File size: 1,686 Bytes
63db6ac c9fa165 72c879a beda96a 63db6ac 72c879a b19e82a 72c879a beda96a 72c879a beda96a 72c879a 63db6ac beda96a 72c879a 63db6ac beda96a 72c879a beda96a 72c879a 63db6ac 72c879a beda96a 72c879a beda96a 72c879a |
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 |
import streamlit as st
from sentence_transformers import SentenceTransformer
import datasets
import faiss
import time
import faiss
if "initialized" not in st.session_state:
st.session_state.dataset = datasets.load_dataset('A-Roucher/english_historical_quotes', download_mode="force_redownload")['train']
st.session_state.all_authors = list(set(st.session_state.dataset['author']))
model_name = "BAAI/bge-small-en-v1.5" # "sentence-transformers/all-MiniLM-L6-v2" # # "Cohere/Cohere-embed-english-light-v3.0" # "sentence-transformers/all-MiniLM-L6-v2"
st.session_state.encoder = SentenceTransformer(model_name)
st.session_state.index = faiss.read_index('index_alone.faiss')
st.session_state.initialized=True
def search(query):
start = time.time()
if len(query.strip()) == 0:
return ""
query_embedding = st.session_state.encoder.encode([query])
_, samples = st.session_state.index.search(
query_embedding, k=10
)
quotes = st.session_state.dataset.select(samples[0])
result = "\n\n"
for i in range(len(quotes)):
result += f"###### {quotes['author'][i]}\n> {quotes['quote'][i]}\n----\n"
delay = "%.3f" % (time.time() - start)
return f"_Computation time: **{delay} seconds**_{result}"
st.markdown(
"""
<style>
div[data-testid="column"]
{
align-self:flex-end;
}
</style>
""",unsafe_allow_html=True
)
col1, col2 = st.columns([8, 2])
text_input = col1.text_input("Type your idea here:", placeholder="Knowledge of history is power.")
submit_button = col2.button("_Search quotes!_")
if submit_button:
st.markdown(search(text_input))
|