search

peterw / Chat-with-Github-Repo

This repository contains two Python scripts that demonstrate how to create a chatbot using Streamlit, OpenAI GPT-3.5-turbo, and Activeloop's Deep Lake.
https://explodinginsights.com/
MIT License
1.14k stars 168 forks source link

Embeddings are not getting created in Deep Lake #7

Open vinodvarma24 opened 1 year ago

vinodvarma24 commented 1 year ago

When I start the streamlit app, with the .env file as below:

OPENAI_API_KEY=sk-xxxxxxxx ACTIVELOOP_TOKEN=xxxxxxxxxxxxxx DEEPLAKE_USERNAME=vinodvarma24 DEEPLAKE_DATASET_PATH=hub://orgname/embeddings DEEPLAKE_REPO_NAME=embeddings REPO_URL=https://github.com/peterw/Chat-with-Github-Repo SITE_TITLE="Your Site Title"

I'm getting the below message: Saying the dataset is read-only and 'label` got an empty value.

May i know what is the issue here?

hub://talktodata/embeddings loaded successfully.

2023-04-26 07:58:11.346 Deep Lake Dataset in hub://orgname/embeddings already exists, loading from the storage
Dataset(path='hub://orgname/embeddings', read_only=True, tensors=['embedding', 'ids', 'metadata', 'text'])

  tensor     htype    shape    dtype  compression
  -------   -------  -------  -------  ------- 
 embedding  generic   (0,)    float32   None   
    ids      text     (0,)      str     None   
 metadata    json     (0,)      str     None   
   text      text     (0,)      str     None   
2023-04-26 07:58:11.348 `label` got an empty value. This is discouraged for accessibility reasons and may be disallowed in the future by raising an exception. Please provide a non-empty label and hide it with label_visibility if needed.
linbuxiao commented 1 year ago

Maybe orgname should be username?

mikayelh commented 1 year ago

yep, @linbuxiao , you're correct, this issue has been resolved. let me know if you are experiencing any issues!