app.py

import streamlit as st
from langchain.document_loaders import TextLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains import RetrievalQA
from langchain.llms import HuggingFaceHub

@st.cache_resource
def load_vector_store():
    loader = TextLoader("data/sample.txt")
    documents = loader.load()

    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
    chunks = splitter.split_documents(documents)

    embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
    db = FAISS.from_documents(chunks, embedding_model)
    return db

def main():
    st.title("📄 Ask Your Document (RAG with LangChain + Hugging Face)")
    st.write("Upload a document, ask questions, and get answers powered by open-source LLMs!")

    query = st.text_input("Enter your question:")
    if query:
        db = load_vector_store()
        qa_chain = RetrievalQA.from_chain_type(
            llm=HuggingFaceHub(
                repo_id="google/flan-t5-base", 
                model_kwargs={"temperature": 0.5, "max_length": 256}
            ),
            retriever=db.as_retriever(),
            return_source_documents=True
        )
        result = qa_chain.run(query)
        st.write("### 📌 Answer")
        st.write(result)

if __name__ == "__main__":
    main()