Hi everyone, I have seen condensed

from llama_index.core import Settings
llm = Anthropic instance

Settings.llm = llm # your defined llm

from llama_index.core.settings import Settings
from llama_index.core.chat_engine import CondenseQuestionChatEngine
from llama_index.core.memory import ChatMemoryBuffer
from llama_index.core.query_engine import BaseQueryEngine
from llama_index.core import VectorStoreIndex, get_response_synthesizer
from llama_index.core.retrievers import VectorIndexRetriever
from llama_index.core.query_engine import RetrieverQueryEngine

from app.engine.templates.system_prompt import get_system_prompt_template
from app.engine.settings import init_settings
from app.engine.memory.multi_chat_memory import MultiChatMemoryBuffer
from app.core.config import settings as app_settings
from app.engine.multi_chat_engine import MultiChatEngine


# build index
index = VectorStoreIndex.from_documents([])

# configure retriever
retriever = VectorIndexRetriever(
    index=index,
    similarity_top_k=2,
)

# configure response synthesizer
response_synthesizer = get_response_synthesizer(
    response_mode="tree_summarize",
)

# assemble query engine
query_engine = RetrieverQueryEngine(
    retriever=retriever,
    response_synthesizer=response_synthesizer,
)


def create_chat_engine(chat_store):
    init_settings()

    memory = MultiChatMemoryBuffer(
        chat_store=chat_store,
        token_limit=app_settings.MAX_TOKEN,
    )

    return CondenseQuestionChatEngine.from_defaults(
        query_engine=query_engine,
        memory=memory,
        llm=Settings.llm,
        system_prompt=get_system_prompt_template().format(),
    )

resp = llm.chat("hey")