ValueError: Metadata length (407) is longer than chunk size (128). Consider increasing the chunk size or decreasing the size of your metadata to avoid this.
include_metadata
to False, turn off that behavior?SentenceSplitter(chunk_overlap=0, include_metadata=False, chunk_size=128)
include_metadata
do in the SentenceSplitter class?nodes = splitter.get_nodes_from_documents(docs, show_progress=True)
excluded_embed_metadata_keys
param when creating the Documents.nodes = pipeline.run(documents=docs, show_progress=True)
Again, only because I excluded the metadata from the embeddings.