chenk-gd
chenk-gd
openai确实是限制了最多4个（https://help.openai.com/en/articles/5072263-how-do-i-use-stop-sequences-in-the-openai-api），就是不知道为什么要做这个限制...
好像直接用Assistant就可以，参考assistant_rag.py, 设置一下rag_cfg的‘parser_page_size’参数。
@deshraj Thanks for the reply, I'll be following your progress.
Thank you for reply. So the Infinity server version can have multiple copies of the pod at the same time, using the same minio shared storage?
If the ActionNode is responsible for modularizing the Prompt, but actually with the parameter strgy='complex', each ActionNode builds the Prompt individually and calls LLM to get the result. This seems...
And for the example of printing the Fibonacci series using ActionNode, it also takes the output of the previous ActionNode (SIMPLE_THINK_NODE) as input to the next ActionNode (SIMPLE_CHECK_NODE): ``` elif...
Thank you for answering. When constructing a DAG flow, suppose there are 3 actions A, B and C. If A and B are independent but C depends both on A...