Sebastian Husch Lee

I was running into the same issue, and I found a few things that helped (but did make training time much slower). 1. Specifically, I found that I needed to...

Closing since the original issue is solved by setting an aggregation strategy to aggregate token predictions.

Hey @ZanSara just to let you know, @elundaeva will be splitting this up into two separate PRs, one for the proposal and one for a draft PR of the code...

Hey @elundaeva thanks for the code! I would link back to the proposal you have written for this node under "Proposed Changes"

Hey @julian-risch yeah I think this is still really relevant. For example, I think I needed to go to the paper and github repo of the recent e5 models from...

Yes I found that we can load e5 in Haystack, but we are unable to easily add the prefixes that Mathis mentioned. Even without the prefixes it already works quite...

Here is a minimal example of how to load the embedding retriever. You can then use it as you normally would an Embedding Retriever. **NOTE:** Make sure to use the...

Hey @Haradai thanks for looking into this! It also looks like if we were to switch the type to `float64` then this error would also be avoided. Take a look...

Hey @julian-risch I noticed that the Github workflows for [tests](https://github.com/deepset-ai/haystack/blob/main/.github/workflows/tests.yml) does not contain an integration-tests workflow similar to the one for unit-tests https://github.com/deepset-ai/haystack/blob/1be39367ac6e17fa7f38d228c86ccc1996c57108/.github/workflows/tests.yml#L102-L121 which I believe means that the tests...

Hey @julian-risch thanks for the feedback! And thanks for the further explanation on the difference between unit and integration tests. > I would suggest to re-write and reduce them so...