retriever.py

# Step 1: Load and Prepare the Dataset
# First, we need to transform our raw guest data into a format that’s optimized for retrieval.

# We will use the Hugging Face datasets library to load the dataset and convert it into a list of Document objects from the langchain.docstore.document module.

import datasets
from langchain_core.documents import Document

# Load the dataset
guest_dataset = datasets.load_dataset("agents-course/unit3-invitees", split="train")

# Convert dataset entries into Document objects
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
]