Spaces:
Sleeping
Sleeping
File size: 2,803 Bytes
69881c2 1a3c951 44df7d3 69881c2 44df7d3 1a3c951 44df7d3 1a3c951 44df7d3 1a3c951 44df7d3 1a3c951 800a230 44df7d3 800a230 44df7d3 1a3c951 44df7d3 1a3c951 44df7d3 1a3c951 44df7d3 1a3c951 bddb13b 1a3c951 69881c2 |
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 |
import streamlit as st
# To make things easier later, we're also importing numpy and pandas for
# working with sample data.
import numpy as np
import pandas as pd
import faiss
import numpy as np
from transformers import AutoTokenizer, AutoModel
# Load the embedding model and tokenizer
model_name = "moka-ai/m3e-base"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name)
# Generate some random text contents
texts = ["This is the first document.", "This is the second document.", "And this is the third one.", "Is this the first document?"]
# Convert the text contents to embeddings
embeddings = []
for text in texts:
input_ids = tokenizer.encode(text, return_tensors="pt")
with torch.no_grad():
embedding = model(input_ids)[0][0].numpy()
embeddings.append(embedding)
embeddings = np.array(embeddings)
# Create a Faiss index
d = embeddings.shape[1] # Dimension of the embeddings
index = faiss.IndexFlatIP(d) # Index that uses inner product (dot product) similarity
# Add the embeddings to the index
index.add(embeddings)
# Search for similar documents
query = "This is a new document."
input_ids = tokenizer.encode(query, return_tensors="pt")
with torch.no_grad():
query_embedding = model(input_ids)[0][0].numpy()
k = 2 # Number of similar documents to retrieve
D, I = index.search(query_embedding.reshape(1, -1), k)
# Print the results
st.write(f"Query: {query}")
for i in range(k):
st.write(f"Rank {i+1}: {texts[I[0][i]]} (similarity score: {D[0][i]})")
# Search index for the most similar content
k = 5 # Number of results to retrieve
D, I = index.search(np.array([question_embedding]), k)
# Display the results
st.write("Top {} similar content:".format(k))
for i in range(k):
st.write("{}: {} : {}".format(i+1, knowledge[I[0][i]], I[0][i]))
st.title('My first app')
st.write("Here's our first attempt at using data to create a table:")
df = pd.DataFrame({
'first column': [1, 2, 3, 4],
'second column': [10, 20, 30, 40]
})
st.write(df)
if st.checkbox('Show dataframe'):
chart_data = pd.DataFrame(
np.random.randn(20, 3),
columns=['a', 'b', 'c'])
chart_data
option = st.selectbox(
'Which number do you like best?',
df['first column'])
st.write('You selected: ', option)
text1 = st.text('This is some text.')
if st.button('Say hello'):
st.write('Why hello there')
else:
st.write('Goodbye')
agree = st.checkbox('I agree')
if agree:
st.write('Great!')
age = st.slider('How old are you?', 0, 130, 25)
st.write("I'm ", age, 'years old')
title = st.text_input('Movie title', 'Life of Brian')
st.write('The current movie title is', title)
number = st.number_input('Insert a number')
st.write('The current number is ', number)
|