retriever.py

import datasets
from langchain.docstore.document import Document
from langchain_community.retrievers import BM25Retriever
from smolagents import Tool

def load_guest_dataset():
    try:
        guest_dataset = datasets.load_dataset("agents-course/unit3-invitees", split="train")
        docs = [
            Document(
                page_content="\n".join([
                    f"Name: {guest['name']}",
                    f"Relation: {guest['relation']}",
                    f"Description: {guest['description']}",
                    f"Email: {guest['email']}"
                ]),
                metadata={"name": guest["name"]}
            )
            for guest in guest_dataset
        ]
    except Exception as e:
        # Fallback mock dataset
        docs = [
            Document(
                page_content="\n".join([
                    "Name: Dr. Nikola Tesla",
                    "Relation: old friend from university days",
                    "Description: Dr. Nikola Tesla is an old friend from your university days. He's recently patented a new wireless energy transmission system.",
                    "Email: nikola.tesla@gmail.com"
                ]),
                metadata={"name": "Dr. Nikola Tesla"}
            )
        ]
    return docs