retriever.py

from langchain.tools import Tool
from langchain.docstore.document import Document
from sentence_transformers import SentenceTransformer
import torch
import datasets

# Load the dataset
def load_guest_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
    ]

    # Initialize the sentence-transformers model
    model = SentenceTransformer('all-MiniLM-L6-v2')
    embeddings = model.encode([doc.page_content for doc in docs], convert_to_tensor=True)

    # Define the extraction function
    def extract_text(query: str) -> str:
        """Retrieves detailed information about gala guests based on their name or relation."""
        query_embedding = model.encode(query, convert_to_tensor=True)
        similarities = torch.nn.functional.cosine_similarity(query_embedding, embeddings)
        top_k = torch.topk(similarities, k=3)
        results = [docs[i] for i in top_k.indices]
        if results:
            return "\n\n".join([doc.page_content for doc in results])
        else:
            return "No matching guest information found."

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

    return guest_info_tool