Massimiliano Pippi

@wanmok can you try cleaning up the context in your debug service? This could be related to https://github.com/run-llama/llama_index/issues/18107

The problem is `query`, albeit a synchronous method, expects a running asyncio loop here https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/vector_stores/llama-index-vector-stores-elasticsearch/llama_index/vector_stores/elasticsearch/base.py#L436 The right fix would be creating an async loop with an executor in the `query`...

Can you double check the version of llama_deploy you're using? `/deployments/create` was added later so my best guess would be you're running an earlier version.

I can't reproduce it, here is what I'm doing, from the root of the repo. ``` $ cd examples/quick_start $ docker run -p 4501:4501 -v .:/opt/quickstart -w /opt/quickstart llamaindex/llama-deploy:v0.2.1 dadddad7b79b3d099afcaae132470e603dca82c32edbd7b1f68bebd5831d4b87...

Hi @eyao27 thanks for reporting! I was able to reproduce but couldn't find the problem at first glance, let me dig into this and I'll report back!

@rehevkor5 first of all, thanks for the feedback! What you read in the article is still true but it dates back to before we introduced the apiserver, see how we...

@abdulhuq-cimulate can you open an issue about the problem with multiple control planes if we don't have one already?

> Edit: A quick fix could be to allow passing in a KV store URI that is a separate service for the control plane to use [here](https://github.com/run-llama/llama_deploy/blob/main/llama_deploy/control_plane/server.py#L89) via env var...

@febus982 this aspect has never been fully fleshed out. Currently the way service replicas receive the message to run a task depends on the message queue implementation: - `SimpleMessageQueue`: consumers...

> But also, if I have a single workflow with multiple steps, will be steps distributed among multiple consumers or a single workflow is bound to a single consumer? (A...