BerriAI/litellm · error · ValueError

Vector store create is not supported for {custom_llm_provide

Error message

Vector store create is not supported for {custom_llm_provider}

What it means

Provider-support check in vector store creation: after resolving the provider (and api_type for 'provider/model' strings), ProviderConfigManager returned no vector-store config, meaning the provider does not implement vector store creation.

Source

Thrown at litellm/vector_stores/main.py:220

        if "/" in custom_llm_provider:
            api_type, custom_llm_provider, _, _ = get_llm_provider(
                model=custom_llm_provider,
                custom_llm_provider=None,
                litellm_params=None,
            )
        else:
            api_type = None
            custom_llm_provider = custom_llm_provider

        # get provider config - using vector store custom logger for now
        vector_store_provider_config: Final = ProviderConfigManager.get_provider_vector_stores_config(
            provider=litellm.LlmProviders(custom_llm_provider),
            api_type=api_type,
        )

        if vector_store_provider_config is None:
            raise ValueError(f"Vector store create is not supported for {custom_llm_provider}")

        local_vars.update(kwargs)

        # Get VectorStoreCreateOptionalRequestParams with only valid parameters
        vector_store_create_optional_params: Final[VectorStoreCreateOptionalRequestParams] = (
            VectorStoreRequestUtils.get_requested_vector_store_create_optional_param(local_vars)
        )

        # Pre Call logging
        litellm_logging_obj.update_from_kwargs(
            kwargs=kwargs,
            model=None,
            optional_params={
                "name": name,
                **vector_store_create_optional_params,
            },
            litellm_params={
                "litellm_call_id": litellm_call_id,

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Use a provider that supports vector store creation (e.g. openai, azure, bedrock knowledge bases) instead of {custom_llm_provider}.
2. Implement vector store create in a custom provider wrapper.

When it happens

Trigger: Thrown at litellm/vector_stores/main.py:220 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/d8b4dddf512ea46c. Report an issue: GitHub.