search

Significant-Gravitas / AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
https://agpt.co
Other
168.44k stars 44.43k forks source link

Ollama no longer supported? #8023

Open Iliceth opened 2 months ago

Iliceth commented 2 months ago

⚠️ Search for existing issues first ⚠️

Which Operating System are you using?

Linux

Which version of AutoGPT are you using?

Stable (branch)

What LLM Provider do you use?

Other (detail in issue)

Which area covers your issue best?

Other

What commit or version are you using?

2618d1d87cd04623c848df870800f328fe36bc83

Describe your issue.

The documentation clearly states the possibility to use ollama, via running a model in ollama, then starting the server, starting the builder and then select the last option in the model list in the blocks. The model list always stays the same though, whatever model I run in ollama and the last model in the list is llama3.1:405b which it says in the terminal I don't have, which is correct.

Does that mean that ollama running is not detected by AutoGPT? As the list does not show anything else whatever model I run. Or does the one referring to the model running in ollama not get renamed? Or do I miss something else possibly?

Upload Activity Log Content

No response

Upload Error Log Content

No response

Iliceth commented 2 months ago

I found a way to get it working, by editing the llm.py block file. That means I have to add every model I wish to run via ollama by hand each time I get another one, right?

ntindle commented 1 month ago

This should be possible. Can you tell me more about the modifications you had to make

github-actions[bot] commented 20 hours ago

This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.