run-llama/llama_index · error · ValueError

Vector memory does not support get_all method, can only retr

Error message

Vector memory does not support get_all method, can only retrieve based on input.

What it means

Error "Vector memory does not support get_all method, can only retrieve based on input." thrown in run-llama/llama_index.

Source

Thrown at llama-index-core/llama_index/core/memory/vector_memory.py:157

        if input is None:
            return []

        # retrieve from index
        retriever = self.vector_index.as_retriever(**self.retriever_kwargs)
        nodes = retriever.retrieve(input or "")

        # retrieve underlying messages
        return [
            ChatMessage.model_validate(sub_dict)
            for node in nodes
            for sub_dict in node.metadata["sub_dicts"]
        ]

    def get_all(self) -> List[ChatMessage]:
        """Get all chat history."""
        # TODO: while we could implement get_all, would be hacky through metadata filtering
        # since vector stores don't easily support get()
        raise ValueError(
            "Vector memory does not support get_all method, can only retrieve based on input."
        )

    def _commit_node(self, override_last: bool = False) -> None:
        """Commit new node to vector store."""
        if self.cur_batch_textnode.text == "":
            return

        if override_last:
            # delete the last node
            # This is needed since we're updating the last node in the vector
            # index as its being updated. When a new user-message batch starts
            # we already will have the last user message group committed to the
            # vector store index and so we don't need to override_last (i.e. see
            # logic in self.put().)
            self.vector_index.delete_nodes([self.cur_batch_textnode.id_])

        self.vector_index.insert_nodes([self.cur_batch_textnode])

View on GitHub (pinned to afd0fef371)

Solutions

1. Call get(input=...) with a query string instead of get_all().
2. Use the primary ChatMemoryBuffer if you need the full unfiltered history.

When it happens

Trigger: Thrown at llama-index-core/llama_index/core/memory/vector_memory.py:157 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of run-llama/llama_index@afd0fef371 (2026-08-15). Data as JSON: /api/errors/5b62879c7b45c8ec. Report an issue: GitHub.