how to combine a metadata extractor with

how to combine a metadata_extractor with hungging face llm for embeeding and summary extractor process ?
i run this but not work well ..

embed_model = LangchainEmbedding(HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2"))
from llama_index.node_parser import SimpleNodeParser
from llama_index.node_parser.extractors import (
    MetadataExtractor,
    SummaryExtractor,
    QuestionsAnsweredExtractor,
    TitleExtractor,
    KeywordExtractor,
    MetadataFeatureExtractor,
)
from llama_index.langchain_helpers.text_splitter import TokenTextSplitter

text_splitter = TokenTextSplitter(separator=" ", chunk_size=512, chunk_overlap=128)


class CustomExtractor(MetadataFeatureExtractor):
    def extract(self, nodes):
        metadata_list = [
            {
                "custom": node.metadata["document_title"]
                + "\n"
                + node.metadata["excerpt_keywords"]
            }
            for node in nodes
        ]
        return metadata_list


metadata_extractor = MetadataExtractor(
    extractors=[
        TitleExtractor(nodes=5),
        QuestionsAnsweredExtractor(questions=3),
        # SummaryExtractor(summaries=["prev", "self"]),
        # KeywordExtractor(keywords=10),
        # CustomExtractor()
    ],
)

node_parser = SimpleNodeParser(
    text_splitter=text_splitter,
    metadata_extractor=metadata_extractor,
    
)
service_context_embed = ServiceContext.from_defaults(embed_model=embed_model)

from llama_index import SimpleDirectoryReader, DocumentSummaryIndex
itmg_docs = SimpleDirectoryReader(input_files=["./Laporan Tahunan ITMG 2022.pdf"]).load_data()
itmg_front_pages = itmg_docs[0:67]
itmg_content = itmg_docs[68:69]
itmg_docs=itmg_front_pages+itmg_content

itmg_nodes= node_parser.get_nodes_from_documents(itmg_docs, service_context=service_context_embed)
print (f" Finished building node with {len(itmg_nodes)} nodes")

Find answers from the community

how to combine a metadata extractor with