fix: optimize unique document filtering with set (#10082)

pull/12372/head
omr 2 years ago committed by Joel
parent c1c13cf828
commit b1946c60d8

@ -27,16 +27,15 @@ class RerankModelRunner(BaseRerankRunner):
:return: :return:
""" """
docs = [] docs = []
doc_id = [] doc_id = set()
unique_documents = [] unique_documents = []
dify_documents = [item for item in documents if item.provider == "dify"] for document in documents:
external_documents = [item for item in documents if item.provider == "external"] if document.provider == "dify" and document.metadata["doc_id"] not in doc_id:
for document in dify_documents: doc_id.add(document.metadata["doc_id"])
if document.metadata["doc_id"] not in doc_id:
doc_id.append(document.metadata["doc_id"])
docs.append(document.page_content) docs.append(document.page_content)
unique_documents.append(document) unique_documents.append(document)
for document in external_documents: elif document.provider == "external":
if document not in unique_documents:
docs.append(document.page_content) docs.append(document.page_content)
unique_documents.append(document) unique_documents.append(document)

Loading…
Cancel
Save