app.py

import streamlit as st
from langchain_community.document_loaders import TextLoader
from langchain_community.text_splitter import CharacterTextSplitter
from langchain_community.embeddings import OpenAIEmbeddings
from langchain_community.vectorstores import Chroma
from langchain_community.chains import RetrievalQA
from langchain_community.embeddings.sentence_transformer import SentenceTransformerEmbeddings


class TextLoader:
    def __init__(self, file):
        self.file = file
    def load(self):
        return self.file.read().decode("utf-8")

st.title("Please upload files that are txt format")
uploaded_file = st.file_uploader("Choose a text file", type=["txt"])

if uploaded_file is not None:
    with open("uploaded_file.txt", "wb") as f:
        f.write(uploaded_file.getbuffer())

text_loader = TextLoader(open("uploaded_file.txt","rb"))
documents = text_loader.load()
# st.write(documents)
text_splitter = CharacterTextSplitter (chunk_size=200,
chunk_overlap=0)

texts= text_splitter.split_documents(documents)
st.write(texts)
# embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
# db = Chroma.from_documents(texts, embeddings)
# db._collection.get(include=['embeddings'])
# retriever = db.as_retriever(search_kwargs={"k": 1})
# docs = retriever.get_relevant_documents("What is the capital of india?")
# st.write("Answer")
# st.text(docs)
# # st.write("File content:")
# # st.text(file_content)