Find answers from the community

Updated 10 months ago

Jinai

I have a little issue with ChromaDB server embeddings, QueryEngine is returning: Type is not JSON serializable: numpy.float64. I found this https://github.com/run-llama/llama_index/pull/11458/files which seems to fix the issue, but it's llama_index.core only, how can I do if I'm using legacy (due to JinaAI needs, not included in core)? thanks a lot

9 comments

LLogan M

The jina embeddings not from legacy should be using this fix

There will be no fixes applied to legacy going forward -- it's merely there to help people transition at their own pace

eemmepra

thank you Logan!

eemmepra

but are you sure there's a non-legacy jina version?

eemmepra

I also cannot find ChromaVectorStore in core..

LLogan M

In v0.10.x every integration is a package 👀

Jina has their own package for using their api. There's also a general huggi face embedding package for using them locally (this might be what you are already using from legacy?)

pip install llama-index llama-index-vector-stores-chroma llama-index-embeddings-huggingface

Plain Text

from llama_index.embedding.huggingface import HuggingFaceEmbedding
from llama_index.vector_stores.chroma import ChromaVectorStore

eemmepra

THANK YOU MAN

eemmepra

found it very difficult to find how this new package logic works from documentation!!

eemmepra

I'm afraid I'll never repay you for your support!

LLogan M

The docs/notebooks should have all the updated imports and installs 🙏

llamahub.ai has all the packages/integrations as well

Add a reply