Hi I have transferred to using azure openai api, but I am now receiving an error when trying to stream the response: line 165, in gen
delta = response["choices"][0]["delta"]
~~~~~~~^^^
IndexError: list index out of range. I don't receive this error using the standard openai api so I was wondering what could cause this.

I'm getting this error even though I have streaming set to True when creating the query engine. Why is this?

Why aren't these modules recognised?

Does anyone know where I can find index ids?

Hi, is it possible to run multiple queries on the same index asynchronously?

Hi, I'm trying to implement AzureOpenAI using the exact code here: https://gpt-index.readthedocs.io/en/latest/examples/customization/llms/AzureOpenAI.html however it keeps telling me I need to include a deployment_id or engine parameter to create an embedding class. Yet, when i add "engine" or "deployment_id" it says it's not a valid parameter.

Hi, I am using summary and question metadata to help retrieve nodes for querying however it's suddenly stopped working and I am receiving the error: ValueError: Query id f08e5e79-08c9-4bb8-ac61-feae11a10be5 not found in either retriever_dict or query_engine_dict. All the nodes have been created with their associated metadata however it's as if they can't be located for some reason. Any ideas what can be done to fix this?

I'm getting high prompt token counts even for small prompts. for example just passing the word "hello." is giving a token count of over 1000 tokens. surely the token count should be 2 or 3? I'm using the token counting handler from llama index.

Hey, any idea why llama_docs_bot isn't being recognised? Can't be installed with pip install, so I had to clone the repo instead. The files are located in the same area as all the other libraries....

Hi I am all of a sudden getting an error saying storage_context has not been assigned a value (even though it has). I haven't changed my code or deleted any files. This error has just spontaneously started appearing. Any ideas why this could be happening?

Is there a streaming option when querying a composable graph?

I'm trying to query a specific index to get a response however the response is just "None" no matter what the query is. What could be causing this?