```

Plain Text

chat_id = "test"
docstore = RedisDocumentStore.from_redis_client(
    redis_client=redis_client,
    namespace="Docstore",
)
index_store = RedisIndexStore.from_redis_client(
    redis_client=redis_client,
    namespace="IndexStore"
)
vector_store = RedisVectorStore(
    redis_url=f"redis://:{REDIS_DB_PASSWORD}@{REDIS_DB_HOST}:{REDIS_DB_PORT}/0",
    index_name="VectorStore" + chat_id,
    index_prefix=chat_id
)

storage_context=StorageContext.from_defaults(
    docstore=docstore, index_store=index_store, vector_store=vector_store
)

index = VectorStoreIndex(
    nodes=[],
    storage_context=storage_context,
    service_context=service_context)

print(index.as_chat_engine(ChatMode.CONTEXT).chat("hola"))

The code above fails. With the following error:

raise response
redis.exceptions.ResponseError: VectorStoretest: no such index

9 comments

LLogan M

It might not be getting created if theres no documents

LLogan M

Just a hunch, I know a few vector stores work like that

bbeaverTango

@LORKA Were you able to mak it work?

LLORKA

In this case the problem was not having any nodes to build the index from

LLORKA

For this use case I moved to EmptyIndex