bozo32

quota exceeded...when I know it is a good openAI API key

3

Failed Files: rutte speech.txt Reason: Error getting embeddings: error, status code: 429, message: You exceeded your current quota, please check your plan and billing details.

homebrew for the manual dependencies brew install golang, poppler, node@19

1 high severity vulnerability To address all issues, run: npm audit fix (vault) peter@peter vault-ai % npm audit # npm audit report webpack 5.0.0 - 5.75.0 Severity: high Cross-realm object...

OOM with mixtral 8x22b

6

### What is the issue? OOM with mixtral on an A100 80gb. gets 47/57 layers onto the GPU and then chokes. running off the binary. just redownloaded it and re-ran...

import error

2

ImportError: cannot import name 'GPTSimpleVectorIndex' from 'llama_index' (/home/tamas002/miniconda3/envs/lama_difu/lib/python3.10/site-packages/llama_index/__init__.py) history conda create -n lama_difu python==3.10 conda activate lama_difu git clone... pip install -r.... python main.py

just updated this am. UI authenticates and then blank screen (pure white) on 3 separate browsers

1

# Bug Report ## Description **Bug Summary:** The UI accepts my password then I get a blank screen **Steps to Reproduce:** update to latest docker docker run -d -p 3030:8080...

**Describe the bug** It worked a couple of days ago. Now when I try to call Ollama I get the error Ollama call failed with status code 404: model 'llama3:latest'...

feature: adding 'mps' backend for GPU acceleration on macOS m1

6

aiserver.py is built around cuda. This was totally reasonable till about 3 months ago. Now there is PyTorch support for m1 hardware This requires recognition of torch.device('mps')...which does not have...

binary install on a cluster produces extra information in responses in both cpu and gpu mode

1

### What is the issue? I installed ollama on the university cluster following the instructions here: The download page has a list of assets, one of them is binary for...

api key headaches

10

Hi I managed to get it up and running fairly easily on a M1 Mac. the only issue I'm having is that when I go to index a newly uploaded...