Sebastian Husch Lee

@silvanocerza Thanks for the feedback! I was hoping to find some easy tests to mark as unit tests, but I can see that most here don't fit the definition. So...

Hi @julian-risch thanks for checking in. Good to know about the end-to-end test workflow. Unfortunately, I haven't had much time to work on this, but I agree reducing the scope...

Hey, @mayankjobanputra just to let you know we do support some tracking through MLFlow which was added in this PR https://github.com/deepset-ai/haystack/pull/2337. There is some mention of MLFlow in our docs...

The Solution Engineering team would also find this to be very useful! We've had people request being able to track token consumption over time on their hosted pipelines. We currently...

Hey, @hsm207 thanks for the addition! Also, I noticed that the function `get_embedding_count` should be updated https://github.com/deepset-ai/haystack/blob/fffa2288639348690a69e91265f8bc8ff0fa4bc0/haystack/document_stores/weaviate.py#L598-L603 to reflect that not all documents will necessarily have embeddings anymore. Similarily, this...

@hsm207 Thanks for opening the issue in the weaviate library. However, I think we can employ the same method as used by the InMemoryDocumentStore https://github.com/deepset-ai/haystack/blob/7b3d7ee83a277c9a7ab9a8c7f1c0f02bd7d905ad/haystack/document_stores/memory.py#L572-L578 This might not be the...

@hsm207 Thanks for the additional information. In that case, it could be worth just raising a `NotImplementedError` for `get_embedding_count` while we wait for the above-mentioned fixes if you believe this...

This issue https://github.com/deepset-ai/haystack/issues/6706 is related since we currently do not keep page break information when converting a PDF file to a Haystack Document.

Hi @davidsbatista! Thanks for taking on this issue :) I don't think we need to keep the associated text for the use case I am imagining. Basically what we are...

Hmm I'm not entirely sure. Initially I would say that it makes sense to return `List[List[Documents]]`, but often we want a flattened list to be returned since we will often...