train/faq.py

def train():
    from langchain_community.document_loaders.csv_loader import CSVLoader
    from langchain.text_splitter import RecursiveCharacterTextSplitter
    from langchain_openai import OpenAIEmbeddings
    from langchain_community.vectorstores.faiss import FAISS
    from langchain_community.document_loaders import WebBaseLoader
    
    documents = WebBaseLoader("https://rise.mmu.ac.uk/what-is-rise/").load()
    documents[0].page_content = documents[0].page_content.split("Student FAQ")[1].strip();

    # Split document in chunks
    text_splitter = RecursiveCharacterTextSplitter(

        chunk_size=250,
        chunk_overlap=50
    )
    docs = text_splitter.split_documents(documents=documents)

    embeddings = OpenAIEmbeddings()
    # Create vectors
    vectorstore = FAISS.from_documents(docs, embeddings)
    # Persist the vectors locally on disk
    vectorstore.save_local("_rise_faq_db");

    return {"trained":"success"}