Update agent.py

agent.py

@@ -15,8 +15,12 @@ from langchain_core.tools import tool
 from langchain.tools.retriever import create_retriever_tool
 from supabase.client import Client, create_client
 from typing import TypedDict, List, Annotated
-from langchain.vectorstores.chroma import Chroma
 from langchain.agents.agent_toolkits import create_retriever_tool
+from langchain_community.document_loaders import TextLoader
+from langchain_community.vectorstores import FAISS
+from langchain_openai import OpenAIEmbeddings
+from langchain_text_splitters import CharacterTextSplitter
+
 
 load_dotenv()
 
@@ -124,25 +128,14 @@ sys_msg = SystemMessage(content=system_prompt)
 
 
 def create_retriever_tool(persist_directory="vector_store"):
-    # Initialize embeddings
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #dim=768
-    
-    # Create/load Chroma vector store - must use same parameter name as in your function
-    vector_store = Chroma(
-        embedding_function=embeddings,
-        persist_directory=persist_directory  # Use the parameter, not hardcoded path
-    )
+    documents = TextLoader("state_of_the_union.txt").load()
+    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+    texts = text_splitter.split_documents(documents)
+    retriever = FAISS.from_documents(texts, OpenAIEmbeddings()).as_retriever()
     
-    # Create retriever tool
-    retriever_tool = create_retriever_tool(
-        retriever=vector_store.as_retriever(),
-        name="Question Search",
-        description="A tool to retrieve similar questions from a vector store.",
-    )
-    
-    return retriever_tool, vector_store
-       
-tool, store = create_retriever_tool(persist_directory="/home/wendy/Downloads")
+    #docs = retriever.invoke("What did the president say about Ketanji Brown Jackson")
+    #pretty_print_docs(docs)
+
 
 tools = [
     multiply,