Settings.callback_manager = callbackmanager when requests A and B are running in parallel kinda, where it starts from A then to B sequential. B would override A's callback_manager right? TypeError: llama_index.core.indices.vector_store.retrievers.retriever.VectorIndexRetriever() got multiple values for keyword argument 'callback_manager'vector_query_engine = base_index.as_query_engine(
vector_store_kwargs={"qdrant_filters": vector_filters},
callback_manager=callback_manager,
node_postprocessors=[rerank],
similarity_top_k=10,
use_async=True
)llm = OpenAI(..., callback_manager=callback_manager) embed_model = OpenAIEmbedding(..., callback_manager=callback_manager) index = VectorStoreIndex(...., embed_model=embed_model, callback_manager=callback_manager) rerank = CohereRerank(..., callback_manager=callback_manager) # pass in the llm query_engine = index.as_query_engine(..., llm=llm)
llama_index.core.indices.vector_store.retrievers.retriever.VectorIndexRetriever() got multiple values for keyword argument 'callback_manager'do you have any idea why this error would happen.
llama-index-core==0.10.44 llama-index-llms-azure-openai==0.1.8 llama-index-vector-stores-qdrant==0.1.3 llama-index-embeddings-huggingface==0.1.4 llama-index-callbacks-arize-phoenix==0.1.5
token_counter = TokenCountingHandler(
tokenizer=tiktoken.encoding_for_model("gpt-4").encode,
verbose=True
)
callback_manager = CallbackManager([token_counter])
embedding_model = EmbeddingModel(callback_manager=callback_manager)
client = qdrant_client.AsyncQdrantClient(
url=os.getenv('QDRANT_CLOUD_URL'),
api_key=os.getenv('QDRANT_CLOUD_API_KEY')
)
vector_store = QdrantVectorStore(
aclient=client,
collection_name=db_config.get('QDRANT_COLLECTION')
)
base_index = VectorStoreIndex.from_vector_store(
vector_store=vector_store,
callback_manager=callback_manager,
embed_model=embedding_model
)
llm = AzureLLMClient(callback_manager=callback_manager)vector_query_engine = base_index.as_query_engine(
vector_store_kwargs={"qdrant_filters": vector_filters},
llm=llm,
node_postprocessors=[rerank],
similarity_top_k=10,
use_async=True
)
vector_tool = QueryEngineTool.from_defaults(
query_engine=vector_query_engine,
)
router_query_engine = RouterQueryEngine(
llm=llm,
selector=LLMSingleSelector.from_defaults(llm=llm),
query_engine_tools=[
summary_tool,
vector_tool,
]
)