holmesgpt issues

holmes ask shows error

1

holmes ask --api-key="" "what pods are unhealthy in my cluster and why?" When I run this after deploy through helm ( basically i try running as a operator). Pod run...

m-kamran-zortik

Feature request: adding qwencode

6

Summary Is it possible to run Qwencode llm localy? or do you know any tool that I can use to connect holmes to it? Appendix No response

adrien-barret

NOT-READY - oci tool calling working

Avi-Robusta

Getting Error when trying to run holmes command line

1

Hi, I just started learning, and I was able to install holmesgpt using Cutting Edge (instead of pip used pip3). pip3 install "https://github.com/robusta-dev/holmesgpt/archive/refs/heads/master.zip" holmes version HEAD -> master-2d2a5b3 I am...

bhanupratapm02

Cohere support

To run: ``` export COHERE_API_KEY=... poetry run python3 holmes.py ask "what issues does my kubernetes cluster pods have?." --model="cohere/command-r-plus" ``` It looks like there are some internal issues with some...

Avi-Robusta

Bad environment variable in README

7

The instructions for using a self-hosted LLM in the README file say that you need to set the OPENAI_API_BASE variable. This should be OPENAI_BASE_URL to work properly.

AIUser2324

Trying holmesgpt with local ollama3.1 fails w. KeyError: 'name'

Hi, I wanted to give this a try and installed ollama locally. I am able to use the ollama API on http://localhost:11434/api/generate with curl. I evaluated `export OLLAMA_API_BASE=http://localhost:11434`, installed holmes...

suukit