some code i used ```# define llm with

# define llm with HuggingFaceInferenceAPI
llm = HuggingFaceInferenceAPI(
    model_name="HuggingFaceH4/zephyr-7b-beta",
    token=os.environ.get("HUGGINGFACE_ACCESS_TOKEN")
)

# create QdrantClient with the location set to ":memory:", which means the vector db will be stored in memory
vectordb_client = qdrant_client.QdrantClient(location=":memory:")

# create QdrantVectorStore using QdrantClient and the collection name "wonderful_life"
vector_store = QdrantVectorStore(
    client=vectordb_client, collection_name="wonderful_life"
)

# create StorageContext object using the QdrantVectorStore
storage_context = StorageContext.from_defaults(vector_store=vector_store)

node_parser = SentenceSplitter()

service_context = ServiceContext.from_defaults(
    llm=llm,
    embed_model="local:WhereIsAI/UAE-Large-V1",
    callback_manager=callback_manager
)

# Build agents dictionary
query_engine_tools = []

for idx, wiki_title in enumerate(wiki_titles):
    nodes = node_parser.get_nodes_from_documents(city_docs[wiki_title])

    if not os.path.exists(f"./data/{wiki_title}"):
        # build vector index
        vector_index = VectorStoreIndex(
            nodes, service_context=service_context, callback_manager=callback_manager,storage_context=storage_context,
        )
        vector_index.storage_context.persist(persist_dir=f"./data/{wiki_title}")
    else:
        vector_index = load_index_from_storage(
            StorageContext.from_defaults(persist_dir=f"./data/{wiki_title}"),
            service_context=service_context,
            callback_manager=callback_manager,
        )
    # define query engines
    vector_query_engine = vector_index.as_query_engine()