Shilin HE

We would suggest wrap around the taskweaver and automatically send a request (e.g., pull the data) to Taskweaver on behalf of human when starting the services.

Thanks for the suggestion. We will try to support it in the future!

The issue of `"send_to" field is None` is usually caused by the incorrect LLM response. In TaskWeaver, the response is expected to follow a predefined schema (in `json`). However, if...

Close as no more activity

Hi @cswangxiaowei, could you check any configuration related the codespace? I can see the codespace after switching to my private GitHub account. 

We don't directly support the baichuan model, but you can configure it by using the `litellm` api_type. In `litellm`, you can follow instructions in this [page](https://docs.litellm.ai/docs/providers/vllm) to connect via `vllm`...

Thanks for sharing the information. For the baichuan model, are you referring to the open-sourced one or the commercial one? Do you have any docs about the Baichuan on QWen?...

Hi, @cswangxiaowei, the issue was triggered because Baichuan2 on QWen does not support the streaming mode. However, we also find that the context length of Baichuan2 7B/13B on QWen (not...

@jackiezhangcn Hi, It is because that the LLM model is not correctly referred. You should ensure the running ollama model same as the one you configured in the taskweaver_config.json. For...

Since this is a 404 error, it should be related to the `ollama serving`. Can you check whether the port is correctly configured, and you can send request to the...