Closed bilgeyucel closed 1 month ago
Similar to https://github.com/deepset-ai/haystack-core-integrations/issues/904.
To fix this, we can follow an approach similar to https://github.com/deepset-ai/haystack-core-integrations/pull/907
But at this point, I also have doubts about the format produced by the DocumentSplitter
, which seems not to be compatible with several Document Stores.
IMO, fixing DocumentSplitter
is a better solution. #907 seems more like a workaround
I think that for Document Stores that greatly limit the types of metadata values allowed, discarding invalid metadata and warning the user may be a good approach.
E.g., Chroma only supports str, int, float, bool
. How can we store this structured information?
However, I agree with you that we should think of better choices for _split_overlap
type.
Describe the bug
PineconeDocumentStore
raises an error when I try to index a document that was split byDocumentSplitter
. Error message 👇Document object that raises the error is below.
"_split_overlap"
seems to be a list of dictTo Reproduce
Describe your environment (please complete the following information):