Ben Heckmann
Ben Heckmann
@ZanSara Fixed the lossy tokenizer behavior by using the `return_offsets_mapping` kwarg and then splitting the text at the offsets. I didn't know about this kwarg when I first created this...
Hi @julian-risch. Created a [PR](https://github.com/deepset-ai/haystack/pull/5276) for this. Would be great if someone could take a look!
@you-n-g Looking into this at the moment. Is there any related work of such a checker (papers, repos) to point me in the right direction? Or could you specify some...
Hi @you-n-g, just drafted a first idea, and would really appreciate some feedback. Also, some questions I still have: - What do you mean by "If a factor is not...
@you-n-g Thank you. Regarding (2), you mean it makes sense to keep checking only raw data for now, right? I have added a simple function checking for a missing "factor"...
@microsoft-github-policy-service agree
Update: I have done some more tests and find that the `{rev: true}` option causes this specific issue. Here are some examples of what the cli returns vs what the...
I have done some more tests and keep running into situations with unexpected behavior. For instance, ```js const chats: string[] = await kv.zrange(`user:chat:${userId}`, 0, -1) ``` sometimes returns an empty...