Sebastian Husch Lee
Sebastian Husch Lee
For some additional context it's true that we need to create a new instance of a `streaming_callback` for every `Pipeline.run` done in a deployment setting. E.g. here is how we...
Hey @srini047 thanks for the work on this! I wanted to make a suggestion on changing the PR slightly: I think instead of mapping each row to a single Document...
Hey @srini047 those are great points! And I agree that CSV files can easily become too large to easily work with. However, I'd like to suggest a different approach that...
> @sjrl Agree to this. But I have a small concern. Currently the splitter can split the following regexes: \n\n, \f, ., and . But loading a CSV as bytes...
Ahh okay good to know. Is there a place we could check to see if that is still the case? They do have the ability to return tool call information...
More detail specifically in this comment https://github.com/deepset-ai/haystack-experimental/pull/120#discussion_r1806334949 > The HF API allows this use case, but I made this decision for the following reasons: > - the streaming output to...
@bglearning new version has been released v3.7.0!
This will definitely require an investigation to see if it can be made to generalize. I brought it up initially because deepset requires this since we store our files in...
After discussion with @julian-risch about this an initial idea for completing this issue could be creating a `S3FileDownloader` component which would mimic the current one we are using in deepset....
@wochinge would this be nice to have for the platform?