Update retriever.py

retriever.py

@@ -50,16 +50,41 @@
 #     return GuestInfoRetrieverTool(docs)
 
 
-from langchain_community.vectorstores import Chroma
-from langchain_openai import OpenAIEmbeddings
-
-def get_retriever():
-    """创建并返回检索器"""
-    embeddings = OpenAIEmbeddings()
-    vectorstore = Chroma(
-        embedding_function=embeddings,
-        persist_directory="./chroma_db",
-        collection_name="rag_docs"
+import datasets
+from langchain.docstore.document import Document
+from langchain_community.retrievers import BM25Retriever
+from langchain.tools import Tool
+
+# 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"]}
     )
-    return vectorstore.as_retriever(search_kwargs={"k": 5})
+    for guest in guest_dataset
+]
+
+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."
+)