to_rag_tuples#
- scikitplot.corpus.to_rag_tuples(documents)[source]#
Convert documents to
(text, metadata, embedding)tuples.- Parameters:
- documentsSequence[CorpusDocument]
Source documents.
- Returns:
- list[tuple[str, dict, Any]]
Each tuple is
(text, metadata_dict, embedding_or_None). Compatible with most vector storeupsertinterfaces.
- Parameters:
- Return type:
Notes
User note: Feed directly to any vector store:
for text, meta, emb in to_rag_tuples(docs): vector_store.upsert(id=meta["doc_id"], vector=emb, metadata=meta, text=text)
Gallery examples#
corpus WHO European Region local or url per file with examples
corpus WHO European Region local or url per file with examples