microsoft / microsoft/rag-experiment-accelerator
Bicep deployment template lacks an embedding model
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 311
- Forks
- 111
- PR merge metrics
- No merged PRs in 30d
Description
An embedding model is not deployed as part of the bicep template. This means that the indexing script won't work out of the box without manually deploying an embedding model and setting it in configuration.
EDIT: I'm seeing now that the default embedding model is a sentence transformer, all-mpnet-base-v2. I don't see where it gets deployed to AML, so that would still be nice if thats the preferred default.
Also when I ran the indexing script, it seemed like it was working. If there isn't an embedding model deployed, it should error out and alert the user.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the Bicep deployment template and the indexing script, then inspect how the default all-mpnet-base-v2 embedding model is configured and whether it is deployed to AML. Done means a fresh deployment has the required embedding model, or the indexing script clearly errors when it is unavailable.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- azure, python
- Domain
- cloud, devops, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100