Koenlaermans
Koenlaermans
**Describe the bug** When you add a 3rd retriever to the pipeline as input to the JoinDocuments node, only the first 2 are shown in evaluation. ``` eval_pipe = Pipeline()...
When I split documents with the preprocessor, currently being 256 split with 160 overlap, and pass those to the reader, I sometimes get the error Exception: Exception while running node...
**Is your feature request related to a problem? Please describe.** When I want to train a reader, my dataset uses 40Gb RAM. I only have 12Gb available. Streaming (loading only...