Lumi 503 error "The model is overloaded" when asking questions using Gemini key
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 207
- Forks
- 31
- Avg merge
- 3h 33m
- Merged PRs (30d)
- 1
Description
After asking Lumi questions (after adding Google AI Studio key), the first 1-2 responses work, then soon I get Chrome console errors as if your model is overloaded. Is this expected, because Gemini should not get overloaded so easily, or do you have a separate model? I recommend you look at your logs for the 503 errors.
Failed to load resource: the server responded with a status of 503 ()
hook.js:608
Error getting Lumi response: FirebaseError: Model call failed: 503 UNAVAILABLE. {'error': {'code': 503, 'message': 'The model is overloaded. Please try again later.', 'status': 'UNAVAILABLE'}}
bundle.js:65
POST https://us-central1-lumi-459321.cloudfunctions.net/get_lumi_response 503 (Service Unavailable)
bundle.js:982
Error getting Lumi response: FirebaseError: Model call failed: 503 UNAVAILABLE. {'error': {'code': 503, 'message': 'The model is overloaded. Please try again later.', 'status': 'UNAVAILABLE'}}
Let me know if unable to reproduce, or see the 503 errors in your logs, and I can provide the source Arxiv PDF.
Contributor guide
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 reviewing Firebase logs for the get_lumi_response Cloud Function and reproduce the failure after the first 1-2 responses. Compare the logs with the 503 errors shown for bundle.js and Chrome. Done means the cause of the model overload response is identified and the issue has a verified resolution or documented limitation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- firebase, python
- Domain
- ai, api, backend, cloud
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100