RyanCodrai/turbovec · error · ValueError

Please provide a list of Documents.

Error message

Please provide a list of Documents.

What it means

Raised in TurboQuantDocumentStore.write_documents when the input is not an iterable of haystack Document objects (e.g. a plain string, a single Document, or a list containing non-Document items). It mirrors InMemoryDocumentStore's input-shape validation, failing fast before any lock or mutation instead of an AttributeError on .embedding.

Source

Thrown at turbovec-python/python/turbovec/haystack.py:233

        else:
            docs = [self._reconstruct(data) for data in list(self._u64_to_doc.values())]
        # `return_embedding` is informational here — we never have the
        # full-precision embedding to begin with. Kept for parity.
        return docs

    def write_documents(
        self,
        documents: List[Document],
        policy: DuplicatePolicy = DuplicatePolicy.NONE,
    ) -> int:
        # Match InMemoryDocumentStore's input-shape validation rather
        # than letting a bad input AttributeError on `.embedding`.
        if (
            not isinstance(documents, Iterable)
            or isinstance(documents, str)
            or any(not isinstance(doc, Document) for doc in documents)
        ):
            raise ValueError("Please provide a list of Documents.")

        if policy == DuplicatePolicy.NONE:
            policy = DuplicatePolicy.FAIL

        with self._write_lock:
            return self._write_documents_locked(documents, policy)

    def _write_documents_locked(
        self, documents: List[Document], policy: DuplicatePolicy
    ) -> int:
        if policy == DuplicatePolicy.FAIL:
            # Reference parity (issue #167): InMemoryDocumentStore commits
            # each document as it iterates and raises on the *first*
            # duplicate, so every non-duplicate document preceding it
            # stays persisted — a partial write. Mirror that observable
            # state exactly: validate and commit per document, raising on
            # the first collision. A repeated id within a single call
            # collides with its already-committed first instance, the same

View on GitHub (pinned to ccab9f325e)

Solutions

1. Pass a list of haystack Document instances, e.g. [Document(content=..., embedding=...)].
2. Validate the caller's pipeline output — upstream components may yield raw strings or dicts instead of Documents.
3. Catch the ValueError in ingestion code to give a clearer 'wrong input type' message.

When it happens

Trigger: Thrown at turbovec-python/python/turbovec/haystack.py:233 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of RyanCodrai/turbovec@ccab9f325e (2026-09-06). Data as JSON: /api/errors/6b4388dd38ed9a53. Report an issue: GitHub.