import gradio as gr
from langchain_community.llms import HuggingFaceHub
from langchain_community.document_loaders import PyPDFLoader
from langchain.chains.question_answering import load_qa_chain
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS

def ask_question(query):
    loader = PyPDFLoader("sample_document.pdf")  # ✅ Update this line
    documents = loader.load()
    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
    texts = text_splitter.split_documents(documents)

    embeddings = HuggingFaceEmbeddings()
    db = FAISS.from_documents(texts, embeddings)

    retriever = db.as_retriever()
    relevant_docs = retriever.get_relevant_documents(query)

    llm = HuggingFaceHub(repo_id="google/flan-t5-base", model_kwargs={"temperature":0.5, "max_length":100})
    chain = load_qa_chain(llm, chain_type="stuff")
    response = chain.run(input_documents=relevant_docs, question=query)
    return response

iface = gr.Interface(fn=ask_question, inputs="text", outputs="text", title="MedAssist.AI")
iface.launch()