seehi
seehi
Zhipu embedding seems not yet supported by [Llama Index](https://github.com/run-llama/llama_index/tree/main/llama-index-integrations/embeddings), need to create a [custom embedding](https://docs.llamaindex.ai/en/stable/examples/embeddings/custom_embeddings/) and pass to [`embed_model`](https://github.com/geekan/MetaGPT/blob/main/metagpt/rag/engines/simple.py#L82). For more info, you can take a look at [RAG Module](https://docs.deepwisdom.ai/main/en/guide/in_depth_guides/rag_module.html).
Seems get wrong answer from LLM, prefer `gpt-4-turbo`
According to the documentation's [Install with Docker](https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html) , it can run normally. Due to the lack of updates or replies by the user for a long time, we will close...
It seems `res["answer_box"]` is a `list` not a `dict`. Is it reproduced? could you post the value of `res` which in this [func](https://github.com/geekan/MetaGPT/blob/main/metagpt/tools/search_engine_serpapi.py#L83)
The type of the field may have changed, or there is a special situation. FYI: @shenchucheng
Make sure the open_llm service port can be connected, such as testing with telnet: `telnet {OPEN_LLM_IP} {OPEN_LLM_PORT}`.
[Topologically sort](https://github.com/geekan/MetaGPT/blob/main/metagpt/schema.py#L378)
Dependent on the capabilities of LLM. FYI: @shenchucheng
FYI: @garylin2099
DI的部分代码未开源，请关注后续版本。