run-llama/llama_index · error · NotImplementedError

Delete not implemented for Struct Store Index.

Error message

Delete not implemented for Struct Store Index.

What it means

StructStoreIndex (base class for SQL/JSON GPT index variants) has no node-level deletion: _delete_node unconditionally raises NotImplementedError. The index struct (table containers) does not map deletable nodes, so the base delete machinery cannot apply.

Source

Thrown at llama-index-core/llama_index/core/indices/struct_store/base.py:63

        index_struct: Optional[BST] = None,
        schema_extract_prompt: Optional[BasePromptTemplate] = None,
        output_parser: Optional[OUTPUT_PARSER_TYPE] = None,
        **kwargs: Any,
    ) -> None:
        """Initialize params."""
        self.schema_extract_prompt = (
            schema_extract_prompt or DEFAULT_SCHEMA_EXTRACT_PROMPT
        )
        self.output_parser = output_parser or default_output_parser
        super().__init__(
            nodes=nodes,
            index_struct=index_struct,
            **kwargs,
        )

    def _delete_node(self, node_id: str, **delete_kwargs: Any) -> None:
        """Delete a node."""
        raise NotImplementedError("Delete not implemented for Struct Store Index.")

    @property
    def ref_doc_info(self) -> Dict[str, RefDocInfo]:
        """Retrieve a dict mapping of ingested documents and their nodes+metadata."""
        raise NotImplementedError("Struct Store Index does not support ref_doc_info.")

View on GitHub (pinned to afd0fef371)

Solutions

1. Do not call node deletion on struct-store indexes; rebuild the index from the updated database/JSON instead
2. For SQL indexes, change the data in the database itself and re-create the index
3. Branch on index type in shared pipelines: skip deletion when isinstance(index, StructStoreIndex)

Example fix

# before
index.delete(node_id)  # raises NotImplementedError on StructStoreIndex

# after
index = GPTSQLStructStoreIndex(sql_database, tables=['my_table'])  # rebuild from source data

from llama_index.core.indices.struct_store.base import StructStoreIndex
if not isinstance(index, StructStoreIndex):
    index.delete(node_id)
else:
    logger.warning('node deletion unsupported; rebuild StructStoreIndex from source data')

def supports_node_deletion(index) -> bool:
    from llama_index.core.indices.struct_store.base import StructStoreIndex
    from llama_index.core.indices.property_graph import PropertyGraphIndex
    return not isinstance(index, (StructStoreIndex, PropertyGraphIndex))

try:
    index.delete(node_id)
except NotImplementedError:
    index = build_struct_store_index_from_source()  # rebuild path

When it happens

Trigger: Calling index.delete(node_id), index.delete_nodes([...]), or any API that funnels into _delete_node on a GPTSQLStructStoreIndex/GPTStructStoreIndex/JSON index; also refresh workflows that try to remove stale nodes.

Common situations: Generic document-management code written against VectorStoreIndex being reused for SQL-backed indexes; calling index.delete_refdoc after re-ingesting documents.

Related errors

• Struct Store Index does not support ref_doc_info.
• Cannot insert into an empty index.
• Cannot delete from an empty index.
• ref_doc_info not supported for an empty index.
• Delete is not supported for KG index yet.

AI-assisted analysis of run-llama/llama_index@afd0fef371 (2026-08-15). Data as JSON: /api/errors/00af4db7f8bc4d98. Report an issue: GitHub.