I ve got a nice chatbot server working

bbradcohn

I've got a nice chatbot/server working locally but I've been struggling to deploy it for a few days. It seems like the main issue is my index.json file is very large -- 175MB -- and so it's not compatible with the serverless/lambda pattern generally used by most of the platforms I'd like to deploy on. Does anyone have experience with this or advice on how to deploy apps that use llama_index?

4 comments

jjerryjliu0

hey! have you tried using one of our indexes backed by vector stores? e.g. pinecone/weaviate

bbradcohn

Thanks, currently giving that a try with Weaviate. Is this the notebook to follow? https://github.com/jerryjliu/llama_index/blob/main/examples/vector_indices/WeaviateIndexDemo.ipynb
If so -- I think there's a minor change to the auth client, it seems to now take an API key instead of a username and password for new instances. I've been working on uploading my index to the vector store, but have been running into issues with the requests failing partway through upload. I'll put in some more time working on it and report back.

The new auth line should look like this:

Plain Text

resource_owner_config = weaviate.auth.AuthApiKey(
    api_key="API_KEY_HERE"
)

bbradcohn

Really appreciate your response!

bbradcohn

Was able to get it taken care of by upgrading to the most recent version

Add a reply

Find answers from the community

I ve got a nice chatbot server working