Update retriever.py

retriever.py

@@ -1,6 +1,24 @@
 from langchain_community.retrievers import BM25Retriever
 from langchain.tools import Tool
+import datasets
+from langchain.docstore.document 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
+]
 bm25_retriever = BM25Retriever.from_documents(docs)
 
 def extract_text(query: str) -> str: