Julia Yin
Julia Yin
I had the same issue when I initially installed holmes with Brew, then realized that I needed to use pipx to upgrade my holmes version. When I used pipx install...
One idea that came up from our team: Can we have Holmes call the LLM (perhaps a cheaper model) to analyze/summarize the larger outputs, e.g. intelligently truncating the outputs as...
As discussed today: - For tool calls with large outputs (> x tokens), do a first pass of summarization by calling a smaller LLM model - Data summarization on a...
Hi @robbiezhang @kthakar1990, are there any updates on investigating this issue?
Hey @AbelHu @kiashok, are there any updates on this issue? Is it still in the 'fixing' phase?
Does the truncation take place after all of the tools have been called? In that case, it would be valuable to compare the full results from each tool call vs....
Hi @Gomolemo-Matsunyane, can you please provide more details on your cluster configuration and repro steps so we can investigate further?
Hi @MageshSrinivasulu, you can change the second nodepool to be a user pool. We do not allow any system pools to have
Hi @tyler-lloyd, are you looking into this issue / do you have any updates you can share with the customer?
Hi @edoyon90, thanks for reporting this issue. We have tried following the repro steps and were only able to reproduce it intermittently. If you are still facing this issue in...