Azure / Azure/azureml-examples
azureml.rag.utils.deployment: No module named 'openai.api_resources'
- Dominant language
- Jupyter Notebook
- Stars
- 2k
- Forks
- 1.7k
- Avg merge
- 18h 18m
- Merged PRs (30d)
- 2
Description
### Operating System
Linux
### Version Information
python 3.8
azureml-0.2.7
### Steps to reproduce
Follow steps in https://github.com/Azure/azureml-examples/blob/main/sdk/python/generative-ai/rag/notebooks/faiss/scheduled_update_faiss_index.ipynb
Run the rag deployment part: `from azureml.rag.utils.deployment import infer_deployment`
It reports error: ModuleNotFoundError: No module named 'openai.api_resources'
It seems `openai.api_resources` has been deprecated.
### Expected behavior
No error
### Actual behavior
ModuleNotFoundError: No module named 'openai.api_resources'
### Addition information
_No response_
Contributor guide
Research direction
Start with the scheduled_update_faiss_index.ipynb notebook and reproduce the RAG deployment step that imports infer_deployment from azureml.rag.utils.deployment. Trace that import to the dependency reference for openai.api_resources and check the installed package versions listed in the issue. Done means the deployment import runs without ModuleNotFoundError.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- azure, jupyter-notebook, python
- Domain
- cloud, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100