Bug Description

我正在尝试使用https://github.com/run-llama/llama_index/blob/main/llama-index-packs/llama-index-packs-raptor/examples/raptor.ipynb自己进行一些RAPTOR类型的实验。然而，在创建索引时，由于重复的文档ID,代码偶尔会失败。我已经提供了以下代码，其中llama_index_document是一个看起来像这样的Document对象列表：

[
Document(id_='dc2247a2-3a75-4fa1-baa0-4ce074cae205', embedding=None, metadata={'header': 'xxx Inc.'}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='TABLE OF CONTENTS\nAccess Control Policy2 Asset Management Policy8 ', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),

 Document(id_='69ca22a5-37d7-4132-b83b-e631d0992ada', embedding=None, metadata={'header': 'Access Control Policy'}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='Policy Owner: \nEffective Date: 01/28/2024', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n')
]

然后，在创建RAPTOR索引时会出现错误。

版本

0.10.15

重现步骤

from llama_index.core.schema import Document
def convert_to_llama_index_document(parsed_google_docs):
 documents = []
 for doc in parsed_google_docs:
 if len(doc.metadata['header_structure']) > 0:
 header = doc.metadata['header_structure'][-1]
 else:
 header = ''
 documents.append(
 Document(
 text=doc.content,
 metadata={
 "header": header
 }
 )
 )
 return documents
llama_index_documents = convert_to_llama_index_document(parsed_google_docs)
 raptor_pack_google_doc = RaptorPack(
 llama_index_documents,
 embed_model=OpenAIEmbedding(
 model="text-embedding-ada-002"
 ), # used for embedding clusters
 llm=OpenAI(model="gpt-3.5-turbo", temperature=0), # used for generating summaries
 vector_store=vector_store, # used for storage
 similarity_top_k=5, # top k for each layer, or overall top-k for collapsed
 mode="tree_traversal", # sets default mode
 transformations=[
 SentenceSplitter(chunk_size=400, chunk_overlap=50)
 ], # transformations applied for ingestion
 )

相关日志/回溯