from langchain.text_splitter import CharacterTextSplitter
from langchain_community.document_loaders import TextLoader
from langchain_community.document_loaders import DirectoryLoader
from langchain_community.embeddings.sentence_transformer import SentenceTransformerEmbeddings
from langchain_community.vectorstores import Chroma
import streamlit as st

lang = st.radio("Choose Language:",
               ["English", "Chinese"],
               captions= ['Support in English', 'Chinese QnA'])
if lang == "English":
    embedding_function = SentenceTransformerEmbeddings(model_name="all-mpnet-base-v2")
    chdb = Chroma(persist_directory="./chroma_db_info", embedding_function=embedding_function)
else:
    embedding_function = SentenceTransformerEmbeddings(model_name="shibing624/text2vec-base-chinese")
    chdb = Chroma(persist_directory="./chroma_db_ch", embedding_function=embedding_function)
   
query = st.text_input("Enter a query about IC design：")
disnum = 3
if query:
    docs = chdb.similarity_search_with_score(query)
    docnum = len(docs)
    index = 0
    ret = f"Query:{query}\n"
    for ii in range(docnum):    
        doc = docs[ii][0]
        score = docs[ii][1]
        ret += f"Return {index} ({score:.4f}) :\n{doc.page_content}\n"
        index += 1
        if index > disnum:
            break
    st.text(ret)