Sebastian Husch Lee
Sebastian Husch Lee
No problem! Thanks for the update
Hey @bglearning thanks for your work on this and for exploring the two different options you proposed. Let's start with your step 1 so > First propose and implement a...
> As such, leaning towards the first approach (Route1) mentioned above i.e. with a MetaDocumentAggregator that has a list of retrievers. Yeah I think I am also leaning towards this...
This will close issue https://github.com/deepset-ai/haystack/issues/7011
It seems that we can check off Weaviate @julian-risch? Integration page here: https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/weaviate
@vblagoje is this safe to close since we do support the BingAPI through the WebRetriever? https://github.com/deepset-ai/haystack/blob/4265c7cd51ed3ad26e2de7a8726dc8fccce066e1/haystack/nodes/retriever/web.py#L28
Hey @julian-risch could we also add the `nltk` support for the DocumentSplitter in this list? That is a very common feature we are using right now in Haystack v1.
And to clarify, is the `TextClassifier` in this list referring to the `TransformersQueryClassifier` from Haystack v1?
@julian-risch thanks for the clarification! @bglearning might also be taking a look at porting the `TransformersQueryClassifier`, so tagging him here.
> But it's not only prompts, the same would apply to a ranker too. Just out of curiosity, what scenario do you have in mind where this would be relevant...