Shaswata Roy

icon location No one knows when your or my last commit will be. So take it easy—live your life, fix what matters. Don’t limit yourself to just code.

Results 5 comments of Shaswata Roy

Can't initialize models without providing API Key for OpenAI embedding model. Is there an alternative?

> hii i git checkout rb/remove-key-assertion and set variable below set WORKSPACE_DIR=test set LLM_EMBEDDING_MODEL = llama2 set LLM_EMBEDDING_MODEL_BASE_URL = http://127.0.0.1:11434 > > still when i add prompt on step 0...

ollama: 'llama2' not found, try pulling it first

> It's defaulting to using OpenAI for the core model. Can you set `LLM_MODEL="ollama/llama2"` and see if that fixes it? STEP 99 Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new LiteLLM.Info: If...

ollama: 'llama2' not found, try pulling it first

> It looks like litellm thinks the model name is just `llama2`. Did you set `LLM_MODEL=llama2`? Or `LLM_MODEL=ollama/llama2`? It should be the latter yes both done. Still same issue.

ollama: 'llama2' not found, try pulling it first

> I got it running using > ``` > export LLM_MODEL=ollama/llama2 > export LLM_API_KEY= > export LLM_BASE_URL=http://localhost:11434 > PYTHONPATH=`pwd` python opendevin/main.py -d ./workspace/ -i 100 -t "Write a bash script...

Detect and stop infinite loops

> We've mostly been testing on OpenAI--llama (especially local 7B llama) is inevitably going to do worse :/ > > Might be worth creating a special agent for the less-capable...