retriever

app.py

@@ -3,9 +3,11 @@ from huggingface_hub import InferenceClient, login
 import random
 from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFacePipeline
 from langchain.schema import AIMessage, HumanMessage
+from langchain.tools import Tool
 import os
 import datasets
 from langchain.docstore.document import Document
+from retriever import extract_text
 
 login(token=os.environ["HUGGINGFACEHUB_API_TOKEN"])
 
@@ -26,6 +28,10 @@ docs = [
     for guest in guest_dataset
 ]
 
+
+bm25_retriever = BM25Retriever.from_documents(docs)
+
+
 llm = HuggingFaceEndpoint(
     repo_id="HuggingFaceH4/zephyr-7b-beta",
     task="text-generation",

retriever.py

@@ -0,0 +1,11 @@
+from langchain_community.retrievers import BM25Retriever
+from langchain.tools import Tool
+
+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."
+