Spaces:
Sleeping
Sleeping
File size: 2,142 Bytes
81cce87 |
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 |
import streamlit as st
import os
import logging
from dotenv import load_dotenv
from langchain_community.embeddings import CohereEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.document_loaders.csv_loader import CSVLoader
#setup logging
logging.basicConfig(level = logging.DEBUG)
#load Environemnt Variables
load_dotenv()
#ensure COHERE_API_KEY is set properly
if not os.getenv("COHERE_API_KEY"):
raise ValueError("COHERE_API_KEY environment variable not set")
st.set_page_config(page_title = "Educate Kids" , page_icon=":robot:")
st.header("SIMILARITY MATCHING")
model_name = "embed-english-v3.0"
user_agent = "my-app/1.0" # Replace with your agent if you Want
embeddings = CohereEmbeddings(model = model_name , user_agent = user_agent)
# embeddings = CohereEmbeddings(model = model_name)
loader = CSVLoader(file_path = "myData.csv" , csv_args={
'delimiter' : ',',
'quotechar' : '"',
'fieldnames' : ['words']
})
data = loader.load()
logging.debug(f"loaded data : {data}")
print(f"loaded data : {data}")
#extract data from data and ensure they are valid
texts = [doc.page_content for doc in data]
#validate the databeing passed to the mebeddings
for text in texts:
logging.debug(f"Document text : {text}")
#initialize FAISS database
try:
db = FAISS.from_documents(data , embeddings)
st.write("FAISS database created successfully")
except ValueError as e:
logging.error(f"Error occured : {e}")
for text in texts:
try:
embedding = embeddings.embed_documents([text])
logging.debug(f"Embeddings : {embedding}")
except ValueError as ve:
logging.error(f"Failed to embed document: {text} with error :{ve}")
def get_input():
input_text = st.text_input("you : " , key = "input")
return input_text
user_input = get_input()
submit = st.button("Find similar Things")
if submit:
docs = db.similarity_search(user_input)
print(docs)
st.subheader("Top Matches : ")
st.text(docs[0].page_content)
st.text(docs[1].page_content) |