Hi Team and , I've done local dev on llama index and it works fine and now wanting to promote this to this. We build a docker image and while trying to run the image we get a regex package error. Has anyone encountered this error before? It only seems to complain about the regex package and it fails at that and the application crashes.

Hello All, from my understanding, the Llama-index Palm2 abstraction uses the google-generative-ai API to talk to Palm2, is there any way can configure to use the Vertex API instead?

Hi Team, I successfully integrated a custom llm using the documentation guide. It works well and as expected with the default querying strategy. However, now I need to enhance retrieval and was looking to implement Hybrid search using BM25 and semantic search your guide from the docs. However, it always asks for an Open AI key (not for embedding). Could not load open ai model etc…
Can someone throw in a few suggestions? Thanks.

Hi Team, I’m using the Custom llm class and want to send out a streaming response. Basically we have a custom llm that hosted and I have an API endpoint that I need to call (Using requests in Python) and return a generator response for streaming. It’s a flask endpoint. Do we have any examples/ documentation for this? Thanks.