BerriAI/litellm · error · ValueError

custom_llm_provider is required for initializing vector stor

Error message

custom_llm_provider is required for initializing vector store, got custom_llm_provider={custom_llm_provider}

What it means

Config validation while loading vector stores from config.yaml: custom_llm_provider is missing/None in the entry's litellm_params, so no provider backend can be selected. The offending value is echoed.

Source

Thrown at litellm/vector_stores/vector_store_registry.py:406

    def load_vector_stores_from_config(self, vector_stores_config: list[dict]):
        """
        Loads vector stores from the litellm proxy config.yaml
        """
        for vector_store_config in vector_stores_config:
            # cast to VectorStoreConfig
            litellm_vector_store_config = LiteLLM_VectorStoreConfig(**vector_store_config)
            vector_store_name = litellm_vector_store_config.get("vector_store_name")
            vector_store_litellm_params: dict[str, Any] = litellm_vector_store_config.get("litellm_params") or {}

            vector_store_id = vector_store_litellm_params.get("vector_store_id")
            if vector_store_id is None:
                raise ValueError(
                    f"vector_store_id is required for initializing vector store, got vector_store_id={vector_store_id}"
                )
            custom_llm_provider = vector_store_litellm_params.get("custom_llm_provider")
            if custom_llm_provider is None:
                raise ValueError(
                    f"custom_llm_provider is required for initializing vector store, got custom_llm_provider={custom_llm_provider}"
                )

            litellm_managed_vector_store = LiteLLM_ManagedVectorStore(
                vector_store_id=vector_store_id,
                custom_llm_provider=custom_llm_provider,
                litellm_params=vector_store_litellm_params,
                vector_store_name=vector_store_name,
                vector_store_description=vector_store_litellm_params.get("vector_store_description"),
                vector_store_metadata=vector_store_litellm_params.get("vector_store_metadata"),
                created_at=datetime.now(timezone.utc),
                updated_at=datetime.now(timezone.utc),
            )
            self.vector_stores.append(litellm_managed_vector_store)

        verbose_logger.debug(
            "all loaded vector stores = %s",
            json.dumps(self.vector_stores, indent=4, default=str),

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Set custom_llm_provider (e.g. 'openai') when initializing the vector store.

When it happens

Trigger: Thrown at litellm/vector_stores/vector_store_registry.py:406 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/0a39ed0ed2b6f417. Report an issue: GitHub.