Update interim.py

interim.py

@@ -1,4 +1,5 @@
 import os
+import chromadb
 import streamlit as st
 from dotenv import load_dotenv
 from langchain_openai import ChatOpenAI
@@ -6,7 +7,7 @@ from langchain.agents import AgentExecutor, create_openai_tools_agent
 from langchain_core.messages import BaseMessage, HumanMessage
 from langchain_community.tools.tavily_search import TavilySearchResults
 from langchain_experimental.tools import PythonREPLTool
-from langchain_community.document_loaders import DirectoryLoader, TextLoader
+from langchain_community.document_loaders import DirectoryLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import Chroma
 from langchain.embeddings import HuggingFaceBgeEmbeddings
@@ -15,10 +16,15 @@ from langchain_core.runnables import RunnablePassthrough
 from langchain.output_parsers.openai_functions import JsonOutputFunctionsParser
 from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langgraph.graph import StateGraph, END
+from langchain_core.documents import Document
 from typing import Annotated, Sequence, TypedDict
-from langchain_core.tools import tool
 import functools
 import operator
+from langchain_core.tools import tool
+
+
+# Clear ChromaDB cache to fix tenant issue
+chromadb.api.client.SharedSystemClient.clear_system_cache()
 
 # Load environment variables
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
@@ -47,6 +53,7 @@ def agent_node(state, agent, name):
 
 @tool
 def RAG(state):
+    """Use this tool to execute RAG. If the question is related to Japan or Sports, this tool retrieves the results."""
     st.session_state.outputs.append('-> Calling RAG ->')
     question = state
     template = """Answer the question based only on the following context:\n{context}\nQuestion: {question}"""
@@ -72,7 +79,7 @@ if uploaded_files:
     docs = []
     for uploaded_file in uploaded_files:
         content = uploaded_file.read().decode("utf-8")
-        docs.append(TextLoader(file_path=None, content=content).load()[0])
+        docs.append(Document(page_content=content, metadata={"name": uploaded_file.name}))
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=10, length_function=len)
     new_docs = text_splitter.split_documents(documents=docs)
     embeddings = HuggingFaceBgeEmbeddings(model_name="BAAI/bge-base-en-v1.5", model_kwargs={'device': 'cpu'}, encode_kwargs={'normalize_embeddings': True})