app.py

import pandas as pd
from langchain_core.documents import Document
from langchain_community.vectorstores import FAISS
from langchain.chains import RetrievalQA
from langchain_community.llms import HuggingFacePipeline
from langchain_community.embeddings import HuggingFaceEmbeddings
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
import torch
import gradio as gr

# Load dataset
dataset = pd.read_csv("dataset.csv")

# Convert to LangChain Documents
documents = [
    Document(
        page_content=str(row["answer"]),
        metadata={"question": str(row["question"])}
    )
    for _, row in dataset.iterrows()
]

# Setup embeddings
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")

# Load LLM
model_name = "google/flan-t5-base"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
pipe = pipeline("text2text-generation", model=model, tokenizer=tokenizer, max_length=512,
                device=0 if torch.cuda.is_available() else -1)
llm = HuggingFacePipeline(pipeline=pipe)

# Create vector store
vector_store = FAISS.from_documents(documents, embeddings)
retriever = vector_store.as_retriever(search_kwargs={"k": 3})

# Create QA chain
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    retriever=retriever,
    return_source_documents=True
)

# Chatbot function
def chatbot_interface(question: str) -> str:
    if not qa_chain:
        return "Chatbot backend not initialized properly."
    try:
        response = qa_chain.invoke({"query": question})
        answer = response.get("result", "No answer found.")
        sources = response.get("source_documents", [])
        source_texts = [doc.page_content for doc in sources]
        return f"Answer: {answer}\n\nSources:\n" + "\n".join(f"- {text}" for text in source_texts)
    except Exception as e:
        return f"Error: {e}"

# Gradio UI
interface = gr.Interface(
    fn=chatbot_interface,
    inputs=gr.Textbox(label="Enter your question"),
    outputs=gr.Textbox(label="Response"),
    title="RAG Chatbot",
    description="Ask questions about AI, ChatBots, NLP, and more.",
    theme="default"
)

# Launch the interface
interface.launch()