retriever.py

# retriever tool
from langchain.tools import Tool
from langchain_community.retrievers import BM25Retriever

# load dataset
import datasets
from langchain.docstore.document import Document


###########################
# Retriever - changed to LangGraph version
###########################
bm25_retriever = BM25Retriever.from_documents(docs)

def extract_text(query: str) -> str:
    """Retrieves detailed information about gala guests based on their name or relation."""
    results = bm25_retriever.invoke(query)
    if results:
        return "\n\n".join([doc.page_content for doc in results[:3]])
    else:
        return "No matching guest information found."

guest_info_tool = Tool(
    name="guest_info_retriever",
    func=extract_text,
    description="Retrieves detailed information about gala guests based on their name or relation."
)
###########################



# no change from smolagents to LangGraph
def load_guest_dataset():
    # 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
    ]

    # Return the tool
    return GuestInfoRetrieverTool(docs)