Rolnan Fang

please try to install openai==0.28.0

have you deployed llama-2-13b-chat on local? If not, you should first deploy the model via [https://github.com/lm-sys/FastChat/blob/main/docs/langchain_integration.md](url), then you can use model to generate by api call

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 -m fastchat.serve.model_worker \ --port 31021 --worker http://localhost:31021 \ --host localhost \ --model-names your-model-name \ --model-path /model/path \ --max-gpu-memory 31Gib \ --dtype float16 \ --num-gpus 8 see in [https://github.com/zjunlp/AutoAct/blob/main/Scripts/model_bash/single_model.sh](url)...

> [@aysan0](https://github.com/aysan0) Yeah. This was quite a mole hunt! I need some help with testing this out first. I pushed this to the [bug fix branch](https://github.com/unclecode/crawl4ai/tree/2025-MAR-ALPHA-1). Could you pull this,...