash_funcs={"builtins.SwigPyObject": lambda _: None},allow_output_mutation=True)
|
23 |
+
|
24 |
def start_haystack(temp.name, file):
|
25 |
document_store = InMemoryDocumentStore()
|
26 |
documents = pre.load_document(temp.name, file)
|
|
|
31 |
pipeline = ExtractiveQAPipeline(reader, retriever)
|
32 |
return pipeline
|
33 |
|
|
|
34 |
def ask_question(question):
|
35 |
prediction = pipeline.run(query=question, params={"Retriever": {"top_k": 10}, "Reader": {"top_k": 5}})
|
36 |
results = []
|