Find answers from the community

Updated 10 months ago

Hey all, trying to instantiate a

Hey all, trying to instantiate a pipeline using a local Qdrant vector store and Huggingface embedding but am running into this error now, thoughts?
Attachments
image.png
image.png
L
D
W
12 comments
πŸ€” Can you try with a fresh venv?

For example (just guessing on the deps you'll need here)

Plain Text
python -m venv venv
source venv/bin/activate
pip install llama-index llama-index-vector-stores-qdrant llama-index-embeddings-huggingface
after fresh import
Attachment
image.png
Attachment
image.png
thanks although it's throwing that error when I am trying to import the HuggingFaceEmbedding
I think some imports are incorrect in the huggingface file. Let me check on my system
getting this with the openai embeddings now as well
Attachment
image.png
is there a notebook synced with an old release version that will work for a very simple RAG demo with local vector store and local documents? I can't use a LlamaPack here and am running into lots of errors trying to quickly whip up the simple RAG demo (ie. can't find the correct llamaindex version that works with any of these notebooks)
Attachment
image.png
I just did a fresh installation on colab and I'm able to import Huggingface embedding correctly
Attachment
image.png
thanks, are you able to point me to the versions that will work with this notebook? https://docs.llamaindex.ai/en/stable/examples/vector_stores/QdrantIndexDemo.html
Current version is the stable version. I think that you should reset the current session and try installing llama-index freshly once. It should work then
Add a reply
Sign up and join the conversation on Discord