Spaces:
Sleeping
Sleeping
File size: 3,086 Bytes
1710b29 |
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 |
#Allows you to use Streamlit, a framework for building interactive web applications.
#It provides functions for creating UIs, displaying data, and handling user inputs.
import streamlit as st
#This module provides a way to interact with the operating system, such as accessing environment variables, working with files
#and directories, executing shell commands, etc
import os
#Helps us generate embeddings
#An embedding is a vector (list) of floating point numbers. The distance between two vectors measures their relatedness.
#Small distances suggest high relatedness and large distances suggest low relatedness.
#As Langchain team has been working aggresively on improving the tool, we can see a lot of changes happening every weeek,
#As a part of it, the below import has been depreciated
#from langchain.embeddings import OpenAIEmbeddings
#New import from langchain, which replaces the above
from langchain_openai import OpenAIEmbeddings
#FAISS is an open-source library developed by Facebook AI Research for efficient similarity search and clustering of large-scale datasets, particularly with high-dimensional vectors.
#It provides optimized indexing structures and algorithms for tasks like nearest neighbor search and recommendation systems.
#As Langchain team has been working aggresively on improving the tool, we can see a lot of changes happening every weeek,
#As a part of it, the below import has been depreciated
#from langchain.vectorstores import FAISS
#New import from langchain, which replaces the above
from langchain_community.vectorstores import FAISS
#load_dotenv() is a function that loads variables from a .env file into environment variables in a Python script.
#It allows you to store sensitive information or configuration settings separate from your code
#and access them within your application.
from dotenv import load_dotenv
load_dotenv()
#By using st.set_page_config(), you can customize the appearance of your Streamlit application's web page
st.set_page_config(page_title="Educate Kids", page_icon=":robot:")
st.header("Hey, Ask me something & I will give out similar things")
#Initialize the OpenAIEmbeddings object
embeddings = OpenAIEmbeddings()
#The below snippet helps us to import CSV file data for our tasks
from langchain.document_loaders.csv_loader import CSVLoader
loader = CSVLoader(file_path='myData.csv', csv_args={
'delimiter': ',',
'quotechar': '"',
'fieldnames': ['Words']
})
#Assigning the data inside the csv to our variable here...
data = loader.load()
#Display the data
print(data)
db = FAISS.from_documents(data, embeddings)
#Function to receive input from user and store it in a variable
def get_text():
input_text = st.text_input("You: ", key= input)
return input_text
user_input=get_text()
submit = st.button('Find similar Things')
if submit:
#If the button is clicked, the below snippet will fetch us the similar text
docs = db.similarity_search(user_input)
print(docs)
st.subheader("Top Matches:")
st.text(docs[0])
st.text(docs[1].page_content)
|