Spaces:
Runtime error
Runtime error
File size: 1,673 Bytes
138d490 c31e1ce 138d490 c31e1ce 138d490 bcb4b7e 64071f7 138d490 |
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 |
import streamlit as st
from bs4 import BeautifulSoup
from langchain.embeddings import HuggingFaceEmbeddings
import pickle
import torch
import io
class CPU_Unpickler(pickle.Unpickler):
def find_class(self, module, name):
if module == 'torch.storage' and name == '_load_from_bytes':
return lambda b: torch.load(io.BytesIO(b), map_location='cpu')
else: return super().find_class(module, name)
@st.cache_resource
def get_hugging_face_model():
model_name = "mchochlov/codebert-base-cd-ft"
hf = HuggingFaceEmbeddings(model_name=model_name)
return hf
@st.cache_resource
def get_db():
with open("codesearchdb.pickle", "rb") as f:
db = CPU_Unpickler(f).load()
return db
def get_similar_links(query, db, embeddings):
embedding_vector = embeddings.embed_query(query)
docs_and_scores = db.similarity_search_by_vector(embedding_vector)
hrefs = []
for docs in docs_and_scores:
html_doc = docs.page_content
soup = BeautifulSoup(html_doc, 'html.parser')
href = [a['href'] for a in soup.find_all('a', href=True)]
hrefs.append(href)
return hrefs
embedding_vector = get_hugging_face_model()
db = get_db()
st.title("📒 DSASearch Engine 🤖 ")
text_input = st.text_input("Enter some text")
button = st.button("Find Similar Questions on Leetcode")
if text_input:
query = text_input
answer = get_similar_links(query, db, embedding_vector)
for link in answer:
st.write(link[0])
else:
st.info("Please Input Valid Text")
with st.sidebar:
st.markdown("""
### Created by Ashwin Rachha.
Source Data : https://github.com/AshwinRachha/LeetCode-Solutions
Medium Blog :
""")
|